blog
Notes
Field notes on cloud infrastructure, AI agents, and the boring engineering that decides whether a system runs for a quarter or 5 years.
- 01
The 90/10 software rule small businesses can use
For decades only big companies could afford to build their differentiated software. AI collapsed the cost of that slice to where one developer can deliver it — which is exactly what a small business can now afford.
tags: ai-agents · llm-engineering · build-vs-buy · small-business · cost
- 02
What one AI email actually costs
Most AI ROI talk is hand-waving. Here is a traced, per-email cost from a production agent — and the risk/reward math a CFO can check.
tags: ai-agents · llm-engineering · roi · cost · observability · pydantic-ai
- 03
Troubleshooting application failures with Logfire
A repeatable workflow for using Logfire span trees, SQL-over-traces, and OpenTelemetry semantic conventions to turn opaque application failures into one-line diagnoses — walked through a real production bug.
tags: logfire · opentelemetry · observability · debugging · pydantic-ai
- 04
Smoke-testing an LLM agent with a Claude Code skill
A Claude Code skill that smoke-tests an LLM agent end-to-end — real Gmail, real Drive, real model. Verifies that the agent does the right thing on real inputs, which ruff and pytest cannot.
tags: testing · claude-code · ai-coding · smoke-test
- 05
Code consistency is the casualty of agent velocity
spec-driven-dev keeps a single Claude Code agent coherent with itself across a long session — one SPEC.md it re-reads every turn, telegraph-encoded to a 41% token cut versus prose.
tags: spec-driven-development · claude-code · ai-coding · benchmarks