Deep dive · · 6 min read
Every question your AI readiness review asks was answered months ago
The last six days of a sixty-day series, and the pattern is that operability gets bought early or it does not get bought at all.
Topic
Architecture
12 entries and 3 references.
In the glossary: Event-driven architecture, what each means and how to say it in a review
Entries
Architecture pattern · · 1 min read
Pattern: the outbox for agent actions
Agents that write to systems of record need the same transactional outbox that event-driven services use. This entry covers the shape and the trade-offs.
Architecture pattern · · 1 min read
Designing a Multi-Agent System for Real-World Use
How to design and run a multi-agent system in production, using the supervisor pattern, with its trade-offs and where human approval belongs.
Article · · 2 min read
The architecture review that happens before launch, not after the incident
Quality, safety, cost, latency, resilience and operations have to be visible on one diagram, at the same time.
Explainer · · 2 min read
You are already building a control plane, badly
Policy, memory, evals and rollout get rebuilt inside every feature until someone names the layer they belong to.
Comparison · · 2 min read
Most agents are workflows wearing a costume
Chatbot, workflow, agent, RAG. Pick the wrong one and you spend a quarter debugging autonomy nobody asked for.
Explainer · · 2 min read
Every model call should go through something you own
Routing, budgets, fallbacks and policy need one place to live. Scattered SDK calls give you none of them.
Deep dive · · 5 min read
Your AI system's biggest problem is probably not the model
Six days of production AI notes, and the model choice never once turned out to be the thing that broke.
Article · · 2 min read
From model demos to mission-ready AI systems
A practical map for moving from impressive AI demos to systems people can trust.
Article · · 1 min read
Why production AI is coordinated infrastructure
Why production AI is the coordination of data, models, tools, controls, evaluation, and people.
Comparison · · 2 min read
When to use a chatbot, workflow, or agent
A practical way to choose between conversation, repeatable workflows, and bounded autonomy.
Explainer · · 2 min read
Why model choice is rarely the first production AI problem
Why production AI succeeds or fails in the system around the model, not in the model choice alone.
References
- Read
Designing Data-Intensive Applications
O'Reilly · Recommended · The book behind most good decisions about storage, replication and consistency.
- Read
The System Design Primer
GitHub · Getting started · The best free grounding in the distributed systems ideas every AI application eventually needs.
- Read
Building Effective Agents
Anthropic · Recommended · The clearest written case for simple, composable agent patterns over frameworks.