Writing on agents in production.
What we've learned from shipping. No takes on whether agents are real.
Why your eval suite belongs in CI.
If your evals don't run on every PR, they're not evals — they're a screenshot from a meeting in March.
Posts
Latest writing — filter by tag, search titles locally, load older pages.
Why your eval suite belongs in CI.
If your evals don't run on every PR, they're not evals — they're a screenshot from a meeting in March.
Durable workflows are not retries.
A reasonable mental model for when you actually need a durable orchestrator vs. just better backoff.
A2A and MCP: pick both.
They solve adjacent problems. The mistake is treating them as a fork in the road.
How to build a retrieval eval set in a week.
A practical recipe. 200 questions, your real corpus, baselines, and a "do not optimize this" set.
Notes & reports
Process and industry field notes — real posts tagged process / industry.
A2A and MCP: pick both.
They solve adjacent problems. The mistake is treating them as a fork in the road.
The runbook that ships with every agent.
Failure modes, escalations, rollback conditions. Boring on purpose.
Why we run on-call for 60 days after handoff.
Because the first 60 days surface every assumption the eval suite missed.
Favorites
Saved posts for your account — not available anonymously.
Checking identity…
Ship the first system.
Fixed-price discovery in 2 weeks. You leave with an architecture, a working spike, and a build plan.