@@ -0,0 +1,63 @@
+// Generate examples/*.md verbatim from a real benchmark run (output.json):
+// each file shows the same task answered with no skill vs with ponytail, same model.
+//   node benchmarks/generate-examples.mjs
+import { readFileSync, writeFileSync } from 'node:fs';
+import loc from './loc.js';
+
+const j = JSON.parse(readFileSync(new URL('./output.json', import.meta.url), 'utf8'));
+const isHaiku = (id) => id.includes('haiku');
+
+const meta = [
+  [/validates email/, 'email-validation', 'Email Validation'],
+  [/debounce/,        'debounce',         'Debounce'],
+  [/sales\.csv/,      'csv-sum',          'CSV Sum'],
+  [/countdown timer/, 'react-countdown',  'Countdown Timer'],
+  [/rate limiting/,   'rate-limit',       'Rate Limiting'],
+];
+
+const pick = (re, armIdx) =>
+  j.results.results.find((r) => isHaiku(r.provider.id) && r.promptIdx === armIdx && re.test(r.vars.task));
+
+const rows = [];
+for (const [re, slug, title] of meta) {
+  const b = pick(re, 0), p = pick(re, 2);
+  if (!b || !p) { console.log('MISS', slug, !!b, !!p); continue; }
+  const bL = loc(b.response.output).score, pL = loc(p.response.output).score;
+  const md = `# ${title}
+
+**Task:** "${b.vars.task}"
+
+Verbatim model output from a benchmark run — Claude Haiku 4.5, no-skill arm vs ponytail arm, temperature 1, source \`benchmarks/output.json\`. Reproduce: \`npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml\`.
+
+## Without Ponytail — ${bL} lines of code
+
+${b.response.output.trim()}
+
+## With Ponytail — ${pL} lines of code
+
+${p.response.output.trim()}
+
+**${bL} → ${pL} lines of code** — same model, same prompt.
+`;
+  writeFileSync(new URL(`../examples/${slug}.md`, import.meta.url), md);
+  rows.push([title, slug, bL, pL]);
+  console.log('wrote examples/' + slug + '.md', bL, '->', pL);
+}
+
+const tbl = rows.map(([t, s, b, p]) => `| [${t}](${s}.md) | ${b} | ${p} |`).join('\n');
+const readme = `# Examples
+
+Real model output, verbatim from benchmark runs — the same task answered by the same model
+with no skill (\`## Without Ponytail\`) and with ponytail (\`## With Ponytail\`), so you can
+compare side by side. Model: Claude Haiku 4.5, temperature 1, source \`benchmarks/output.json\`.
+
+These are not hand-written. Reproduce them yourself:
+\`npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml\`. Method, all three models, and
+median-of-10 numbers: [../benchmarks/](../benchmarks/).
+
+| Example | Without (LOC) | With (LOC) |
+|---|--:|--:|
+${tbl}
+`;
+writeFileSync(new URL('../examples/README.md', import.meta.url), readme);
+console.log('wrote examples/README.md');
@@ -0,0 +1,17 @@
+# Examples
+
+Real model output, verbatim from benchmark runs — the same task answered by the same model
+with no skill (`## Without Ponytail`) and with ponytail (`## With Ponytail`), so you can
+compare side by side. Model: Claude Haiku 4.5, temperature 1, source `benchmarks/output.json`.
+
+These are not hand-written. Reproduce them yourself:
+`npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml`. Method, all three models, and
+median-of-10 numbers: [../benchmarks/](../benchmarks/).
+
+| Example | Without (LOC) | With (LOC) |
+|---|--:|--:|
+| [Email Validation](email-validation.md) | 75 | 3 |
+| [Debounce](debounce.md) | 116 | 10 |
+| [CSV Sum](csv-sum.md) | 20 | 3 |
+| [Countdown Timer](react-countdown.md) | 267 | 9 |
+| [Rate Limiting](rate-limit.md) | 128 | 10 |
@@ -0,0 +1,71 @@
+# CSV Sum
+
+**Task:** "Write Python code that reads sales.csv and sums the 'amount' column."
+
+Verbatim model output from a benchmark run — Claude Haiku 4.5, no-skill arm vs ponytail arm, temperature 1, source `benchmarks/output.json`. Reproduce: `npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml`.
+
+## Without Ponytail — 20 lines of code
+
+# Python code to read sales.csv and sum the 'amount' column
+
+```python
+import pandas as pd
+
+# Read the CSV file
+df = pd.read_csv('sales.csv')
+
+# Sum the 'amount' column
+total_amount = df['amount'].sum()
+
+# Print the result
+print(f"Total amount: ${total_amount:,.2f}")
+```
+
+## Alternative methods:
+
+**Using CSV module (without pandas):**
+```python
+import csv
+
+total_amount = 0
+
+with open('sales.csv', 'r') as file:
+    reader = csv.DictReader(file)
+    for row in reader:
+        total_amount += float(row['amount'])
+
+print(f"Total amount: ${total_amount:,.2f}")
+```
+
+**Using pandas with error handling:**
+```python
+import pandas as pd
+
+try:
+    df = pd.read_csv('sales.csv')
+    total_amount = df['amount'].sum()
+    print(f"Total amount: ${total_amount:,.2f}")
+except FileNotFoundError:
+    print("Error: sales.csv not found")
+except KeyError:
+    print("Error: 'amount' column not found")
+```
+
+**The pandas method is recommended** because it's:
+- More concise and readable
+- Handles data types automatically
+- Provides built-in error handling
+- Efficient for large files
+
+## With Ponytail — 3 lines of code
+
+```python
+import csv
+
+total = sum(float(row['amount']) for row in csv.DictReader(open('sales.csv')))
+print(total)
+```
+
+Skipped: pandas, error handling, file closing — add when the CSV is large, malformed, or you need more analysis.
+
+**20 → 3 lines of code** — same model, same prompt.