Production AI Agents
15 articles in this topic.
An Agent Is a System, Not a Prompt
The useful mental model for agentic software starts with an execution loop, not a clever system message.
Tools: Where Reasoning Meets the Real World
Tool design is not plumbing. It is one of the most important safety and product-design surfaces in an agent system.
MCP: A Shared Capability Layer for Agents
Model Context Protocol is most useful when capabilities need to be reusable across agents, clients, and frameworks.
Context Engineering: Give the Model Less, but Better
The best context window is not the biggest one. It is the smallest trustworthy working set needed for the next decision.
RAG vs Live Tools: Knowledge Is Not State
Use retrieval for unstructured knowledge and live tools for current authoritative state—and know when the same source needs both.
Deterministic vs Probabilistic Orchestration
The most important architecture decision in an agent system is deciding which parts should not be agentic at all.
Reliability: Idempotency, Retries, and Partial Failure
Agentic systems inherit every distributed-systems failure mode—plus a probabilistic decision-maker on top.
Security: Identity, ACLs, Prompt Injection, and Blast Radius
The model is not a trusted principal. Design as though untrusted content can influence it—and make that influence powerless.
Human Confirmation Without Confirmation Fatigue
User approval is useful, but it is not authorization—and asking “Are you sure?” before everything is not a product strategy.
Scaling Agent Systems: Backpressure, Quotas, and Workload Isolation
Ten thousand users is not a capacity number. Peak concurrency, latency SLOs, downstream limits, and workload mix are.
Tool Sprawl, Routers, and Specialist Agents
When an agent has forty tools, the answer is rarely “write a better prompt and hope.” Reduce the effective action space.
Evals: The Test Harness Around a Stochastic Application
A production agent needs more than unit tests. It needs a repeatable way to measure outcomes, trajectories, safety, cost, and regressions.
Ablation, Variance, and Adaptive Sampling
Agent evaluation becomes much clearer once you borrow a small amount of statistical vocabulary—without turning product development into a statistics thesis.
Production Observability: From Traces to Better Agents
The first month after launch should produce more than dashboards. It should produce a better eval suite and a sharper failure taxonomy.
The Production Agent Vocabulary Sheet
A compact glossary for architecture discussions, design reviews, and building shared language across teams.
New posts, straight from Chris
A short note from me whenever a new article goes live — product engineering, AI workflows, IoT, indie apps, and engineering leadership. No spam, unsubscribe anytime.
By subscribing, you agree to our Privacy Policy. We do not share your email.