justin/ai-workflow-course
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(wiki): sync from modules/ @ 7f439212

Claude (agent)
2026-06-23 22:24:46 +00:00
parent 0c6d3ffc96
commit 7a4e1f6491
28 changed files with 308 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
01-the-copy-paste-problem.md
+12
@@ -125,6 +125,18 @@ you already feel is the curriculum.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/01-the-copy-paste-problem/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 1"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell + a tiny bit of Python (just enough to have something real to run). You will
not write Python; you'll run a small app we provide.
02-version-control-as-a-safety-net.md
+12
@@ -138,6 +138,18 @@ Everything above is standard Git. What's *specific* to AI-assisted work:
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/02-version-control-as-a-safety-net/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 2"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands), on the `tasks-app` project from Module 1.
**You'll need:** Git installed (`git --version`; if it's missing, install from
03-version-control-for-words.md
+12
@@ -199,6 +199,18 @@ Here's why this module is more than "learn Git on easy mode":
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/03-version-control-for-words/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 3"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands) plus a little markdown writing, on the `tasks-app` from
Modules 1–2. The AI stays in the **browser**; you copy its draft into the file yourself, exactly as
in Module 2.
04-getting-the-ai-out-of-the-browser.md
+12
@@ -287,6 +287,18 @@ loop and the loop is unchanged.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/04-getting-the-ai-out-of-the-browser/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 4"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell + a small Python change *made by the AI, not by you*. You'll drive an agentic
tool; the tool writes the Python.
05-commit-the-ai-config.md
+12
@@ -201,6 +201,18 @@ Three things make this specifically an AI problem, not a generic config chore:
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/05-commit-the-ai-config/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 5"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell + markdown, on the `tasks-app` project from Modules 1–2. You'll use your
editor-integrated AI (Module 4) for the part where the AI obeys the file.
06-branches-sandboxes-for-experiments.md
+12
@@ -239,6 +239,18 @@ Everything above is standard Git. Here's why it matters *more* in an AI-assisted
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/06-branches-sandboxes-for-experiments/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 6"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands), driving the `tasks-app` from Modules 1–2 with your
editor-integrated AI from Module 4.
07-worktrees-running-agents-in-parallel.md
+12
@@ -219,6 +219,18 @@ to run two agents and watch them overwrite each other's work.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/07-worktrees-running-agents-in-parallel/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 7"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands), plus two AI edit sessions on the `tasks-app`.
In this lab you'll run **two AI sessions at the same time** on the same project (one adding a
08-remotes-and-hosting.md
+12
@@ -301,6 +301,18 @@ A remote isn't only about durability. It's what the AI parts of this course run
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/08-remotes-and-hosting/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 8"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands), plus one short provided shell script. Runs on macOS, Linux,
WSL, or Git Bash on Windows. Continues the `tasks-app` repo from Module 2.
09-issues-and-the-task-layer.md
+12
@@ -231,6 +231,18 @@ valuable, not less.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/09-issues-and-the-task-layer/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 9"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** Markdown + shell, against the `tasks-app` repo you pushed to a forge in Module 8.
You'll draft issues as Markdown locally (so you can version and reuse the format), then have your
10-reviewing-code-you-didnt-write.md
+12
@@ -197,6 +197,18 @@ you couldn't do yourself.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/10-reviewing-code-you-didnt-write/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 10"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell + the Python `tasks-app`. You won't write Python; you'll open a PR for a
real change, then review a diff the "AI" produced and catch the trap planted in it.
11-collaboration-humans-and-agents.md
+12
@@ -259,6 +259,18 @@ You're not learning collaboration *and then* learning to work with agents. They'
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/11-collaboration-humans-and-agents/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 11"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell plus your host's web UI for the issue, PR, review, and merge steps. From
Module 4 on you direct the AI to do the git work and verify the result; the only commands you type by
hand here are read-only checks like `git branch` and `git show`. You'll implement the feature with
12-revert-reset-and-recovery.md
+12
@@ -227,6 +227,18 @@ Recovery was always a real skill. AI raises its value on every axis:
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/12-revert-reset-and-recovery/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 12"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git commands), on the `tasks-app` from Modules 1–2.
You'll do the two scenarios that matter most: **revert a bad merge** that's already on `main`, then
13-testing-in-the-ai-era.md
+12
@@ -208,6 +208,18 @@ Passing for the right reason is the skill.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/13-testing-in-the-ai-era/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 13"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** Python (standard-library `unittest`), with a couple of shell commands to run the
suite. Nothing to install.
14-continuous-integration.md
+12
@@ -211,6 +211,18 @@ the more you need a reviewer that checks behavior instead of believing the diff.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/14-continuous-integration/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 14"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** YAML (the CI config) plus the Python `tasks-app` and shell commands. You direct
the agent to place files, commit, and recover; you commit a starter workflow, watch it pass, then
break it on purpose and watch CI catch it.
15-security-scanning.md
+9
@@ -209,6 +209,15 @@ add them *despite* using AI; using AI is what moves them from "nice to have" to
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/15-security-scanning/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/15-security-scanning/lab ~/ai-workflow-course/15-security-scanning-lab
> cd ~/ai-workflow-course/15-security-scanning-lab && git init -b main && git add -A && git commit -m "start: module 15"
> ```
**Lab language:** shell, driving Python tooling, on the `tasks-app` from Module 1. You'll install two
scanners (both pip-installable, cross-platform), let the AI introduce all three problems, catch them,
and wire the catch into your pipeline.
16-containers-and-reproducible-environments.md
+12
@@ -170,6 +170,18 @@ Docker itself you may already know. What makes containers matter *more* in AI-as
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/16-containers-and-reproducible-environments/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 16"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Docker CLI) on the `tasks-app` from Module 1. You won't write Python; you'll
containerize and run the app you already have.
17-secrets-config-and-environments.md
+9
@@ -283,6 +283,15 @@ model will keep offering it. Concretely:
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/17-secrets-config-and-environments/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/17-secrets-config-and-environments/lab ~/ai-workflow-course/17-secrets-config-and-environments-lab
> cd ~/ai-workflow-course/17-secrets-config-and-environments-lab && git init -b main && git add -A && git commit -m "start: module 17"
> ```
**Lab language:** Python + shell, on a new `sync` feature for the `tasks-app` from Module 1.
You'll take a file that hardcodes a secret (the exact thing an AI hands you) and refactor it so the
18-continuous-delivery-and-deployment.md
+9
@@ -205,6 +205,15 @@ between an autonomous contributor and your users.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/18-continuous-delivery-and-deployment/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/18-continuous-delivery-and-deployment/lab ~/ai-workflow-course/18-continuous-delivery-and-deployment-lab
> cd ~/ai-workflow-course/18-continuous-delivery-and-deployment-lab && git init -b main && git add -A && git commit -m "start: module 18"
> ```
**Lab language:** shell, driving the container tooling from Module 16. You'll extend the `tasks-app`
into a tiny running service, then build a deploy script that ships it locally with a health check and
automatic rollback, the whole CD motion simulated on your own machine.
19-runners-the-compute-behind-automation.md
+9
@@ -208,6 +208,15 @@ review reflex from Module 10 has to extend to the workflow files, not just the a
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/19-runners-the-compute-behind-automation/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/19-runners-the-compute-behind-automation/lab ~/ai-workflow-course/19-runners-the-compute-behind-automation-lab
> cd ~/ai-workflow-course/19-runners-the-compute-behind-automation-lab && git init -b main && git add -A && git commit -m "start: module 19"
> ```
**Lab language:** shell, plus a one-line edit to the YAML workflow from Module 14. Runs on your own
machine and your own forge, with no hosted account required for the core of it.
20-mcp-servers-giving-the-ai-hands.md
+12
@@ -231,6 +231,18 @@ That changes what matters about the integration.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/20-mcp-servers-giving-the-ai-hands/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 20"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** Python (a ~15-line MCP server) plus your agentic tool's config. Runs on your own
machine, any OS.
21-skills-teaching-the-ai-your-playbook.md
+12
@@ -166,6 +166,18 @@ On paper this is just "write a runbook." The AI-specific twist is what changes t
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/21-skills-teaching-the-ai-your-playbook/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 21"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** markdown (the skill file) plus shell and Python (the `tasks-app`). You'll write a
skill, then have your editor-integrated AI (Module 4) execute it.
22-securing-third-party-mcp-and-skills.md
+9
@@ -201,6 +201,15 @@ skills different from any dependency you've shipped before:
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/22-securing-third-party-mcp-and-skills/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/22-securing-third-party-mcp-and-skills/lab ~/ai-workflow-course/22-securing-third-party-mcp-and-skills-lab
> cd ~/ai-workflow-course/22-securing-third-party-mcp-and-skills-lab && git init -b main && git add -A && git commit -m "start: module 22"
> ```
**Lab language:** shell, with a small Python file to read. You'll audit a deliberately sketchy
third-party skill, run a static red-flag scan over it, then reproduce a prompt-injection attack
against the Module 1 `tasks-app` and apply the least-privilege mitigation.
23-working-with-existing-codebases.md
+9
@@ -168,6 +168,15 @@ into a revertable diff.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/23-working-with-existing-codebases/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/23-working-with-existing-codebases/lab ~/ai-workflow-course/23-working-with-existing-codebases-lab
> cd ~/ai-workflow-course/23-working-with-existing-codebases-lab && git init -b main && git add -A && git commit -m "start: module 23"
> ```
**Lab language:** shell + the provided Python script (`orient.py`); you run it, you don't write it.
This lab does **not** use `tasks-app`; the entire point is a codebase you *didn't* write.
24-assistive-agents.md
+9
@@ -173,6 +173,15 @@ occasionally wrong with no consequences.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/24-assistive-agents/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/24-assistive-agents/lab ~/ai-workflow-course/24-assistive-agents-lab
> cd ~/ai-workflow-course/24-assistive-agents-lab && git init -b main && git add -A && git commit -m "start: module 24"
> ```
**Lab language:** Python (two small stdlib-only scripts) driven by Claude Code (`claude`; sub your
own agent). No `pip install`, no hosted account. The scripts do the deterministic halves (assemble
the prompt, validate and render the response, present the decision gate); the model does the one part
25-autonomous-agents.md
+9
@@ -208,6 +208,15 @@ the job is non-deterministic and persuasive**, and that changes what "automation
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/25-autonomous-agents/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/25-autonomous-agents/lab ~/ai-workflow-course/25-autonomous-agents-lab
> cd ~/ai-workflow-course/25-autonomous-agents-lab && git init -b main && git add -A && git commit -m "start: module 25"
> ```
**Lab language:** Python (one orchestrator script) plus a little shell and Git. It runs on your own
machine, any OS, against the `tasks-app` repo from Module 1, with no forge account or paid agent
required to complete it.
26-orchestrating-multiple-agents.md
+12
@@ -260,6 +260,18 @@ imaginary, and that the fix was a ten-minute coordination plan you skipped.
## Hands-on lab
> **Starting point (this lab is skip-friendly).** You do not need to have done the earlier labs.
> To begin from a clean, known state, copy this module's snapshot into a fresh `tasks-app` and
> make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/modules/26-orchestrating-multiple-agents/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: module 26"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell (Git + a couple of helper scripts) driving multiple AI edit sessions on the
`tasks-app`, integrated through PRs.
27-evals.md
+9
@@ -218,6 +218,15 @@ That's the durable skill. Models are weather. The eval set is the thermometer yo
## Hands-on lab
> **Starting point (this lab is skip-friendly).** This lab is self-contained and does not depend
> on the earlier labs. Its files live in `modules/27-evals/lab/`. Copy them into a working folder
> and make a first commit so you start clean:
>
> ```bash
> cp -r ~/ai-workflow-course/modules/27-evals/lab ~/ai-workflow-course/27-evals-lab
> cd ~/ai-workflow-course/27-evals-lab && git init -b main && git add -A && git commit -m "start: module 27"
> ```
**Lab language:** Python + shell. You'll run a tiny eval harness, point an agent at a task, and run
a regression eval across a "model swap."
capstone.md
+11
@@ -133,6 +133,17 @@ swappable part; the workflow is the durable skill*), and you just lived it inste
## Hands-on lab
> **Starting point (this lab is skip-friendly).** The capstone runs the whole loop on one feature.
> To begin from a clean app, copy the snapshot into a fresh `tasks-app` and make the first commit:
>
> ```bash
> mkdir -p ~/ai-workflow-course/tasks-app
> cp -r ~/ai-workflow-course/capstone/lab/start/. ~/ai-workflow-course/tasks-app/
> cd ~/ai-workflow-course/tasks-app && git init -b main && git add -A && git commit -m "start: capstone"
> ```
>
> Already carrying your `tasks-app` from earlier modules? Keep using it and ignore this box.
**Lab language:** shell + Python, on the `tasks-app` repo. You'll direct Claude Code (`claude`; sub
your own agent) to do the git and the edits (M4); you make the calls and verify each result.