LPractice & Learn AI
deliver · advanced · 180 min

Capstone: the claims desk

Put the course together into one assistant for Parcel Desk and hand it to someone else to run.

Start step 1 ↓
HANDS-ON LAB · YOU RUN IT ON YOUR MACHINE · 4 STEPS
  1. Step 1 of 4

    Join the parts: extract the claim, look up policy, decide, approve over 100, pay

    Run this to check

    uv run claim_desk.py samples/damaged-01.txt

    You pass when

    A decision with the policy page it relied on. A large claim stops and waits for approval.

    Files you write

    • claim_desk.py
  2. Step 2 of 4

    Score it on 40 graded claims with your checked judge

    Run this to check

    uv run eval.py --suite capstone

    You pass when

    It meets the success number you wrote in lab 50. If not, the trace of the worst failures tells you which part to fix.

    Files you write

    • eval.py
  3. Step 3 of 4

    Run your five attacks against the finished assistant

    Run this to check

    uv run redteam.py; echo "exit $?"

    You pass when

    Exit 0: none succeed.

  4. Step 4 of 4

    Write the runbook: start, stop, where the logs are, the three most likely failures and their fix

    The work is finished when it keeps running after you have left.

    Run this to check

    wc -l RUNBOOK.md

    You pass when

    Under 80 lines. Give it to a colleague: they start the assistant, break it and fix it without asking you.

    Files you write

    • RUNBOOK.md
No transcript here on purpose. This page does not show terminal output, because model answers differ from run to run. Each step says what a pass looks like; your own terminal is the proof.