A Hands-On Course · 12 lessons

Agentic Workflows

How to actually run agents day to day — plan-first loops, parallel fleets, headless CI, reversible setup, and eval-driven development.

Short lessons (~5–8 min each), each with one tangible win and a retrieval-practice quiz. Built for engineers who already use AI coding tools and want the non-obvious mechanics.

Grounded in the agentpatterns.ai corpus (CC BY 4.0). Keep the Glossary open as you go.

Part 1 · The Inner Loop

1 Plan Before Code The single highest-leverage move in agent-assisted development isn't a better prompt. It's refusing to let the agent write code until it has described the system back to you. 2 Research, Plan, Implement Plan-first was the reflex. This is the structure underneath it — three phases, a cost ladder that makes the ordering non-negotiable, and a way to spend reasoning where it actually pays. 3 Where You Stand There are exactly three places a human can stand relative to an agent loop. Two of them scale badly. The third is where the leverage lives — and reversibility tells you when each is right.

Part 2 · Scaling Out

4 Becoming a Tech Lead Running several agents at once doesn't make you a faster coder. It makes you a tech lead — and your review bandwidth, not agent speed, becomes the thing that's actually scarce. 5 Sandboxes for Swarms Two agents writing to the same working directory is a recipe for lost writes and stale views. Git worktrees fix that cleanly — until agent count climbs high enough that the branching itself becomes the bottleneck. 6 Agents in the Pipeline An agent in CI is an agent with no human to redirect it. That changes everything — the cap on its turns, the source of its permissions, and what happens when its output merges unreviewed. 7 Handoffs Most complex tasks have a nuanced final tenth that needs human judgment. The trick isn't full automation — it's a clean handoff at the right moment, carrying just enough context to continue.

Part 3 · Keeping the Codebase Healthy

8 Snapshot and Roll Back Repository setup is where general agents quietly fail — and the fix is to make every state-changing command reversible, then verify with two roles instead of one exit code. 9 Monolith to Sub-Agents Your agent prototype is one big prompt in a loop. It works on your laptop and fails silently in production. Here is the five-step path out — applied in order, because each step exposes the failure the next one fixes. 10 Garbage-Collecting Entropy Codebases rot between commits — docs drift, deprecated patterns spread, conventions decay in corners no one watches. Scheduled agents catch that decay on a cadence and hand you one-minute PRs. 11 Define "Done" First Write the evaluation before the feature. A low pass rate on a new eval isn't a problem — it's the improvement surface made visible before a single line of code exists.

Capstone

12 The Workflow Decision Table Eleven lessons, one reflex: read the situation, reach for the move. This is the whole course as a lookup table — and a mixed review to prove it stuck.