Diff your context, not your prompts
I kept saying we should diff contexts instead of prompts, then realized no tool actually did it. So I built one: ctxdiff, a git diff for your agent's context window.
#agents
6 posts
Context engineering is the job now
Prompt wording is a rounding error next to what the model can see and when. The discipline that replaced prompt engineering, and how we practice it.
Prompt injection is an agent problem now
A chatbot that gets injected says something embarrassing. An agent that gets injected does something. Defense notes from systems with tools.
MCP quietly fixed the worst part of building agents
Before the Model Context Protocol, every agent-to-tool integration was a bespoke adapter. Notes from moving production systems onto MCP.
Human-in-the-loop is not a checkbox
Approval gates that people rubber-stamp are worse than no gates at all. Designing HITL that survives contact with busy humans.
Most 'AI agents' are just workflows (and that's fine)
The industry keeps calling everything an agent. Most production systems I've shipped are workflows with LLM steps — and that's usually the right call.