AI coding agents.
4 posts · Read or watch
Start with the working set: what an agent can see and how it finds the right files. Then follow the tools and permissions that decide what it can actually do. These walkthroughs connect the moving parts to day-to-day engineering work.
Start here, then go deeper
3 min readVideo
How Codex Actually Finds the Right Files
AGENTS.md, skills, MCP, search, and compaction — the layers Codex uses to narrow a big repo down to a working set.
Watch on YouTube8 min readVideo
How MCP Actually Works: The Capability Bus Behind Codex, Claude Code, and Gemini CLI
MCP, demystified. Why it's a capability bus, not a plugin store, and what that changes about how agents reach external tools.
Watch on YouTube2 min readVideo
How Repo Rules, MCP, and Approvals Control AI Coding Agents
The three control surfaces that decide what an agent can read, run, and change inside your repo.
Watch on YouTube8 min readVideo
Why AI Coding Agents Ship Unreviewed Work
A review approves artifact A, a retry drops artifact B at the same path, and the saved approval still passes because it was never bound to the bytes. A read-only verifier recomputes the digest at the action boundary and refuses the replacement.
Watch on YouTube
Pick a thread
AI coding agents
Understand how agents find context, call tools, and work within the boundaries of a real repository.
4 handpicked posts02Local AI
Models, memory, and practical tradeoffs when the hardware running your AI is your own.
4 handpicked posts03Data & backend systems
Trace pipelines, inspect their data, and move slow work out of the request path.
3 handpicked posts