Production and ops — AI agent development

Everything after the demo works: evaluation sets, tracing and monitoring, prompt injection and guardrails, latency and token cost control, and scaling agents to real traffic.

5 guides

Scaling AI Agents: Latency, Concurrency and Rate Limits

Agents scale differently from web services: the bottleneck is a rate limit and a multi-second call, not your CPU. Queue the slow work, stream the fast part, degrade on purpose.

Production and ops 8 min read

AI Agent Security: Guardrails, Permissions and Prompt Injection

An agent is a user of your systems that can be argued with. Give it least privilege, treat all fetched content as untrusted, and put a human in front of anything you cannot undo.

Production and ops 10 min read

Monitoring AI Agents in Production: What to Log and What to Alert On

Uptime tells you nothing about an agent. Trace every run, watch six behavioural metrics, and alert on drift in behaviour rather than on errors alone.

Production and ops 9 min read

Cutting AI Agent Costs Without Making It Worse

Most agent bills are context, not intelligence. Measure per run, route cheap steps down a tier, cache the stable prefix, and stop carrying documents you already used.

Production and ops 8 min read

Testing AI Agents: Building an Evaluation Set That Earns Its Keep

Fifty real cases beat any benchmark. Grade outcomes rather than transcripts, keep the failures you have already fixed, and run the set before every change.

Production and ops 9 min read

Scope a build