docs: multi-scenario evaluation example and failure classification for agentic workflow agent - #49891
Merged
Merged
Conversation
…-agentic-workflow.md Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Explore agent persona evaluation findings
docs: multi-scenario evaluation example and failure classification for agentic workflow agent
Aug 3, 2026
pelikhan
marked this pull request as ready for review
August 3, 2026 04:41
Contributor
There was a problem hiding this comment.
Pull request overview
Adds multi-scenario evaluation guidance and failure classification to the agentic workflow creation prompt.
Changes:
- Adds a three-persona evaluation prompt example.
- Defines a standardized recommendation table.
- Introduces failure categories and fallback actions.
Show a summary per file
| File | Description |
|---|---|
.github/aw/create-agentic-workflow.md |
Adds evaluation examples, output fields, and failure handling guidance. |
Review details
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 1/1 changed files
- Comments generated: 3
- Review effort level: Balanced
|
|
||
| To compare multiple persona or task slices in a single request, use the following prompt format: | ||
|
|
||
| > agentic-workflows evaluate these scenarios without creating files: |
|
|
||
| ### Failure Classification | ||
|
|
||
| When evaluating scenarios, classify any failure before stopping: |
|
|
||
| | Failure type | Symptom | Action | | ||
| |---|---|---| | ||
| | Transient issue | Network error, timeout, or quota exceeded | Retry once; if it persists, record `invocation_unavailable` and continue with partial results | |
Contributor
|
🎉 This pull request is included in a new release. Release: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Agent Persona Explorer found that the
agentic-workflowsagent had no discoverable path for evaluation-only requests, no multi-scenario comparison format, and no way to distinguish product gaps from transient invocation failures.Changes
.github/aw/create-agentic-workflow.mdMulti-Scenario Evaluation Example — adds a prompt template for requesting evaluation across multiple persona slices in one shot, plus a standard recommendation table schema (trigger, scope, tools, safe outputs, permissions, noop condition) to make cross-persona comparisons consistent:
Failure Classification — replaces the single vague fallback bullet with a three-row table distinguishing:
invocation_unavailable— transient (network/timeout/quota); retry oncecommand_not_supported— unsupported command; fall back to local guidanceresponse_unavailable— product gap (invocation succeeds, returns nothing); surface as missing capability, not an error.github/aw/github-agentic-workflows.md— no changes; the existing "Ad Hoc Scenario Evaluation" section already covers the evaluation-only entry point.