docs(evaluators + playgrounds): add #105
Conversation
|
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. Caution Review failedThe pull request is closed. WalkthroughAdds new documentation pages for Playgrounds and Evaluators, updates site navigation to include Playgrounds and Evaluators groups, reorders two paragraphs in an existing datasets page, and adds Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor User
participant UI as App UI
participant Gen as Generate Evaluator
participant Store as Evaluator Store
User->>UI: Open Evaluators library
User->>UI: Select "Generate Evaluator"
UI->>Gen: Send mapped column(s) + options
Gen-->>UI: Return proposed prompt template
User->>UI: Edit template & Test on sample rows
UI-->>User: Show test results (pass/fail, outputs)
User->>UI: Save evaluator
UI->>Store: Persist evaluator definition
Store-->>UI: Confirm saved
UI-->>User: Evaluator appears in library
sequenceDiagram
autonumber
actor User
participant UI as Playground
participant Col as Prompt Column
participant Model as LLM Provider
User->>UI: Configure Prompt Column (messages, vars, model, schema/tools)
loop For each row
UI->>Col: Render prompt using row variables
Col->>Model: Send prompt (with schema/tool config)
Model-->>Col: Return response (or structured/tool-call)
Col-->>UI: Store response in target column cell
end
UI-->>User: Display updated table cells
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro 💡 Knowledge Base configuration:
You can enable these sources in your CodeRabbit configuration. ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (6)
✨ Finishing Touches🧪 Generate unit tests
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
There was a problem hiding this comment.
Caution
Changes requested ❌
Reviewed everything up to 5b40173 in 2 minutes and 36 seconds. Click for details.
- Reviewed
642lines of code in10files - Skipped
37files when reviewing. - Skipped posting
15draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. datasets/quick-start.mdx:8
- Draft comment:
Consider adding alt attributes totags for improved accessibility.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
2. evaluators/custom-evaluator.mdx:3
- Draft comment:
Remove trailing whitespace in the description and add alt attributes to images for accessibility. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
3. evaluators/evaluator-library.mdx:8
- Draft comment:
Add alt attributes totags to enhance accessibility.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
4. evaluators/intro.mdx:8
- Draft comment:
Reword header 'Evaluators types' to 'Evaluator Types' for clarity and consistency. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
5. evaluators/made-by-traceloop.mdx:10
- Draft comment:
Consider adding alt attributes totags to improve accessibility.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
6. mint.json:168
- Draft comment:
Verify the new navigation groups ('Playgrounds' and 'Evaluators') are ordered consistently with design requirements. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
7. playgrounds/columns/column-management.mdx:10
- Draft comment:
Consider adding alt attributes to image tags for better accessibility compliance. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
8. playgrounds/columns/data-columns.mdx:8
- Draft comment:
Add alt attributes totags for accessibility improvements.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
9. playgrounds/columns/prompt.mdx:15
- Draft comment:
Add alt attributes totags to support accessibility.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
10. playgrounds/quick-start.mdx:5
- Draft comment:
Use 'interactive spreadsheets' (plural) instead of 'spreadsheet' for grammatical accuracy. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
11. playgrounds/quick-start.mdx:9
- Draft comment:
Consider adding alt attributes totags for accessibility.
- Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
12. evaluators/custom-evaluator.mdx:3
- Draft comment:
Typographical note: There is an extra space at the end of the description in the front-matter on line 3. Consider removing the trailing whitespace. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 10% vs. threshold = 50% While technically correct, this is an extremely minor formatting issue that doesn't affect functionality. It's the kind of thing that should be handled by automated formatting tools or linters, not manual code review. The rules specifically say not to make comments that are obvious or unimportant. The trailing space could potentially cause issues with some markdown processors or frontmatter parsers. Maybe it's more important than I think. Even if it could cause issues, this is still the kind of thing that should be caught by automated tools, not human review. The rules specifically say not to make obvious or unimportant comments. This comment should be deleted as it addresses a trivial formatting issue that would be better handled by automated tools.
13. evaluators/intro.mdx:8
- Draft comment:
Typo: The header '## Evaluators types' might be better phrased as '## Evaluator Types' for clarity and grammatical correctness. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 20% vs. threshold = 50% While this is a real grammatical issue, it's a very minor one in documentation. The rules state not to make purely informative comments and to only comment if there's clearly a code change required. Documentation typos, unless they significantly impact understanding, probably don't meet this bar. The grammatical error could potentially cause confusion for readers, and proper documentation is important for user experience. While documentation quality matters, this particular issue is extremely minor and doesn't impact comprehension - readers will easily understand the meaning regardless of the grammatical imperfection. Delete this comment as it's too minor and doesn't meet the bar for requiring a code change.
14. playgrounds/columns/column-management.mdx:3
- Draft comment:
Typographical suggestion: The description could be rephrased for clarity. Consider revising "Learn all columns general functionalities" to "Learn all columns' general functionalities" or "Learn all general functionalities of columns." - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 10% vs. threshold = 50% While the grammar suggestion is technically correct, this is a very minor issue in documentation metadata that doesn't affect functionality or user understanding. The current phrasing, while not perfect, is still clear enough. The rules state not to make purely informative comments or comments about obvious/unimportant issues. The grammar issue could potentially affect documentation quality and professionalism. Poor grammar in user-facing text might reduce credibility. While grammar is important, this is an extremely minor issue in metadata that doesn't significantly impact readability or understanding. The rules explicitly say not to make unimportant comments. Delete this comment as it addresses a trivial grammar issue that doesn't meaningfully impact documentation quality or user understanding.
15. playgrounds/quick-start.mdx:5
- Draft comment:
Typo: In the sentence "Playgrounds are interactive spreadsheet..." consider using "interactive spreadsheets" (plural) for grammatical consistency. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 10% vs. threshold = 50% While this is technically correct and the comment is about changed code, our rules say not to make purely informative comments. This is a very minor grammatical issue in documentation that doesn't affect understanding. The meaning is perfectly clear either way. We should focus on substantive issues that require code changes. The grammar mistake could make the documentation look unprofessional. Documentation quality is important for user experience. While documentation quality matters, this is an extremely minor issue that doesn't impact comprehension. Our rules explicitly say to avoid obvious or unimportant comments. Delete this comment as it's too minor and doesn't require a meaningful code change.
Workflow ID: wflow_Cu0H6FydFupMJiUS
You can customize 
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (33)
datasets/quick-start.mdx (1)
48-52: Grammar nit: “Published versions” and SDK wordingMinor copy polish to improve clarity and correctness.
Apply this diff:
-1. Click **Publish Version** to create a stable snapshot -2. Published versions are immutable -3. Publish versions are accessible in the SDK +1. Click **Publish Version** to create a stable snapshot. +2. Published versions are immutable. +3. Published versions are accessible via the SDK.evaluators/intro.mdx (2)
8-13: Heading + list style: singularize and align capitalization“Titled section” and bullet capitalization are a bit off. Recommend tightening phrasing and casing.
Apply this diff:
-## Evaluators types +## Evaluator types @@ -- **Custom evaluators** - Create your own evaluation logic tailored to specific needs -- **Built-in evaluators** - pre-configured evaluators by Traceloop for common assessment tasks +- **Custom evaluators** — Create your own evaluation logic tailored to specific needs. +- **Built-in evaluators** — Preconfigured evaluators by Traceloop for common assessment tasks.
14-16: Word choice: “define” → “use” (or “create”)“Select the evaluator you want to define” reads oddly in the library context. Suggest:
-In the Evaluator Library, select the evaluator you want to define. -You can either create a custom evaluator by clicking **New Evaluator** or choose one of the prebuilt **Made by Traceloop** evaluators. +In the Evaluator Library, select the evaluator you want to use. +You can create a custom evaluator by clicking **New Evaluator**, or choose a prebuilt **Made by Traceloop** evaluator.playgrounds/columns/column-management.mdx (7)
6-6: Grammar: subject–verb agreementChange “as your analysis evolve” → “as your analysis evolves”.
-Columns in the Playground can be reordered, edited, or deleted at any time to adapt your workspace as your analysis evolve. Understanding how to manage columns effectively helps you maintain organized and efficient playgrounds. +Columns in the Playground can be reordered, edited, or deleted at any time to adapt your workspace as your analysis evolves. Understanding how to manage columns effectively helps you maintain organized and efficient playgrounds.
8-10: Consistency: “Column Settings” (singular) across heading and bodyHeading currently says “Columns Settings” while body says “Column Settings”. Recommend singular for both.
-## Columns Settings +## Column Settings -Column Settings lets you hide specific columns from the Playground and reorder them as needed. To open the settings, click the Playground Action button and select Column Settings +Column Settings let you hide specific columns from the Playground and reorder them as needed. To open the settings, click the Playground Action button and select Column Settings.
10-15: Accessibility: add alt text to imagesAdd descriptive alt attributes for screen readers.
-<img - className="block dark:hidden" - src="/img/playground/play-action-light.png" -/> -<img className="hidden dark:block" src="/img/playground/play-action-dark.png" /> +<img + alt="Playground action menu button (light theme)" + className="block dark:hidden" + src="/img/playground/play-action-light.png" +/> +<img + alt="Playground action menu button (dark theme)" + className="hidden dark:block" + src="/img/playground/play-action-dark.png" +/>
16-19: Flow + repetition: vary sentence starts and add periodReduce repetitive “To …” starters and add missing punctuation.
-To change the column order, use the six-dot handle on the right side of each column to simply drag the column into the desired position. - -To hide a column, toggle its switch in the menu. +To change the column order, drag the six-dot handle on the right side of each column to the desired position. + +To hide a column, toggle its switch in the menu.
19-28: Accessibility: add alt text to settings imagesMirror the alt improvements for the settings screenshots.
-<img - className="block dark:hidden" - src="/img/playground/play-column-settings-light.png" - style={{maxWidth: '600px'}} -/> -<img - className="hidden dark:block" - src="/img/playground/play-column-settings-dark.png" - style={{maxWidth: '600px'}} -/> +<img + alt="Column settings modal (light theme)" + className="block dark:hidden" + src="/img/playground/play-column-settings-light.png" + style={{maxWidth: '600px'}} +/> +<img + alt="Column settings modal (dark theme)" + className="hidden dark:block" + src="/img/playground/play-column-settings-dark.png" + style={{maxWidth: '600px'}} +/>
31-37: Consistency: “Column Actions” (singular) to match “Column Settings”Align section naming.
-## Columns Actions +## Column Actions @@ -Each column has a menu that lets you manage and customize it. From this menu, you can: +Each column has a menu that lets you manage and customize it. From this menu, you can:
39-48: Accessibility: add alt text to per-column action imagesProvide alt descriptions; keep maxWidth consistent.
-<img - className="block dark:hidden" - src="/img/playground/play-column-options-light.png" - style={{maxWidth: '350px'}} -/> -<img - className="hidden dark:block" - src="/img/playground/play-column-options-dark.png" - style={{maxWidth: '350px'}} -/> +<img + alt="Per-column options menu (light theme)" + className="block dark:hidden" + src="/img/playground/play-column-options-light.png" + style={{maxWidth: '350px'}} +/> +<img + alt="Per-column options menu (dark theme)" + className="hidden dark:block" + src="/img/playground/play-column-options-dark.png" + style={{maxWidth: '350px'}} +/>evaluators/made-by-traceloop.mdx (3)
6-6: Minor style: avoid split infinitiveReads smoother as “to assess … systematically.”
-The Evaluator Library provides a comprehensive collection of pre-built quality checks designed to systematically assess AI outputs. +The Evaluator Library provides a comprehensive collection of prebuilt quality checks designed to assess AI outputs systematically.
8-8: Grammar: pluralize “schema”Use “schemas” for multiple types; also tighten wording.
-Each evaluator comes with a predefined input and output schema. When using an evaluator, you’ll need to map your data to its input schema. +Each evaluator includes predefined input and output schemas. When using an evaluator, map your data to its input schema.
17-87: UX: link each evaluator Card to its docs and confirm icon assets
Optional refactor: add an
hrefprop to each<Card>so users can jump straight to the detailed evaluator section. For example:- <Card title="Faithfulness" icon="circle-check"> + <Card + title="Faithfulness" + icon="circle-check" + href="/docs/evaluators/evaluator-library#faithfulness" + > Detect hallucinations and verify facts to maintain accuracy and truthfulness in AI responses. </Card>Verified image assets under
img/evaluator/:
• eval-made-by-traceloop-dark.png
• eval-made-by-traceloop-light.png
• eval-library-dark.png
• eval-library-light.pngIcons referenced in this file (please confirm these match your Card component’s supported icon keys):
• text
• hashtag
• align-left
• bullseye
• circle-check
• shield
• triangle-exclamation
• lock
• database
• code
• asteriskPlease verify that:
- Your Card component library includes all of the above icon keys.
- The
hrefvalues align with your site’s routing and anchor conventions.evaluators/custom-evaluator.mdx (3)
3-3: Trim trailing whitespace in front matter description.Minor polish to avoid spurious diffs.
Apply:
-description: "Define an evaluator for your specific needs " +description: "Define an evaluator for your specific needs"
9-15: Add alt text to images for accessibility and SEO.All images lack alt; add concise, descriptive alt attributes.
<img className="block dark:hidden" src="/img/evaluator/eval-custom-light.png" + alt="Custom evaluator overview in light mode" /> - <img className="hidden dark:block" src="/img/evaluator/eval-custom-dark.png" /> + <img className="hidden dark:block" src="/img/evaluator/eval-custom-dark.png" alt="Custom evaluator overview in dark mode" /><img className="block dark:hidden" src="/img/evaluator/eval-do-it-yourself-light.png" + alt="Do It Yourself evaluator flow in light mode" /> - <img className="hidden dark:block" src="/img/evaluator/eval-do-it-yourself-dark.png" /> + <img className="hidden dark:block" src="/img/evaluator/eval-do-it-yourself-dark.png" alt="Do It Yourself evaluator flow in dark mode" />Also applies to: 21-27
31-36: Tighten and clarify the “Generate Evaluator” workflow copy.Removes passive phrasing and clarifies prerequisites.
-The evaluator prompt can be automatically configured by Traceloop by clicking on the **Generate Evaluator** button. -To enable the button, map the column you want to evaluate (such as an LLM response) and add any additional data columns required for prompt creation. -Describe the evaluator’s purpose and reference the relevant data columns in the description. - -The system generates a prompt template that you can edit and customize as needed. +Click **Generate Evaluator** to have Traceloop draft the evaluator prompt automatically. +First, map the column you want to evaluate (e.g., an LLM response). Optionally add any additional data columns the prompt should reference. +Then describe the evaluator’s purpose and reference the mapped columns. +Traceloop will generate an editable prompt template that you can review and customize.playgrounds/quick-start.mdx (4)
26-26: Resolve run-on sentence in Row Characteristics.-Each row in the Playground is independent and can be executed on its own, maintains an order that can be rearranged as needed. +Each row is independent, can be executed on its own, and has an order you can rearrange as needed.
29-34: Make list style consistent (end with periods) and tighten phrasing.-- **Add Row**: Create new rows manually or through bulk operations -- **Delete Row**: Remove unwanted rows individually or in bulk -- **Duplicate Row**: Copy existing rows to create variations -- **Reorder Rows**: Drag and drop to change row order -- **Generate Rows**: Use AI to generate multiple similar rows based on patterns +- **Add Row**: Create rows manually or via bulk operations. +- **Delete Row**: Remove rows individually or in bulk. +- **Duplicate Row**: Copy rows to create variations. +- **Reorder Rows**: Drag to change row order. +- **Generate Rows**: Use AI to create multiple similar rows from a pattern.
39-43: Normalize data source names and casing.-1. CSV files -2. JSON file -3. From A Dataset -4. From production spans +1. CSV files +2. JSON files +3. From a dataset +4. From production spans
9-15: Add alt text to images and minor inline style tweak.<img className="block dark:hidden" src="/img/playground/play-list-light.png" + alt="Playgrounds list in light mode" /> - <img className="hidden dark:block" src="/img/playground/play-list-dark.png" /> + <img className="hidden dark:block" src="/img/playground/play-list-dark.png" alt="Playgrounds list in dark mode" />-<Frame style={{margin: '80px'}}> +<Frame style={{ margin: 80 }}> <img className="block dark:hidden" src="/img/playground/play-empty-table-light.png" + alt="Empty playground table in light mode" /> - <img className="hidden dark:block" src="/img/playground/play-empty-table-dark.png" /> + <img className="hidden dark:block" src="/img/playground/play-empty-table-dark.png" alt="Empty playground table in dark mode" /> </Frame>Also applies to: 45-51
playgrounds/columns/data-columns.mdx (2)
8-13: Add alt text to all images; fix minor style props.Improves accessibility and SEO. Keep alt concise and contextual.
<img className="block dark:hidden" src="/img/playground/play-column-list-light.png" + alt="Columns list in light mode" /> -<img className="hidden dark:block" src="/img/playground/play-column-list-dark.png" /> +<img className="hidden dark:block" src="/img/playground/play-column-list-dark.png" alt="Columns list in dark mode" /><img className="block dark:hidden" src="/img/playground/play-number-col-light.png" - style={{maxWidth: '300px'}} + style={{ maxWidth: 300 }} + alt="Numeric column configuration in light mode" /> <img className="hidden dark:block" src="/img/playground/play-number-col-dark.png" - style={{maxWidth: '300px'}} + style={{ maxWidth: 300 }} + alt="Numeric column configuration in dark mode" /><img className="block dark:hidden" src="/img/playground/play-number-col-summary-light.png" - style={{maxWidth: '300px'}} + style={{ maxWidth: 300 }} + alt="Numeric column summary calculations in light mode" /> <img className="hidden dark:block" src="/img/playground/play-number-col-summary-dark.png" - style={{maxWidth: '300px'}} + style={{ maxWidth: 300 }} + alt="Numeric column summary calculations in dark mode" /><img className="block dark:hidden" - src="/img/playground/play-single-select-creation-light.png" + src="/img/playground/play-single-select-creation-light.png" + alt="Create single-select column in light mode" /> <img className="hidden dark:block" - src="/img/playground/play-single-select-creation-dark.png" + src="/img/playground/play-single-select-creation-dark.png" + alt="Create single-select column in dark mode" /><img className="block dark:hidden" - src="/img/playground/play-single-select-dark.png" + src="/img/playground/play-single-select-light.png" + alt="Single-select cell rendering in light mode" /> <img className="hidden dark:block" src="/img/playground/play-single-select-dark.png" + alt="Single-select cell rendering in dark mode" /><img className="block dark:hidden" src="/img/playground/play-multi-select-light.png" + alt="Multi-select cells in light mode" /> <img className="hidden dark:block" src="/img/playground/play-multi-select-dark.png" + alt="Multi-select cells in dark mode" /><img className="block dark:hidden" src="/img/playground/play-json-light.png" + alt="JSON editor panel in light mode" /> <img className="hidden dark:block" src="/img/playground/play-json-dark.png" + alt="JSON editor panel in dark mode" />Also applies to: 30-39, 44-53, 67-75, 78-85, 93-100, 109-116
41-41: Clarify “last row” behavior.If this is a footer summary row (not user data), consider naming it “summary row (footer)” to avoid confusion with real data rows.
-The last row allows you to choose a calculation method for the column, such as average, median, minimum, maximum, or sum. +The summary row (footer) lets you choose a calculation method for the column (average, median, minimum, maximum, or sum).evaluators/evaluator-library.mdx (2)
8-14: Add alt text to the library image.<img className="block dark:hidden" src="/img/evaluator/eval-library-light.png" + alt="Evaluator Library in light mode" /> - <img className="hidden dark:block" src="/img/evaluator/eval-library-dark.png" /> + <img className="hidden dark:block" src="/img/evaluator/eval-library-dark.png" alt="Evaluator Library in dark mode" />
66-73: Broaden output type; some evaluators return structured JSON or scores.-### Outputs -- **results**: String-based evaluation results -- **pass**: Boolean indicator for pass/fail status +### Outputs +- **result**: A string or JSON object with evaluation details (e.g., score, label, rationale). +- **pass**: Boolean pass/fail indicator (when applicable).playgrounds/columns/prompt.mdx (7)
11-13: Fix comma splice in Info block.-Prompt columns make it easy to test different prompts against real data, compare model outputs side by side. +Prompt columns make it easy to test different prompts against real data and compare model outputs side by side.
15-24: Add alt text and fix maxWidth units.style={{maxWidth: '400'}} should include units or use a number in JSX (interpreted as px when applied inline in React-style objects). The current values are strings without units.
<img className="block dark:hidden" src="/img/playground/play-prompt-column-light.png" - style={{maxWidth: '400'}} + style={{ maxWidth: 400 }} + alt="Prompt column example in light mode" /> <img className="hidden dark:block" src="/img/playground/play-prompt-column-dark.png" - style={{maxWidth: '400'}} + style={{ maxWidth: 400 }} + alt="Prompt column example in dark mode" /><img className="block dark:hidden" src="/img/playground/play-prompt-write-light.png" - style={{maxWidth: '400'}} + style={{ maxWidth: 400 }} + alt="Prompt writing UI in light mode" /> <img className="hidden dark:block" src="/img/playground/play-prompt-write-dark.png" - style={{maxWidth: '400'}} + style={{ maxWidth: 400 }} + alt="Prompt writing UI in dark mode" />Also applies to: 33-42
28-31: Terminate sentence and tighten mapping guidance.-You can insert variables into the prompt using curly brackets (e.g., `{{variable_name}}`). These variables can then be mapped to existing column data, allowing your prompt to dynamically adapt to the playground +Insert variables using double curly braces (e.g., `{{variable_name}}`). Map each variable to an existing column so the prompt dynamically adapts to the playground.
46-51: Model list is likely to drift; prefer durable guidance and link to source of truth.Hard-coding model names (e.g., GPT‑5) risks rapid obsolescence. Recommend generic guidance + link to a “Supported models” page.
-### Model Selection -Choose from supported LLM providers and models: -- **OpenAI**: GPT-5, GPT-5-Mini, GPT-5-Nano, GPT-4o, GPT-4o-mini and more -- **Anthropic**: Claude-3-Opus, Claude-3-5-Sonnet, Claude-3-5-Haiku and more -- **Gemini**: Gemini-2.5-Flash, Gemini-2.5-Pro and more +### Model Selection +Choose from the providers and models supported in your workspace (availability may vary). See the Supported Models page for up‑to‑date options. +– OpenAI +– Anthropic +– Google GeminiPlease confirm the correct link/slug for the “Supported Models” page so I can wire it in.
55-59: Heading level should match peers under “Configuration Options”.“Tools” should be an H3 to live under the same section as Model Selection and Structured Output.
-## Tools +### Tools
60-70: Qualify advanced options with model support and add punctuation.Some options (Logprobs, Thinking Budget, Exclude Reasoning) are provider-specific. Also add missing periods.
-### Advanced Settings -Fine-tune model behavior options: -- **Temperature** (0.0-1.0): Control randomness and creativity -- **Max Tokens**: Limit model output length (1-8000+ depending on model) -- **Top P**: Nucleus sampling parameter (0.0-1.0) -- **Frequency Penalty**: Reduce repetition (0.0 to 1.0) -- **Presence Penalty**: Encourage topic diversity (0.0 to 1.0) -- **Logprobs**: When enabled, returns the probability scores for generated tokens -- **Thinking Budget** (512-24576): Sets the number of tokens the model can use for internal reasoning before producing the final output -A higher budget allows more complex reasoning but increases cost and runtime -- **Exclude Reasoning from Response**: If enabled, the model hides its internal reasoning steps and only outputs the final response +### Advanced Settings +Fine‑tune model behavior (availability varies by provider/model): +- **Temperature** (0.0–1.0): Controls randomness and creativity. +- **Max tokens**: Limits output length (range depends on model). +- **Top‑p**: Nucleus sampling parameter (0.0–1.0). +- **Frequency penalty**: Reduces repetition (0.0–1.0). +- **Presence penalty**: Encourages topic diversity (0.0–1.0). +- **Logprobs**: Returns token‑level probabilities (if supported). +- **Thinking budget** (e.g., 512–24,576): Token budget for internal reasoning before producing the final output. A higher budget can enable more complex reasoning but increases cost and runtime. +- **Exclude reasoning from response**: Hides internal reasoning; only the final response is returned (if supported).
73-75: Minor punctuation and UI cue polish.-A prompt can be executed across all cells in a column or on a specific cell. +A prompt can be executed across all cells in a column or on a specific cell.-Prompt outputs can be mapped to different columns by clicking a cell and selecting the mapping icon, or by double-clicking the cell +Map prompt outputs to other columns by clicking a cell and selecting the mapping icon, or by double‑clicking the cell.mint.json (2)
172-175: Add missing Evaluator Library page to Evaluators navigation and refine orderThe new
evaluators/evaluator-library.mdxfile exists but isn’t yet referenced in the site nav. To maintain a clear progression—Intro → Evaluator Library → Made by Traceloop → Custom Evaluator—please updatemint.json:• File:
mint.json
• Section: group"Evaluators"(around lines 172–175)Apply this diff:
{ "group": "Evaluators", - "pages": ["evaluators/intro", "evaluators/custom-evaluator", "evaluators/made-by-traceloop"] + "pages": [ + "evaluators/intro", + "evaluators/evaluator-library", + "evaluators/made-by-traceloop", + "evaluators/custom-evaluator" + ] },
154-167: Playgrounds navigation validated; optional Columns overview
- ✅ mint.json is well-formed, and every slug under the Playgrounds section (including nested “Columns”) maps to an existing .mdx/.md file.
- ✅ No stale “playbooks/quick-start” references detected.
- ✅ Nested groups render as expected in Mintlify’s schema.
Optional refinement: add a high-level overview page (e.g., playgrounds/columns/index.mdx) to introduce the Columns group before its subpages.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (36)
img/evaluator/eval-custom-dark.pngis excluded by!**/*.pngimg/evaluator/eval-custom-light.pngis excluded by!**/*.pngimg/evaluator/eval-do-it-yourself-dark.pngis excluded by!**/*.pngimg/evaluator/eval-do-it-yourself-light.pngis excluded by!**/*.pngimg/evaluator/eval-library-dark.pngis excluded by!**/*.pngimg/evaluator/eval-library-light.pngis excluded by!**/*.pngimg/evaluator/eval-made-by-traceloop-dark.pngis excluded by!**/*.pngimg/evaluator/eval-made-by-traceloop-light.pngis excluded by!**/*.pngimg/playground/play-action-dark.pngis excluded by!**/*.pngimg/playground/play-action-light.pngis excluded by!**/*.pngimg/playground/play-column-list-dark.pngis excluded by!**/*.pngimg/playground/play-column-list-light.pngis excluded by!**/*.pngimg/playground/play-column-options-dark.pngis excluded by!**/*.pngimg/playground/play-column-options-light.pngis excluded by!**/*.pngimg/playground/play-column-settings-dark.pngis excluded by!**/*.pngimg/playground/play-column-settings-light.pngis excluded by!**/*.pngimg/playground/play-empty-table-dark.pngis excluded by!**/*.pngimg/playground/play-empty-table-light.pngis excluded by!**/*.pngimg/playground/play-json-dark.pngis excluded by!**/*.pngimg/playground/play-json-light.pngis excluded by!**/*.pngimg/playground/play-list-dark.pngis excluded by!**/*.pngimg/playground/play-list-light.pngis excluded by!**/*.pngimg/playground/play-multi-select-dark.pngis excluded by!**/*.pngimg/playground/play-multi-select-light.pngis excluded by!**/*.pngimg/playground/play-number-col-dark.pngis excluded by!**/*.pngimg/playground/play-number-col-light.pngis excluded by!**/*.pngimg/playground/play-number-col-summary-dark.pngis excluded by!**/*.pngimg/playground/play-number-col-summary-light.pngis excluded by!**/*.pngimg/playground/play-prompt-column-dark.pngis excluded by!**/*.pngimg/playground/play-prompt-column-light.pngis excluded by!**/*.pngimg/playground/play-prompt-write-dark.pngis excluded by!**/*.pngimg/playground/play-prompt-write-light.pngis excluded by!**/*.pngimg/playground/play-single-select-creation-dark.pngis excluded by!**/*.pngimg/playground/play-single-select-creation-light.pngis excluded by!**/*.pngimg/playground/play-single-select-dark.pngis excluded by!**/*.pngimg/playground/play-single-select-light.pngis excluded by!**/*.png
📒 Files selected for processing (11)
.gitignore(1 hunks)datasets/quick-start.mdx(1 hunks)evaluators/custom-evaluator.mdx(1 hunks)evaluators/evaluator-library.mdx(1 hunks)evaluators/intro.mdx(1 hunks)evaluators/made-by-traceloop.mdx(1 hunks)mint.json(1 hunks)playgrounds/columns/column-management.mdx(1 hunks)playgrounds/columns/data-columns.mdx(1 hunks)playgrounds/columns/prompt.mdx(1 hunks)playgrounds/quick-start.mdx(1 hunks)
🧰 Additional context used
🪛 LanguageTool
playgrounds/quick-start.mdx
[grammar] ~5-~5: There might be a mistake here.
Context: ...Ms, evaluate outputs, and analyze data. Think of them as powerful workbenches fo...
(QB_NEW_EN)
[grammar] ~6-~6: There might be a mistake here.
Context: ...e power of LLM evaluation and execution. It’s designed for everyone, from product...
(QB_NEW_EN)
[grammar] ~25-~25: There might be a mistake here.
Context: ...ss all columns. ### Row Characteristics Each row in the Playground is independen...
(QB_NEW_EN)
[grammar] ~28-~28: There might be a mistake here.
Context: ...earranged as needed. ### Row Operations - Add Row: Create new rows manually or t...
(QB_NEW_EN)
[grammar] ~39-~39: There might be a mistake here.
Context: ...d from different sources: 1. CSV files 2. JSON file 3. From A Dataset 4. From prod...
(QB_NEW_EN)
[grammar] ~40-~40: There might be a mistake here.
Context: ...ent sources: 1. CSV files 2. JSON file 3. From A Dataset 4. From production spans ...
(QB_NEW_EN)
[grammar] ~41-~41: There might be a mistake here.
Context: ...: 1. CSV files 2. JSON file 3. From A Dataset 4. From production spans You can create a ...
(QB_NEW_EN)
evaluators/made-by-traceloop.mdx
[style] ~6-~6: Try moving the adverb to make the sentence clearer.
Context: ... collection of pre-built quality checks designed to systematically assess AI outputs. Each evaluator comes with a predefine...
(SPLIT_INFINITIVE)
evaluators/intro.mdx
[grammar] ~10-~10: There might be a mistake here.
Context: ...# Evaluators types The system supports: - Custom evaluators - Create your own ev...
(QB_NEW_EN)
[style] ~25-~25: Consider a more concise word here.
Context: ...ut schema. This is valuable information in order to execute the evaluator [through the SDK]...
(IN_ORDER_TO_PREMIUM)
playgrounds/columns/column-management.mdx
[grammar] ~8-~8: There might be a mistake here.
Context: ...icient playgrounds. ## Columns Settings Column Settings lets you hide specific c...
(QB_NEW_EN)
[style] ~17-~17: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...the column into the desired position. To hide a column, toggle its switch in the...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
[grammar] ~19-~19: There might be a mistake here.
Context: ...umn, toggle its switch in the menu. <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~22-~22: There might be a mistake here.
Context: ...light.png" style={{maxWidth: '600px'}} /> <img className="hidden dark:bloc...
(QB_NEW_EN)
[grammar] ~23-~23: There might be a mistake here.
Context: ...ht.png" style={{maxWidth: '600px'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~24-~24: There might be a mistake here.
Context: ..." style={{maxWidth: '600px'}} /> <img className="hidden dark:block" src="...
(QB_NEW_EN)
[grammar] ~27-~27: There might be a mistake here.
Context: ...rk.png" style={{maxWidth: '600px'}} /> ## Columns Actions Each column has...
(QB_NEW_EN)
[grammar] ~33-~33: There might be a mistake here.
Context: ...d customize it. From this menu, you can: - Rename the column directly by editing it...
(QB_NEW_EN)
playgrounds/columns/prompt.mdx
[grammar] ~6-~6: There might be a mistake here.
Context: ...ull model configuration" --- ### Prompt A Prompt column allows you to define a c...
(QB_NEW_EN)
[grammar] ~7-~7: There might be a mistake here.
Context: ...un it directly on your Playground data. You can compose prompts with messages (s...
(QB_NEW_EN)
[grammar] ~8-~8: There might be a mistake here.
Context: ...bles, and configure which model to use. Each row in your playground will be pass...
(QB_NEW_EN)
[grammar] ~15-~15: There might be a mistake here.
Context: ...odel outputs side by side. <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~16-~16: There might be a mistake here.
Context: ...o> <img className="block dark:hidden" src="/img/playground/play-prompt-column-...
(QB_NEW_EN)
[grammar] ~17-~17: There might be a mistake here.
Context: ...playground/play-prompt-column-light.png" style={{maxWidth: '400'}} /> <img cla...
(QB_NEW_EN)
[grammar] ~18-~18: There might be a mistake here.
Context: ...n-light.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~19-~19: There might be a mistake here.
Context: ...ight.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~20-~20: There might be a mistake here.
Context: ...ng" style={{maxWidth: '400'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~21-~21: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-prompt-column-...
(QB_NEW_EN)
[grammar] ~22-~22: There might be a mistake here.
Context: .../playground/play-prompt-column-dark.png" style={{maxWidth: '400'}} /> ## Prompt ...
(QB_NEW_EN)
[grammar] ~23-~23: There might be a mistake here.
Context: ...mn-dark.png" style={{maxWidth: '400'}} /> ## Prompt Writing Write your prompt...
(QB_NEW_EN)
[grammar] ~33-~33: There might be a mistake here.
Context: ...namically adapt to the playground <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~34-~34: There might be a mistake here.
Context: ...d <img className="block dark:hidden" src="/img/playground/play-prompt-write-l...
(QB_NEW_EN)
[grammar] ~35-~35: There might be a mistake here.
Context: .../playground/play-prompt-write-light.png" style={{maxWidth: '400'}} /> <img cla...
(QB_NEW_EN)
[grammar] ~36-~36: There might be a mistake here.
Context: ...e-light.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~37-~37: There might be a mistake here.
Context: ...ight.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~38-~38: There might be a mistake here.
Context: ...ng" style={{maxWidth: '400'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~39-~39: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-prompt-write-d...
(QB_NEW_EN)
[grammar] ~40-~40: There might be a mistake here.
Context: ...g/playground/play-prompt-write-dark.png" style={{maxWidth: '400'}} /> ## Configu...
(QB_NEW_EN)
[grammar] ~41-~41: There might be a mistake here.
Context: ...te-dark.png" style={{maxWidth: '400'}} /> ## Configuration Options ### Model ...
(QB_NEW_EN)
[grammar] ~46-~46: There might be a mistake here.
Context: ...nfiguration Options ### Model Selection Choose from supported LLM providers and ...
(QB_NEW_EN)
[grammar] ~47-~47: There might be a mistake here.
Context: ...from supported LLM providers and models: - OpenAI: GPT-5, GPT-5-Mini, GPT-5-Nano,...
(QB_NEW_EN)
[grammar] ~48-~48: There might be a mistake here.
Context: ...GPT-5-Nano, GPT-4o, GPT-4o-mini and more - Anthropic: Claude-3-Opus, Claude-3-5-S...
(QB_NEW_EN)
[grammar] ~49-~49: There might be a mistake here.
Context: ...de-3-5-Sonnet, Claude-3-5-Haiku and more - Gemini: Gemini-2.5-Flash, Gemini-2.5-P...
(QB_NEW_EN)
evaluators/evaluator-library.mdx
[style] ~6-~6: Try moving the adverb to make the sentence clearer.
Context: ... collection of pre-built quality checks designed to systematically assess AI outputs. You can choose from existing evaluator...
(SPLIT_INFINITIVE)
[grammar] ~22-~22: There might be a mistake here.
Context: ...t Analysis Evaluators Character Count - Analyze response length and verbosity - ...
(QB_NEW_EN)
[grammar] ~26-~26: There might be a mistake here.
Context: ...th requirements Character Count Ratio - Measure the ratio of characters to the i...
(QB_NEW_EN)
[grammar] ~30-~30: There might be a mistake here.
Context: ...g response proportionality Word Count - Ensure appropriate response detail level...
(QB_NEW_EN)
[grammar] ~34-~34: There might be a mistake here.
Context: ...t length consistency Word Count Ratio - Measure the ratio of words to the input ...
(QB_NEW_EN)
[grammar] ~40-~40: There might be a mistake here.
Context: ...ssessment Evaluators Answer Relevancy - Verify responses address the query - Ens...
(QB_NEW_EN)
[grammar] ~50-~50: There might be a mistake here.
Context: ...y & Security Evaluators PII Detection - Identify personal information in respons...
(QB_NEW_EN)
[grammar] ~54-~54: There might be a mistake here.
Context: ...and data security Profanity Detection - Monitor for inappropriate language - Mai...
(QB_NEW_EN)
[grammar] ~58-~58: There might be a mistake here.
Context: ...t quality standards Secrets Detection - Monitor for sensitive information leakag...
(QB_NEW_EN)
[grammar] ~66-~66: There might be a mistake here.
Context: ...eate custom evaluators with: ### Inputs - string: Text-based input parameters - ...
(QB_NEW_EN)
[grammar] ~67-~67: There might be a mistake here.
Context: ... string: Text-based input parameters - Support for multiple input types ### Ou...
(QB_NEW_EN)
[grammar] ~70-~70: There might be a mistake here.
Context: ...rt for multiple input types ### Outputs - results: String-based evaluation resul...
(QB_NEW_EN)
[grammar] ~71-~71: There might be a mistake here.
Context: ...sults**: String-based evaluation results - pass: Boolean indicator for pass/fail ...
(QB_NEW_EN)
evaluators/custom-evaluator.mdx
[grammar] ~31-~31: There might be a mistake here.
Context: ...g on the Generate Evaluator button. To enable the button, map the column you...
(QB_NEW_EN)
[grammar] ~32-~32: There might be a mistake here.
Context: ...a columns required for prompt creation. Describe the evaluator’s purpose and ref...
(QB_NEW_EN)
playgrounds/columns/data-columns.mdx
[style] ~18-~18: Try moving the adverb to make the sentence clearer.
Context: ... edit, or delete columns?** Learn how to effectively manage your columns in the [Column Management](./column-man...
(SPLIT_INFINITIVE)
[grammar] ~21-~21: There might be a mistake here.
Context: ...guide. ## 📝 Data Input Columns Store and manage static data entered manu...
(QB_NEW_EN)
[grammar] ~22-~22: There might be a mistake here.
Context: ...ually or imported from external sources. ### Text field Free-form text input with mult...
(QB_NEW_EN)
[grammar] ~24-~24: There might be a mistake here.
Context: ...d from external sources. ### Text field Free-form text input with multiline supp...
(QB_NEW_EN)
[grammar] ~27-~27: There might be a mistake here.
Context: ...nput with multiline support ### Numeric Numbers, integers, and floating-point va...
(QB_NEW_EN)
[grammar] ~30-~30: There might be a mistake here.
Context: ...ntegers, and floating-point values <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~31-~31: There might be a mistake here.
Context: ...es <img className="block dark:hidden" src="/img/playground/play-number-col-lig...
(QB_NEW_EN)
[grammar] ~32-~32: There might be a mistake here.
Context: ...mg/playground/play-number-col-light.png" style={{maxWidth: '300px'}} /> <img c...
(QB_NEW_EN)
[grammar] ~33-~33: There might be a mistake here.
Context: ...light.png" style={{maxWidth: '300px'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~34-~34: There might be a mistake here.
Context: ...ht.png" style={{maxWidth: '300px'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~35-~35: There might be a mistake here.
Context: ..." style={{maxWidth: '300px'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~36-~36: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-number-col-dar...
(QB_NEW_EN)
[grammar] ~37-~37: There might be a mistake here.
Context: ...img/playground/play-number-col-dark.png" style={{maxWidth: '300px'}} /> The last...
(QB_NEW_EN)
[grammar] ~38-~38: There might be a mistake here.
Context: ...-dark.png" style={{maxWidth: '300px'}} /> The last row allows you to choose a ...
(QB_NEW_EN)
[grammar] ~44-~44: There might be a mistake here.
Context: ...median, minimum, maximum, or sum. <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~45-~45: There might be a mistake here.
Context: .... <img className="block dark:hidden" src="/img/playground/play-number-col-sum...
(QB_NEW_EN)
[grammar] ~46-~46: There might be a mistake here.
Context: ...round/play-number-col-summary-light.png" style={{maxWidth: '300px'}} /> <img c...
(QB_NEW_EN)
[grammar] ~47-~47: There might be a mistake here.
Context: ...light.png" style={{maxWidth: '300px'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~48-~48: There might be a mistake here.
Context: ...ht.png" style={{maxWidth: '300px'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~49-~49: There might be a mistake here.
Context: ..." style={{maxWidth: '300px'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~50-~50: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-number-col-sum...
(QB_NEW_EN)
[grammar] ~51-~51: There might be a mistake here.
Context: ...ground/play-number-col-summary-dark.png" style={{maxWidth: '300px'}} /> ### S...
(QB_NEW_EN)
[grammar] ~52-~52: There might be a mistake here.
Context: ...-dark.png" style={{maxWidth: '300px'}} /> ### Single select Single-choice c...
(QB_NEW_EN)
[grammar] ~58-~58: There might be a mistake here.
Context: ...idth: '300px'}} /> ### Single select Single-choice columns let you define a s...
(QB_NEW_EN)
[grammar] ~59-~59: There might be a mistake here.
Context: ...nd restrict each cell to one selection. To create one, set the column name and a...
(QB_NEW_EN)
[grammar] ~60-~60: There might be a mistake here.
Context: ...dd options in the Create Column drawer. In the values box, type an option and pr...
(QB_NEW_EN)
[grammar] ~88-~88: There might be a mistake here.
Context: ...-single-select-dark.png" /> ### Multi select Multi-select columns let you define a set of ...
(QB_NEW_EN)
🔇 Additional comments (6)
.gitignore (1)
1-2: LGTM: ignore .claude directory added cleanlyThe ignore rule is scoped to the directory via the trailing slash and the comment is clear.
datasets/quick-start.mdx (1)
5-7: Good move: context-before-visual improves information scentBringing the dataset description above the frame improves readability and SEO. No content issues spotted.
evaluators/intro.mdx (1)
25-26: Tighten phrasing in evaluators/intro.mdx and confirm link target
- File: evaluators/intro.mdx, lines 25–26
- Link
../experiments/running-from-codeverified to point to experiments/running-from-code.mdxApply this diff:
- Clicking on existing evaluators will present their input and output schema. This is valuable information in order to execute the evaluator [through the SDK](../experiments/running-from-code). + Clicking an existing evaluator shows its input and output schemas. Use these details to execute the evaluator [via the SDK](../experiments/running-from-code).evaluators/custom-evaluator.mdx (1)
45-45: Verify cross-links are correct.Check that these relative paths resolve at build time:
- ../playgrounds/columns/column-management
- ../experiments/running-from-code
If needed, I can scan the repo for the target slugs and adjust the paths. Do you want a quick link-check script?
evaluators/evaluator-library.mdx (2)
6-7: Solid intro.Clear framing of prebuilt vs. custom evaluators.
76-81: Verify UI copy for consistency (“Use evaluator” button label).Confirm the exact casing/wording in the product UI and mirror it here.
If it differs, I can update this section to match the UI precisely.
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 2940087 in 1 minute and 38 seconds. Click for details.
- Reviewed
69lines of code in3files - Skipped
0files when reviewing. - Skipped posting
5draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. playgrounds/columns/column-management.mdx:20
- Draft comment:
The added block duplicates the reordering instruction already mentioned above. Consider consolidating them for clarity. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 10% vs. threshold = 50% The comment is technically correct about the duplication. However, the two mentions might serve different purposes - one is in the context of Column Settings menu, while the Info block might be highlighting an alternative direct method. Documentation sometimes intentionally repeats important information in different contexts. The comment isn't pointing out a clear problem that needs fixing. The duplication might actually be intentional for emphasis and clarity. Also, the two mentions provide slightly different details about the reordering mechanism. While there is some overlap, the two mentions serve different purposes and provide complementary information. This isn't necessarily a problem that needs fixing. The comment should be deleted as it's not pointing out a clear issue that requires changing the code. The duplication appears intentional and potentially helpful.
2. playgrounds/columns/prompt.mdx:18
- Draft comment:
The image 'maxWidth' style value is missing a CSS unit. Use '400px' instead of '400' to ensure proper rendering. - Reason this comment was not posted:
Comment was not on a location in the diff, so it can't be submitted as a review comment.
3. playgrounds/columns/prompt.mdx:47
- Draft comment:
The updated model selection text removes GPT-5 references and changes provider names. Verify these model names (e.g., GPT-4o, Claude-3.5-Sonnet) are up-to-date and consistent with the rest of the documentation. - Reason this comment was not posted:
Comment did not seem useful. Confidence is useful =0%<= threshold50%The comment asks the PR author to verify the model names and their consistency with the documentation. This falls under asking the author to double-check things, which is against the rules. The comment does not provide a specific suggestion or point out a clear issue.
4. playgrounds/quick-start.mdx:67
- Draft comment:
The new 'Running a Playground' section is a clear and useful addition. Consider mentioning potential delays for large datasets if applicable. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%None
5. playgrounds/columns/column-management.mdx:21
- Draft comment:
Typographical suggestion: Consider adding a period at the end of the sentence for consistency (e.g., '...in the playground.'). - Reason this comment was not posted:
Comment did not seem useful. Confidence is useful =0%<= threshold50%This comment is purely about a typographical suggestion, which is not related to the functionality or logic of the code. It doesn't provide any meaningful insight into the code's operation or suggest any improvements to the code's structure or logic.
Workflow ID: wflow_ic3VA78yje9Aj2Tn
You can customize
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (2)
playgrounds/columns/column-management.mdx (1)
6-6: Fix subject–verb agreement.
Matches prior feedback; keep “evolves”.-Columns in the Playground can be reordered, edited, or deleted at any time to adapt your workspace as your analysis evolve. Understanding how to manage columns effectively helps you maintain organized and efficient playgrounds. +Columns in the Playground can be reordered, edited, or deleted at any time to adapt your workspace as your analysis evolves. Understanding how to manage columns effectively helps you maintain organized and efficient playgrounds.playgrounds/quick-start.mdx (1)
5-7: Fix number agreement and perspective.
Matches prior suggestion; keeps plural subject consistent.-Playgrounds are interactive spreadsheets where you can organize your data and experiment with LLMs, evaluate outputs, and analyze data. -Think of them as powerful workbenches for AI development that combine the flexibility of a spreadsheet with the power of LLM evaluation and execution. -It’s designed for everyone, from product managers and analysts to QA, data engineers, and software developers. +Playgrounds are interactive spreadsheets where you can organize data, experiment with LLMs, evaluate outputs, and analyze results. +Think of them as powerful workbenches that combine the flexibility of spreadsheets with the power of LLM evaluation and execution. +They’re designed for everyone—from product managers and analysts to QA, data engineers, and software developers.
🧹 Nitpick comments (20)
playgrounds/columns/column-management.mdx (8)
3-3: Polish frontmatter description for clarity.
"Learn all columns general functionalities" is awkward.-description: "Learn all columns general functionalities" +description: "Learn general column functionalities"
8-8: Unify section headings (singular).
Use “Column Settings” and “Column Actions” for consistency.-## Columns Settings +## Column Settings-## Columns Actions +## Column ActionsAlso applies to: 36-36
9-9: Add terminal punctuation.-Column Settings lets you hide specific columns from the Playground and reorder them as needed. To open the settings, click the Playground Action button and select Column Settings +Column Settings lets you hide specific columns from the Playground and reorder them as needed. To open the settings, click the Playground Action button and select Column Settings.
16-16: Tighten phrasing and remove filler.-To change the column order, use the six-dot handle on the right side of each column to simply drag the column into the desired position. +To change the column order, drag a column using the six-dot handle on its right.
20-22: Add period and consistent capitalization.-Columns can also be reordered by dragging them to your desired position in the playground +Columns can also be reordered by dragging them to your desired position in the Playground.
10-14: Add alt text for accessibility (light/dark action images).<img className="block dark:hidden" src="/img/playground/play-action-light.png" + alt="Playground Actions menu button in light mode" /> <img className="hidden dark:block" src="/img/playground/play-action-dark.png" + alt="Playground Actions menu button in dark mode" />
24-33: Add alt text for accessibility (column settings screenshots).<img className="block dark:hidden" src="/img/playground/play-column-settings-light.png" style={{maxWidth: '600px'}} + alt="Column Settings panel in light mode with reorder and visibility toggles" /> <img className="hidden dark:block" src="/img/playground/play-column-settings-dark.png" style={{maxWidth: '600px'}} + alt="Column Settings panel in dark mode with reorder and visibility toggles" />
45-54: Add alt text for accessibility (column options menu).<img className="block dark:hidden" src="/img/playground/play-column-options-light.png" style={{maxWidth: '350px'}} + alt="Per-column options menu in light mode: rename, edit, duplicate, delete" /> <img className="hidden dark:block" src="/img/playground/play-column-options-dark.png" style={{maxWidth: '350px'}} + alt="Per-column options menu in dark mode: rename, edit, duplicate, delete" />playgrounds/columns/prompt.mdx (6)
12-13: Fix comma splice by adding conjunction.-Prompt columns make it easy to test different prompts against real data, compare model outputs side by side. +Prompt columns make it easy to test different prompts against real data, and compare model outputs side by side.
15-24: Fix CSS unit and add alt text (prompt column preview).
maxWidth needs px; add alt for accessibility.<img className="block dark:hidden" src="/img/playground/play-prompt-column-light.png" - style={{maxWidth: '400'}} + style={{maxWidth: '400px'}} + alt="Prompt column configuration and output in light mode" /> <img className="hidden dark:block" src="/img/playground/play-prompt-column-dark.png" - style={{maxWidth: '400'}} + style={{maxWidth: '400px'}} + alt="Prompt column configuration and output in dark mode" />
30-30: Use standard term “curly braces” and add period.-You can insert variables into the prompt using curly brackets (e.g., `{{variable_name}}`). These variables can then be mapped to existing column data, allowing your prompt to dynamically adapt to the playground +You can insert variables into the prompt using curly braces (e.g., `{{variable_name}}`). These variables can then be mapped to existing column data, allowing your prompt to dynamically adapt to the Playground.
33-42: Fix CSS unit and add alt text (prompt writing screenshots).<img className="block dark:hidden" src="/img/playground/play-prompt-write-light.png" - style={{maxWidth: '400'}} + style={{maxWidth: '400px'}} + alt="Authoring prompt messages with roles in light mode" /> <img className="hidden dark:block" src="/img/playground/play-prompt-write-dark.png" - style={{maxWidth: '400'}} + style={{maxWidth: '400px'}} + alt="Authoring prompt messages with roles in dark mode" />
59-68: Align ranges and punctuation; fold explanatory line into bullet.
Also confirm penalty ranges and max tokens align with actual constraints in the UI/backend.- **Temperature** (0.0-1.0): Control randomness and creativity -- **Max Tokens**: Limit model output length (1-8000+ depending on model) +- **Max Tokens**: Limit model output length (model-dependent) - **Top P**: Nucleus sampling parameter (0.0-1.0) -- **Frequency Penalty**: Reduce repetition (0.0 to 1.0) -- **Presence Penalty**: Encourage topic diversity (0.0 to 1.0) +- **Frequency Penalty**: Reduce repetition (range depends on provider) +- **Presence Penalty**: Encourage topic diversity (range depends on provider) - **Logprobs**: When enabled, returns the probability scores for generated tokens -- **Thinking Budget** (512-24576): Sets the number of tokens the model can use for internal reasoning before producing the final output -A higher budget allows more complex reasoning but increases cost and runtime +- **Thinking Budget** (e.g., 512–24,576): Sets the number of tokens the model can use for internal reasoning before producing the final output. Higher values enable more complex reasoning but increase cost and runtime. - **Exclude Reasoning from Response**: If enabled, the model hides its internal reasoning steps and only outputs the final response
73-73: Add terminal punctuation.-Prompt outputs can be mapped to different columns by clicking a cell and selecting the mapping icon, or by double-clicking the cell +Prompt outputs can be mapped to different columns by clicking a cell and selecting the mapping icon, or by double-clicking the cell.playgrounds/quick-start.mdx (6)
10-14: Add alt text for accessibility (playgrounds list).<img className="block dark:hidden" src="/img/playground/play-list-light.png" + alt="Playgrounds list view in light mode" /> - <img className="hidden dark:block" src="/img/playground/play-list-dark.png" /> + <img className="hidden dark:block" src="/img/playground/play-list-dark.png" alt="Playgrounds list view in dark mode" />
28-29: Fix comma splice and improve parallelism.-Each row in the Playground is independent and can be executed on its own, maintains an order that can be rearranged as needed. +Each row in the Playground is independent, can be executed on its own, and maintains an order that you can rearrange as needed.
40-40: Capitalize JSON and add serial comma and period.-**Data Input Columns** store static data such as text, json, numbers and tags +**Data Input Columns** store static data such as text, JSON, numbers, and tags.
52-56: Unify list item casing and plurality; avoid inconsistent articles.
If these are UI labels, adjust the docs to match the UI instead.-1. CSV files -2. JSON file -3. From A Dataset -4. From production spans +1. CSV files +2. JSON files +3. From a dataset +4. From production spans
60-63: Add alt text for accessibility (full table).<img className="block dark:hidden" src="/img/playground/play-full-table-light.png" + alt="Playground full table view in light mode" /> - <img className="hidden dark:block" src="/img/playground/play-full-table-dark.png" /> + <img className="hidden dark:block" src="/img/playground/play-full-table-dark.png" alt="Playground full table view in dark mode" />
72-72: Add terminal punctuation.-Ready to build more sophisticated playgrounds? Dive into the [complete documentation](./index) or explore specific [column types](./columns/data-columns) to unlock the full power of Traceloop Playgrounds! +Ready to build more sophisticated playgrounds? Dive into the [complete documentation](./index) or explore specific [column types](./columns/data-columns) to unlock the full power of Traceloop Playgrounds!.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (2)
img/playground/play-full-table-dark.pngis excluded by!**/*.pngimg/playground/play-full-table-light.pngis excluded by!**/*.png
📒 Files selected for processing (3)
playgrounds/columns/column-management.mdx(1 hunks)playgrounds/columns/prompt.mdx(1 hunks)playgrounds/quick-start.mdx(1 hunks)
🧰 Additional context used
🪛 LanguageTool
playgrounds/quick-start.mdx
[grammar] ~30-~30: There might be a mistake here.
Context: ...earranged as needed. ### Row Operations - Add Row: Create new rows manually or t...
(QB_NEW_EN)
[grammar] ~32-~32: There might be a mistake here.
Context: ...on the existing data in your Playground. - Delete Row: Remove unwanted rows indiv...
(QB_NEW_EN)
[grammar] ~52-~52: There might be a mistake here.
Context: ...d from different sources: 1. CSV files 2. JSON file 3. From A Dataset 4. From prod...
(QB_NEW_EN)
[grammar] ~53-~53: There might be a mistake here.
Context: ...ent sources: 1. CSV files 2. JSON file 3. From A Dataset 4. From production spans ...
(QB_NEW_EN)
[grammar] ~54-~54: There might be a mistake here.
Context: ...: 1. CSV files 2. JSON file 3. From A Dataset 4. From production spans You can create a ...
(QB_NEW_EN)
playgrounds/columns/column-management.mdx
[grammar] ~8-~8: There might be a mistake here.
Context: ...icient playgrounds. ## Columns Settings Column Settings lets you hide specific c...
(QB_NEW_EN)
[style] ~17-~17: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...the column into the desired position. To hide a column, toggle its switch in the...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
[grammar] ~24-~24: There might be a mistake here.
Context: ...position in the playground <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~27-~27: There might be a mistake here.
Context: ...light.png" style={{maxWidth: '600px'}} /> <img className="hidden dark:bloc...
(QB_NEW_EN)
[grammar] ~28-~28: There might be a mistake here.
Context: ...ht.png" style={{maxWidth: '600px'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~29-~29: There might be a mistake here.
Context: ..." style={{maxWidth: '600px'}} /> <img className="hidden dark:block" src="...
(QB_NEW_EN)
[grammar] ~32-~32: There might be a mistake here.
Context: ...rk.png" style={{maxWidth: '600px'}} /> ## Columns Actions Each column has...
(QB_NEW_EN)
[grammar] ~38-~38: There might be a mistake here.
Context: ...d customize it. From this menu, you can: - Rename the column directly by editing it...
(QB_NEW_EN)
playgrounds/columns/prompt.mdx
[grammar] ~6-~6: There might be a mistake here.
Context: ...ull model configuration" --- ### Prompt A Prompt column allows you to define a c...
(QB_NEW_EN)
[grammar] ~7-~7: There might be a mistake here.
Context: ...un it directly on your Playground data. You can compose prompts with messages (s...
(QB_NEW_EN)
[grammar] ~8-~8: There might be a mistake here.
Context: ...bles, and configure which model to use. Each row in your playground will be pass...
(QB_NEW_EN)
[grammar] ~15-~15: There might be a mistake here.
Context: ...odel outputs side by side. <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~16-~16: There might be a mistake here.
Context: ...o> <img className="block dark:hidden" src="/img/playground/play-prompt-column-...
(QB_NEW_EN)
[grammar] ~17-~17: There might be a mistake here.
Context: ...playground/play-prompt-column-light.png" style={{maxWidth: '400'}} /> <img cla...
(QB_NEW_EN)
[grammar] ~18-~18: There might be a mistake here.
Context: ...n-light.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~19-~19: There might be a mistake here.
Context: ...ight.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~20-~20: There might be a mistake here.
Context: ...ng" style={{maxWidth: '400'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~21-~21: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-prompt-column-...
(QB_NEW_EN)
[grammar] ~22-~22: There might be a mistake here.
Context: .../playground/play-prompt-column-dark.png" style={{maxWidth: '400'}} /> ## Prompt ...
(QB_NEW_EN)
[grammar] ~23-~23: There might be a mistake here.
Context: ...mn-dark.png" style={{maxWidth: '400'}} /> ## Prompt Writing Write your prompt...
(QB_NEW_EN)
[grammar] ~33-~33: There might be a mistake here.
Context: ...namically adapt to the playground <img className="block dark:hidden" src="/im...
(QB_NEW_EN)
[grammar] ~34-~34: There might be a mistake here.
Context: ...d <img className="block dark:hidden" src="/img/playground/play-prompt-write-l...
(QB_NEW_EN)
[grammar] ~35-~35: There might be a mistake here.
Context: .../playground/play-prompt-write-light.png" style={{maxWidth: '400'}} /> <img cla...
(QB_NEW_EN)
[grammar] ~36-~36: There might be a mistake here.
Context: ...e-light.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block"...
(QB_NEW_EN)
[grammar] ~37-~37: There might be a mistake here.
Context: ...ight.png" style={{maxWidth: '400'}} /> <img className="hidden dark:block" ...
(QB_NEW_EN)
[grammar] ~38-~38: There might be a mistake here.
Context: ...ng" style={{maxWidth: '400'}} /> <img className="hidden dark:block" src="/i...
(QB_NEW_EN)
[grammar] ~39-~39: There might be a mistake here.
Context: ...> <img className="hidden dark:block" src="/img/playground/play-prompt-write-d...
(QB_NEW_EN)
[grammar] ~40-~40: There might be a mistake here.
Context: ...g/playground/play-prompt-write-dark.png" style={{maxWidth: '400'}} /> ## Configu...
(QB_NEW_EN)
[grammar] ~41-~41: There might be a mistake here.
Context: ...te-dark.png" style={{maxWidth: '400'}} /> ## Configuration Options ### Model ...
(QB_NEW_EN)
🔇 Additional comments (2)
playgrounds/columns/column-management.mdx (1)
9-9: Confirm exact UI label.
Is the button labeled “Playground Action” or “Playground Actions/Actions”? Please align text with the UI.playgrounds/columns/prompt.mdx (1)
46-49: Verify provider/model list reflects current support.
Providers and model names evolve quickly; ensure this list matches what the product actually supports today.
nina-kollman
changed the title
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 9e5d526 in 30 seconds. Click for details.
- Reviewed
17lines of code in1files - Skipped
0files when reviewing. - Skipped posting
1draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. evaluators/intro.mdx:32
- Draft comment:
The addition of the 'Where to Use Evaluators' section is clear and informative. Please ensure that the internal links (../playgrounds/quick-start and ../experiments/introduction) are up-to-date. Also, consider maintaining consistent styling (e.g., punctuation in bullet points) throughout the document. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%None
Workflow ID: wflow_nFvl9mL8oKQy4RFd
You can customize
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (4)
evaluators/intro.mdx (4)
16-21: Fix heading grammar and standardize terminology.
- “Evaluators types” → “Evaluator types”.
- Use consistent terminology: “prebuilt” and “preconfigured” are mixed; pick one (suggest “prebuilt”).
Apply this diff:
-## Evaluators types +## Evaluator types The system supports: -- **Custom evaluators** - Create your own evaluation logic tailored to specific needs -- **Built-in evaluators** - pre-configured evaluators by Traceloop for common assessment tasks +- **Custom evaluators** — create your own evaluation logic tailored to specific needs +- **Built-in evaluators** — prebuilt evaluators by Traceloop for common assessment tasks
22-24: Tighten wording; “define” can mislead.Readers are selecting to use or create, not “define”.
-In the Evaluator Library, select the evaluator you want to define. -You can either create a custom evaluator by clicking **New Evaluator** or choose one of the prebuilt **Made by Traceloop** evaluators. +In the Evaluator Library, select an evaluator to use. +You can create a custom evaluator via **New Evaluator** or choose a prebuilt **Made by Traceloop** evaluator.
33-34: Concise phrasing and pluralization.Use “schemas” and tighten “in order to”.
-Clicking on existing evaluators will present their input and output schema. This is valuable information in order to execute the evaluator [through the SDK](../experiments/running-from-code). +Clicking an evaluator shows its input and output schemas. This information helps you execute the evaluator [via the SDK](../experiments/running-from-code).
6-6: Consider capitalizing the proper feature name consistently.If “Evaluator Library” is a product surface, capitalize it in first mention (Line 6) to match later usage (Line 22).
-The evaluation library is a core feature of Traceloop, providing... +The Evaluator Library is a core feature of Traceloop, providing...Also applies to: 22-22
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
evaluators/intro.mdx(1 hunks)
🧰 Additional context used
🪛 LanguageTool
evaluators/intro.mdx
[grammar] ~18-~18: There might be a mistake here.
Context: ...# Evaluators types The system supports: - Custom evaluators - Create your own ev...
(QB_NEW_EN)
[style] ~33-~33: Consider a more concise word here.
Context: ...ut schema. This is valuable information in order to execute the evaluator [through the SDK]...
(IN_ORDER_TO_PREMIUM)
🔇 Additional comments (4)
evaluators/intro.mdx (4)
1-4: Front matter looks good.Title/description are clear and concise.
6-15: Strong, clear motivation.Well-written overview of evaluator purpose and failure modes.
25-31: Image assets confirmed presentThe image files
img/evaluator/eval-library-light.pngandimg/evaluator/eval-library-dark.pngwere found in the repository (checked inpublic/,static/, and project root), so there will be no broken images at build time.
39-40: All linked docs exist and paths are correct. Verified that bothplaygrounds/quick-start.mdxandexperiments/introduction.mdxare present in the repo, so the relative links inevaluators/intro.mdx(lines 39–40) will resolve correctly in the built site.
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 63a51bd in 1 minute and 24 seconds. Click for details.
- Reviewed
29lines of code in1files - Skipped
0files when reviewing. - Skipped posting
1draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. playgrounds/columns/prompt.mdx:58
- Draft comment:
Consider adding alt attributes to thetags (lines 58–67) for accessibility. An alt text (e.g., 'Schema configuration screenshot - light mode') helps screen readers and improves SEO.
- Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 20% vs. threshold = 50% While accessibility is important, the rules state not to comment on UI/styling changes and to assume the author did them correctly. The comment is about UI accessibility rather than logic. Additionally, this appears to be a documentation MDX file where accessibility may be handled differently than regular web pages. Without more context about the project's accessibility standards, we should be cautious about making assumptions. The suggestion could improve accessibility for users. Missing alt text could be considered a functional issue rather than just styling. Per the rules, we should assume UI changes were done correctly and avoid making UI-related comments. Without clear evidence of the project's accessibility requirements, we can't be certain this is actually an issue. The comment should be deleted as it relates to UI/styling rather than logic, and we should assume the author handled UI aspects correctly per the review rules.
Workflow ID: wflow_cGUZbqQfFthYl58J
You can customize
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 0fe9af1 in 48 seconds. Click for details.
- Reviewed
26lines of code in2files - Skipped
0files when reviewing. - Skipped posting
2draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. playgrounds/columns/column-management.mdx:6
- Draft comment:
Grammar fix: change 'analysis evolve' to 'analysis evolves'. - Reason this comment was not posted:
Comment did not seem useful. Confidence is useful =0%<= threshold50%This comment is purely informative and suggests a grammar fix. It doesn't provide a code suggestion or address a potential issue in the code. According to the rules, purely informative comments should be removed.
2. playgrounds/columns/data-columns.mdx:80
- Draft comment:
Consistency fix: update image src for light mode from 'play-single-select-dark.png' to 'play-single-select-light.png'. - Reason this comment was not posted:
Comment did not seem useful. Confidence is useful =0%<= threshold50%This comment is purely informative, as it just states what was done without suggesting any changes or asking for clarification. It doesn't provide any actionable feedback or raise any concerns about the code.
Workflow ID: wflow_UBG87XfZlcU9D0Ti
You can customize
Important
Enhances documentation for Evaluators and Playgrounds, adding new sections and improving navigation, with a minor
.gitignoreupdate..gitignoreto ignore a local tool directory and added a comment.This description was created by
for 0fe9af1. You can customize this summary. It will automatically update as commits are pushed.
Summary by CodeRabbit
Documentation
Chores