Coding with Agents
Build better software with coding agents.
Scope a task, brief a coding agent, coordinate the work, and check the result.
Selected field guides
Start with the core workflow.
-
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.
Read guide → -
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.
Read guide → -
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.
Read guide → -
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.
Read guide →
Resource catalog
115 reviewed resources, available now
Browse the Coding with Agents catalog by collection or topic, search the full library, and open source-backed editorial summaries.
Browse reviewed resources →Make AI coding work survive the next thread.
Keep simple work conversational. When continuity matters, dot-agents stores work items, plans, and verification in plain repo-local files so the next thread can continue.
Explore dot-agents.dev (opens in a new tab)