CATEGORY
Engineering
Browse every post in engineering and discover related writing across the blog.
4 posts in this category
11 min read
Agent tools that scale: a practical checklist
A field guide to shipping dependable tool calling in production, from scoping and observability to rollback paths and user trust.
10 min read
Observability for agents: what to log (and what not to)
A practical logging model for tracing agent behavior end to end without turning your observability stack into a liability.
11 min read
How to evaluate an agent: metrics that actually predict success
A practical framework for measuring agent quality with metrics that correlate to user outcomes, workflow reliability, and operational cost.
10 min read
From prototype to production: hardening your first agent workflow
A practical path from a promising demo to a dependable workflow, with better validation, timeouts, state handling, and user-visible recovery.