Field guides
Practical, source-backed guidance for Coding with Agents.
What Is AI Slop? When Generated Output Only Looks Finished
AI slop looks finished even though something important is missing: a clear purpose, evidence that it works, or someone who owns the result.
Brief the Agent Like a Capable Co-Worker
A practical assignment model for giving coding agents purpose, context, acceptance criteria, authority boundaries, and human ownership.
Your Repo Is the Memory: Durable Context for AI Coding Agents
How to decide which coding-agent context belongs in chat, AGENTS.md, skills, work items, docs, tests, and saved results.
Agentic Coding in 2026: A Practical Map
A 2026 map of coding-agent work: brief the task, preserve context, verify behavior, keep consequential decisions human, and scale only what works.
Make the Agent Prove It
A practical acceptance framework for agent-written code: the harder a failure is to undo, the stronger the evidence required.
Right-Sized Threads, Durable State
How to keep connected agent work in one thread, split only when separation helps, and carry accepted state across the boundary.
Using Amp for Real Coding Work
How to brief, place, delegate, and verify a coding task with Amp.