Agent-Assisted Engineering
Frame, plan, execute, delegate, verify, review, and improve coding-agent work inside real repositories.
#LessonPhaseTimeRequirementOpen
01Agent Workbench Engineering: Why Capable Models Still FailA capable model is not enough. Reliable agents need a workbench: instructions, state, scope, feedback, verification, review, and handoff. Strip those away and even a frontier model produces work that is unsafe to ship.Phase 1445 minRequired↗ Official lesson02Frame the Task Before the Agent Writes CodeA coding agent can implement a clear task quickly. It can also implement an unclear task quickly. The speed is the same. The cost is not.Phase 1460 minRequired↗ Official lesson03Build an Evidence-Backed Execution PlanA plan is not a prettier to-do list. It is a dependency graph in which every change has a reason and every terminal node has proof.Phase 1465 minRequired↗ Official lesson04The Minimal Agent WorkbenchThe smallest useful workbench is three files: a root instructions router, a state file, and a task board. Everything else is layered on top. If a repo cannot carry these three, no model will save it.Phase 1445 minRequired↗ Official lesson05Agent Instructions as Executable ConstraintsInstructions written as prose are wishes. Instructions written as constraints are tests. The workbench turns each rule into something an agent can check at runtime and a reviewer can verify after the fact.Phase 1450 minRequired↗ Official lesson06Repo Memory and Durable StateChat history is volatile. The repo is durable. The workbench stores agent state in versioned files so the next session, the next agent, and the next reviewer all read from the same source of truth.Phase 1460 minRequired↗ Official lesson07Initialization Scripts for AgentsEvery session that starts cold pays a tax. The agent reads the same files, retries the same probes, and rediscovers the same paths. An init script pays the tax once and writes the answers into state.Phase 1445 minRequired↗ Official lesson08Scope Contracts and Task BoundariesThe model does not know where the work ends. A scope contract is a per-task file that says where the work begins, where it ends, and how to roll back if it spills. The contract turns "stay in scope" from a wish into a check.Phase 1450 minRequired↗ Official lesson09Runtime Feedback LoopsAgents that do not see real command output guess. A feedback runner captures stdout, stderr, exit code, and timing into a structured record the next turn can read. Then the agent reacts to facts instead of to its own prediction of facts.Phase 1450 minRequired↗ Official lesson10Verification GatesThe agent does not get to mark its own work as done. A verification gate reads the scope contract, the feedback log, the rule report, and the diff, and answers a single question: is this task actually complete? If the gate says no, the task is not done, no matter what the chat says.Phase 1455 minRequired↗ Official lesson11Reviewer Agent: Separate Builder from MarkerThe agent that wrote the code cannot grade it. A reviewer is a second loop with a different system prompt, a different goal, and read-only access to everything the builder produced. The gap between builder and reviewer is where most reliability lives.Phase 1455 minRequired↗ Official lesson12Delegate Agent Work with Isolation and Merge ContractsParallel agents save wall time only when the work is independent. Otherwise they convert one clear task into a coordination problem with a faster failure rate.Phase 1470 minRequired↗ Official lesson13Multi-Session HandoffThe session is going to end. The work is not. The handoff packet is the artifact that turns "the agent worked for an hour" into "the next session is productive in the first minute." Build it on purpose, not as an afterthought.Phase 1450 minRequired↗ Official lesson14The Workbench on a Real RepoEleven 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.Phase 1460 minRequired↗ Official lesson15Turn Every Agent Correction into a System ImprovementA correction that lives only in chat fixes one run. A correction promoted into a test, boundary, example, or tool improves every later run.Phase 1465 minRequired↗ Official lesson16Capstone: Ship a Reusable Agent Workbench PackThe mini-track ends with a pack you drop into any repo. Eleven lessons of surfaces compressed into a directory you can `cp -r` and have an agent working reliably the next morning. The capstone is the artifact this curriculum trades on.Phase 1475 minRequired↗ Official lesson