The Workbench on a Real Repo
Eleven lessons of surfaces are worth nothing if they do not survive contact with a real codebase. This lesson runs the same task twice on a small sample app: prompt-only versus workbench-guided. The numbers do the arguing. Bring the seven workbench surfaces together on a small application. Run the same task twice (prompt-only and workbench-guided) and measure five outcomes. Read the before/after report and decide which surfaces gave the most leverage. Defend the workbench against a "but my model is good enough" pushback. A demo on a toy task convinces no one. The case for the workbench is made when a real-feeling task on a real-feeling repo lands in production with fewer failures, fewer reverts, and a packet the next session can use. This lesson ships that real-feeling repo and runs the same task through both pipelines. The result is a before/after report you can hand to a skeptic. A minimal FastAPI-style handler in sampleapp/: app.py with /signup (no validation yet). testapp.py with one happy-path test. README.md and scripts/release.sh as forbidden-zone bait. Prompt-only: Read the README. Read app.py. Edit files. Claim done. Workbench-guided: Run init script (Lesson 35). Read scope contract (Lesson 36). Read state (Lesson 34). Edit allowed files only. Run acceptance command via feedback runner (Lesson 37). Run verification gate (Lesson 38). Run reviewer (Lesson 39). Generate handoff…
The Workbench on a Real Repo: Eleven lessons of surfaces are worth nothing if they do not survive contact with a real codebase. This lesson runs the same task…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.