Learning Path
s01 to s20: Progressive Agent Harness Design
Layer Legend
The Agent LoopOne Loop Is All You Need
“The smallest useful agent is a loop that calls the model, runs tools, and feeds results back.”
Learn MoreTool UseAdd a Tool, Add Just One Line
“The loop stays stable while capabilities register into a dispatch table.”
Learn MorePermissionCheck Permissions Before Execution
“Dangerous actions need a harness decision point before the shell runs.”
Learn MoreHooksHang on the Loop, Don't Write into It
“Cross-cutting behavior belongs around the loop, not tangled inside it.”
Learn MoreTodoWriteAn Agent Without a Plan Drifts Off Course
“Explicit plans keep long-running work visible and correctable.”
Learn MoreSubagentBreak Large Tasks into Small Ones with Clean Context
“Subagents give each subtask a clean message history while preserving the main thread.”
Learn MoreSkill LoadingLoad Only When Needed
“Inject specialized knowledge only when the task actually needs it.”
Learn MoreContext CompactContext Will Fill Up
“Compression keeps the conversation usable when the context window gets crowded.”
Learn MoreMemoryKeep a Layer That Doesn't Lose Details
“Some facts should survive summarization and future sessions.”
Learn MoreSystem PromptAssembled at Runtime, Never Hardcoded
“The system prompt is a generated product of policy, tools, skills, and context.”
Learn MoreError RecoveryErrors Are the Start of a Retry
“A robust harness classifies failures and decides what kind of retry is worthwhile.”
Learn MoreTask SystemBreak Big Goals into Small Tasks
“A task graph turns vague goals into ordered, observable work.”
Learn MoreBackground TasksSlow Operations Go to the Background
“The agent can keep reasoning while slow work completes elsewhere.”
Learn MoreCron SchedulerProducing Work on a Schedule
“Recurring work should be created by the harness, not remembered by the model.”
Learn MoreAgent TeamsOne Agent Isn't Enough, Form a Team
“Persistent teammates let work continue in parallel without stuffing every thought into one context.”
Learn MoreTeam ProtocolsTeammates Need Agreements
“Multi-agent systems need explicit message contracts, not vibes.”
Learn MoreAutonomous AgentsCheck the Board, Claim the Task
“Teammates become useful when they can discover and claim work themselves.”
Learn MoreWorktree IsolationSeparate Directories, No Conflicts
“Parallel agents need isolated filesystems as much as isolated conversations.”
Learn MoreMCP ToolsExternal Tools, Standard Protocol
“External services can become agent tools through a standard discovery and call protocol.”
Learn MoreComprehensive AgentAll Mechanisms, One Loop
“The final harness is still one loop, now surrounded by the systems that make it production-shaped.”
Learn MoreCLAUDE.mdPut Your Work Rules in Writing
“AI doesn't disobey — it guesses when you leave blanks. A written manual removes the guessing.”
Learn MoreVerificationDon't Trust 'Done' — Verify It
“Fluent text is not the same as correct output. Define 'done' before the task starts.”
Learn MoreMemoryNew Chat, Same Context
“Memory lives in your files, not in AI's head. A three-part handoff note bridges any conversation gap.”
Learn MoreHooksWhen Rules Aren't Enough, Install a Gate
“CLAUDE.md is a guide. A hook is a guard. If 5% failure is unacceptable, enforce it.”
Learn MoreLayered GovernanceToo Many Rules? Sort Them into Drawers
“AI ignores the second half of a 200-line rule file. Split into global / task / personal layers.”
Learn MoreIntegrationAssemble a System That Actually Works at the Office
“Start with a minimum viable harness — manual, checklist, handoff note — and add pieces only when needed.”
Learn More