Field Notes
Practical notes on AI agent deployment.
Short essays on where agents fit, how teams should sequence implementation, and which technical choices actually change the operating model.
MCP Tool Catalogs for Agent Pilot Readiness
Before connecting an agent to MCP servers, build a tool catalog that names each capability, owner, schema, approval class, and retirement path.
Agent Release Gates for Production Workflows
A practical release-gate model for promoting AI agents from shadow runs into real workflow authority without hiding operational risk.
Agent Handoff Manifests for Operational Workflows
A practical pattern for making agent-to-human and agent-to-agent handoffs inspectable before the next workflow owner takes action.
Agent Memory Policies for Operational Workflows
A practical way to decide what an AI agent should remember, forget, redact, and route for review before memory becomes production risk.
Golden Traces for Operational Agent Regression
A golden trace is a labeled production run that becomes a regression fixture. Use it to catch workflow failures after prompt, tool, or model changes.
Security Questionnaire Response Agents for Trust Reviews
A practical playbook for using agents to prepare security questionnaire responses while keeping evidence, approvals, and customer commitments under human control.
Agent Observability Runbooks for Production Workflows
Agent observability is useful when traces, logs, approvals, and business outcomes are organized into runbooks operators can use after a workflow fails.
Approval Packets for Human-in-the-Loop Agents
Human-in-the-loop agent approvals only work when the reviewer gets a compact packet that explains the action, evidence, risk, and fallback before anything changes.
Agent Evaluation Scorecards Before Production Rollout
A practical agent evaluation scorecard gives operators a production gate based on evidence quality, tool behavior, review load, and rollback readiness.
Tool Permission Inventory Before Agent Launch
Before an AI agent can move work across real systems, the team needs a tool-permission inventory that names what it can read, draft, route, change, and never touch.