Operations
Operations
How to run agents in production — evals, observability, cost, safety, governance.
These ops essays assume Concepts fluency — new here? Start with Concepts →
Safety & Security
Prompt injection, sandboxing, exfiltration, red-teaming, deployment safety — the threat model an agent's environment creates.
11 essays
Evaluation & Observability
Measuring agents that don't have a single right answer — outcome vs trajectory evals, LLM-as-judge, traces, benchmarks.
7 essays
AgentOps: Deploy & Operate
Running agents in production: rollout, versioning, scaling, idempotent retries, cost control, incident response.
8 essays
Economics & ROI
The unit economics of agents — pricing, cost attribution, ROI measurement, build-vs-buy, failure modes.
7 essays
Governance & Compliance
Accountability, audit, policy enforcement and the regulatory landscape — making agent decisions defensible.
8 essays