#agents
Posts tagged with agents.
Fresh context review is not bureaucracy
Verifier agents catch different failures when they are not soaked in the builder rationale.
Tool calling is a contract
Approval buttons need context
An approval step only helps if the human can see the plan, the data, and the rollback story.
Claude 4 and GPT-5 made agent work a maintenance problem
Agent observability needs user-level events
Handoffs are part of the agent
o1 and Gemini 2.0 pushed agents toward the default
MCP turned agent tools into an interface
Agents need boring boundaries
A practical note on agents, MCP tools, identity, permissions, and why clear limits matter.
Why I like small agent tools
Small tools are easier to permission, easier to review, and harder for an agent to misuse quietly.
Agent runbooks need failure examples
Runbooks for agents get better when they include the mistakes the agent is expected to make.