Dev to main, 16th July, 2026

src/components/Header.astro

@@ -86,16 +86,24 @@ const currentPath = Astro.url.pathname;
 
       <!-- Right Actions -->
       <div class="flex items-center gap-3 flex-shrink-0">
+        <!-- Star on GitHub -->
         <a
-          href="https://github.com/future-agi"
+          href="https://github.com/future-agi/future-agi"
           target="_blank"
           rel="noopener noreferrer"
-          aria-label="GitHub"
-          class="hidden sm:inline-flex items-center p-1.5 text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] transition-colors"
+          class="hidden sm:inline-flex items-center gap-1.5 px-2.5 py-1.5 text-sm text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] transition-colors group"
+          aria-label="Star on GitHub"
         >
-          <svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true">
-            <path fill-rule="evenodd" clip-rule="evenodd" d="M12 2C6.477 2 2 6.484 2 12.017c0 4.425 2.865 8.18 6.839 9.504.5.092.682-.217.682-.483 0-.237-.008-.868-.013-1.703-2.782.605-3.369-1.343-3.369-1.343-.454-1.158-1.11-1.466-1.11-1.466-.908-.62.069-.608.069-.608 1.003.07 1.531 1.032 1.531 1.032.892 1.53 2.341 1.088 2.91.832.092-.647.35-1.088.636-1.338-2.22-.253-4.555-1.113-4.555-4.951 0-1.093.39-1.988 1.029-2.688-.103-.253-.446-1.272.098-2.65 0 0 .84-.27 2.75 1.026A9.564 9.564 0 0112 6.844c.85.004 1.705.115 2.504.337 1.909-1.296 2.747-1.027 2.747-1.027.546 1.379.202 2.398.1 2.651.64.7 1.028 1.595 1.028 2.688 0 3.848-2.339 4.695-4.566 4.943.359.309.678.92.678 1.855 0 1.338-.012 2.419-.012 2.747 0 .268.18.58.688.482A10.02 10.02 0 0022 12.017C22 6.484 17.522 2 12 2z"/>
+          <span>Star on</span>
+          <svg class="w-[18px] h-[18px]" fill="currentColor" viewBox="0 0 24 24">
+            <path fill-rule="evenodd" clip-rule="evenodd" d="M12 2C6.477 2 2 6.484 2 12.017c0 4.425 2.865 8.18 6.839 9.504.5.092.682-.217.682-.483 0-.237-.008-.868-.013-1.703-2.782.605-3.369-1.343-3.369-1.343-.454-1.158-1.11-1.466-1.11-1.466-.908-.62.069-.608.069-.608 1.003.07 1.531 1.032 1.531 1.032.892 1.53 2.341 1.088 2.91.832.092-.647.35-1.088.636-1.338-2.22-.253-4.555-1.113-4.555-4.951 0-1.093.39-1.988 1.029-2.688-.103-.253-.446-1.272.098-2.65 0 0 .84-.27 2.75 1.026A9.564 9.564 0 0112 6.844c.85.004 1.705.115 2.504.337 1.909-1.296 2.747-1.027 2.747-1.027.546 1.379.202 2.398.1 2.651.64.7 1.028 1.595 1.028 2.688 0 3.848-2.339 4.695-4.566 4.943.359.309.678.92.678 1.855 0 1.338-.012 2.419-.012 2.747 0 .268.18.58.688.482A10.019 10.019 0 0022 12.017C22 6.484 17.522 2 12 2z" />
           </svg>
+          <span class="inline-flex items-center gap-1 px-1.5 py-0.5 rounded-md bg-[var(--color-bg-tertiary)] border border-[var(--color-border-subtle)] text-[11px] text-[var(--color-text-secondary)] group-hover:border-[var(--color-border-accent)] transition-colors min-w-[28px] justify-center">
+            <svg class="w-2.5 h-2.5" style="color: #fbbf24;" fill="currentColor" viewBox="0 0 24 24">
+              <path d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"/>
+            </svg>
+            <span data-github-stars>—</span>
+          </span>
         </a>
 
         <a
@@ -257,5 +265,42 @@ const currentPath = Astro.url.pathname;
 
     setupHeader();
     document.addEventListener('astro:page-load', setupHeader);
+
+    // GitHub star counter - fetches live count, caches for 10 min
+    function formatStars(count) {
+      if (count >= 1000) {
+        return (count / 1000).toFixed(count >= 10000 ? 0 : 1).replace(/\.0$/, '') + 'k';
+      }
+      return String(count);
+    }
+
+    async function loadGitHubStars() {
+      const targets = document.querySelectorAll('[data-github-stars]');
+      if (!targets.length) return;
+      const CACHE_KEY = 'gh-stars-future-agi';
+      const CACHE_TTL = 10 * 60 * 1000;
+      try {
+        const cached = localStorage.getItem(CACHE_KEY);
+        if (cached) {
+          const { count, ts } = JSON.parse(cached);
+          if (Date.now() - ts < CACHE_TTL && typeof count === 'number') {
+            targets.forEach(el => { el.textContent = formatStars(count); });
+            return;
+          }
+        }
+      } catch {}
+      try {
+        const res = await fetch('https://api.github.com/repos/future-agi/future-agi');
+        if (!res.ok) throw new Error('GitHub API error');
+        const data = await res.json();
+        const count = data.stargazers_count || 0;
+        targets.forEach(el => { el.textContent = formatStars(count); });
+        try { localStorage.setItem(CACHE_KEY, JSON.stringify({ count, ts: Date.now() })); } catch {}
+      } catch {
+        targets.forEach(el => { el.textContent = '★'; });
+      }
+    }
+    loadGitHubStars();
+    document.addEventListener('astro:page-load', loadGitHubStars);
   })();
 </script>

src/lib/navigation.ts

@@ -324,9 +324,19 @@ export const tabNavigation: NavTab[] = [
             title: 'Guides',
             items: [
               { title: 'Running Evaluations', href: '/docs/evaluation/guides/running-evaluations' },
+              {
+                title: 'Explore playground',
+                items: [
+                  { title: 'The Evaluations page', href: '/docs/evaluation/guides/explore-playground' },
+                  { title: 'Test an eval', href: '/docs/evaluation/guides/explore-playground/test-an-eval' },
+                  { title: 'Usage & analytics', href: '/docs/evaluation/guides/explore-playground/usage-analytics' },
+                ]
+              },
               { title: 'Create a custom eval', href: '/docs/evaluation/guides/custom-evals' },
               { title: 'Build a composite evals', href: '/docs/evaluation/guides/composite-evals' },
+              { title: 'Set up guardrails', href: '/docs/evaluation/guides/guardrails' },
               { title: 'Add ground truth', href: '/docs/evaluation/guides/ground-truth' },
+              { title: 'Collect feedback', href: '/docs/evaluation/guides/collect-feedback' },
               { title: 'Use custom models', href: '/docs/evaluation/guides/custom-models' },
               { title: 'Evaluate in CI/CD', href: '/docs/evaluation/guides/cicd' },
               { title: 'Advanced usage', href: '/docs/evaluation/guides/advanced-usage' },

src/pages/docs/evaluation/guides/collect-feedback.mdx

@@ -0,0 +1,132 @@
+---
+title: "Collect feedback"
+description: "Teach an evaluator your standard by correcting the results it gets wrong"
+---
+
+[Feedback](/docs/evaluation/concepts/feedback) is a correction you record on an eval result, which every later run retrieves and shows to the [evaluator model](/docs/evaluation/concepts/evaluator-models) as an example before it scores. This guide corrects a result on a dataset, chooses what gets re-scored, and reviews everything your team has corrected.
+
+You usually work in batches: correct the results an eval got wrong across a run, then re-run and watch it converge on your team's judgment. A single correction nudges the evaluator; a batch is what moves it, and most evals settle in a few rounds.
+
+<Note>
+Feedback isn't available for [code evals](/docs/evaluation/concepts/eval-types) (no evaluator model to steer), [composite evals](/docs/evaluation/concepts/composite-evals) (a roll-up of child scores), raw-number metrics (a computed value with no pass or fail to correct, unlike a Score eval's gradable 0-100), or results in an error state (no score to correct). Code and composite evals also have no Feedback tab.
+</Note>
+
+## Collect feedback on a dataset
+
+This example corrects an eval result on a [dataset](/docs/dataset), then chooses what gets re-scored.
+
+### Open the drawer
+
+- Hover any result in an eval column to see the reason the eval gave
+- Click **Add feedback** in the popover under that reason
+
+You can also open a row and click **Add Feedback** on the eval in the datapoint drawer. Either way the drawer names the eval and repeats its explanation, so you're correcting against what it actually said rather than from memory.
+
+<img src="/images/docs/evaluation/guides/collect-feedback/dataset-add-feedback-hover.png" alt="Hovering an eval result in a dataset grid, with the reason in a popover and an Add feedback button beneath it" style={{ borderRadius: '5px' }} />
+*Hover a result to see the reason the eval gave, and the button that opens the drawer*
+
+### Correct the result
+
+The first field takes the shape of the eval's [output type](/docs/evaluation/reference/output-types):
+
+| Output type | Label | What you enter |
+|---|---|---|
+| Pass/Fail, or a single choice | **Select a right value** | The verdict it should have returned |
+| Multiple choices | **Select the right value(s)** | Every label that should've applied |
+| Score | **Write a right value** | A number between 0 and 100 |
+| Reason | **Write a right value** | The corrected text |
+
+Then write the explanation the eval should have given. This is the field that teaches it, so name the rule you're applying instead of restating the verdict. The value and the explanation are both required.
+
+<img src="/images/docs/evaluation/guides/collect-feedback/dataset-correct-result.png" alt="The Add feedback drawer for a score eval, with the eval's own explanation on top, a Write a right value number field, and an explanation box" style={{ borderRadius: '5px' }} />
+*The drawer repeats the eval's explanation above the fields, so you correct against what it said*
+
+### Choose what gets re-scored
+
+Every option stores your correction against the eval. What they differ on is how much gets re-scored:
+
+| Option | What it does |
+|---|---|
+| **Re-tune** | Stores the correction. Nothing is re-scored, and later runs pick it up |
+| **Re-calculate for this row** | Stores it, then re-runs the eval on this row |
+| **Re-tune and re-calculate for this dataset** | Stores it, then re-runs the eval on every run in the dataset |
+
+The last two re-score existing results, so they take a while on a big dataset; the eval column updates in place as each result finishes, so you can watch it there. Reach for **Re-tune** when you're labelling a batch of corrections and only want them counting from the next run onward.
+
+Whichever you pick, the eval's own criteria stay as they are: your correction is stored and pulled into later runs as an example.
+
+<img src="/images/docs/evaluation/guides/collect-feedback/dataset-rescore-options.png" alt="The filled Add feedback drawer showing the three re-scoring options with Re-calculate for this row selected, and Submit feedback" style={{ borderRadius: '5px' }} />
+*Pick what gets re-scored, then submit*
+
+## Collect feedback in the eval playground
+
+You can also correct a result straight from the eval's own page, without opening a dataset. The steps match the dataset flow, apart from three things: the field labels differ, there are two re-scoring options instead of three, and the row gets a thumb once you submit.
+
+### Open the drawer from the Usage tab
+
+- From **Evals**, open an eval and go to its **Usage** tab
+- Click a row to open its panel
+- Click **Add Feedback**, or **Edit Feedback** if the row already carries one
+
+<img src="/images/docs/evaluation/guides/collect-feedback/playground-add-feedback.png" alt="An eval's Usage tab with a result's panel open, showing its score and reason and an Add Feedback button" style={{ borderRadius: '5px' }} />
+*Open a result's panel on the Usage tab, then click Add Feedback*
+
+### Enter your correction
+
+The drawer here is titled **Feedbacks for Auto Learning**. It has the same two fields as a dataset, under different labels:
+
+- Pick the verdict under **Choose a right value**, or **Write a right value** for a score or text eval
+- Fill in **What would you like to improve** with why the result was wrong
+
+<img src="/images/docs/evaluation/guides/collect-feedback/playground-correct-result.png" alt="The Feedbacks for Auto Learning drawer with a Choose a right value Passed or Failed field and a What would you like to improve box" style={{ borderRadius: '5px' }} />
+*The playground drawer, with the same two fields under different labels*
+
+### Pick a re-scoring option
+
+Both store the correction; the difference is whether past runs get re-scored too:
+
+| Option | What it does |
+|---|---|
+| **Re-tune** | Stores the correction for later runs |
+| **Re-calculate and re-tune** | Stores it, then re-scores every past run of this eval |
+
+Submit, and the row gets a thumb on the Usage tab: a green thumbs-up where you answered passed, a red thumbs-down where you answered failed. That's the quickest way to see which results you've already been through.
+
+<img src="/images/docs/evaluation/guides/collect-feedback/playground-rescore-options.png" alt="The filled playground drawer with Failed chosen, an improvement note written, and the Re-tune and Re-calculate and re-tune options" style={{ borderRadius: '5px' }} />
+*Pick one of the two options, then submit feedback*
+
+## Review your corrections
+
+Every correction on an eval collects on its **Feedback** tab, whichever surface it came from. That tab is the record of what your team has taught the evaluator, so it's where you work from when you want to know whether it's converging. Open an eval and click **Feedback**.
+
+**Feedback History** lists one row per correction:
+
+| Column | What it shows |
+|---|---|
+| **Feedback** | The verdict you gave, as a **Correct** or **Incorrect** chip |
+| **Improvement Note** | The explanation you wrote |
+| **Action** | **Re-tune** or **Re-calculate**, whichever you picked |
+| **Source** | Where it came from, **Dataset** or **Playground** |
+| **By** | Who submitted it |
+| **Date** | When |
+
+A colored bar on the left edge of each row repeats the verdict at a glance. Before anyone has corrected the eval, the tab reads "No feedback submitted yet".
+
+Click a row to open the whole entry beside the list: the improvement note in full, the log ID it came from, and a read-only **Raw Data** view of the stored record. Step through entries with **j** and **k**, close with **Escape**, and click **Edit Feedback** to change one.
+
+<img src="/images/docs/evaluation/guides/collect-feedback/feedback-history.png" alt="The Feedback tab's history table with a correction's full entry open on the right, showing its improvement note, action, source, and raw data" style={{ borderRadius: '5px' }} />
+*The Feedback tab lists every correction, with the full entry open on the right*
+
+## Dive deeper
+
+<CardGroup cols={3}>
+  <Card title="Eval correction loop" icon="arrows-rotate" href="/docs/cookbook/evaluation/eval-correction-loop">
+    A worked example of turning corrections into a better eval
+  </Card>
+  <Card title="Create a custom eval" icon="wand-magic-sparkles" href="/docs/evaluation/guides/custom-evals">
+    Encode your corrections as rules the evaluator follows
+  </Card>
+  <Card title="Ground truth" icon="database" href="/docs/evaluation/concepts/ground-truth">
+    Calibrate an eval against reference rows instead of corrections
+  </Card>
+</CardGroup>