READER EDITION / ISSUE 002 / Revised 2026-11-20
Creative Agentic Computing
CodeFarmer / Issue 002
YOUR OWN AI WORKSHOP / RUN THE LAB

Run a brief.
Read the saved result.

Use the Terminal whose current folder contains programs and lab. This Python checker reads the local inventory and prints Ready for each required model:

python3 lab/beginner-walkthrough-2026-11-15/workshop_check.py

If it reports a missing service, open Ollama or start the other Terminal’s service command. If it reports a missing model, run the printed ollama pull line and repeat the check. The checker downloads nothing.

Ask for the two programs

python3 lab/local-workshop-2026-11-14/benchmark.py \
  --endpoint http://127.0.0.1:11434 \
  --models qwen3.5:4b llama3.2:latest \
  --out my-local-results

The driver sends both printed briefs to each model. Wait for four summaries and the Terminal prompt. Its my-local-results folder contains results.json, fixtures.json and Python files for candidates that passed the code-format checks.

Explain the examples it checked

python3 lab/beginner-walkthrough-2026-11-15/workshop_check.py --results my-local-results/results.json

A 4/4 line means four inputs matched expected records and preserved the input. For a failure, this checker prints expected and received data. Open the saved .py file in a text editor to inspect the function.