Designing an agent harness: loop, tools, context, permissions
How to design the software around an AI model: the agent loop and its stop conditions, tool results, context assembly, permissions, sandboxing and tests.What an AI agent really costs to build and run
A breakdown of AI agent costs: build phases, tokens per task, tools, human review and maintenance, with a worked example you can redo at current prices.AI memory and privacy: what to store, what to forget
Memory makes an assistant a store of personal data. How to handle consent, minimisation, retention, erasure, isolation, poisoning and audit under GDPR.Multi-agent systems: when one agent is not enough
How orchestrator-worker, pipeline, handoff and fan-out designs work, what they cost in tokens, latency and debugging, and when several agents beat one.AI agents in production: what it takes beyond the demo
What separates an agent demo from a production system: scope, tool design, state, retries, approvals, evals, tracing, cost ceilings and a staged rollout.How to evaluate AI agents before you trust them with real work
A practical method for testing AI agents: build a task set from real cases, choose graders, run regression suites in CI and monitor quality after launch.Types of AI memory: working, episodic, semantic, procedural
The four memory types borrowed from cognitive science and how each maps to engineering: what it stores, how it is written and read, and how it fails.