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.
Agent Incident Rollback for System-of-Record Repairs
Agent rollback is a compensating repair in the system of record. Replaying a checkpoint does not unpost overtime, unsend a notice, or restore a closed period.
Agent Cost and Latency SLOs for Production Queues
An agent SLO should bind cycle time and cost per completed case to a named queue. Token charts without an error budget do not tell operators when to shed load.
Third-Party AI Vendor Risk Reviews
An inbound AI vendor review should produce a use-case packet covering models, data flow, subprocessors, and change notice. A recycled SOC 2 questionnaire is not enough.
Citation Freshness for Retrieval-Backed Agents
A retrieval-backed agent should cite a current controlled source or stop. Filename annotations are not enough when the work instruction has a revision stamp.
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.