Run Local LLMs on Mac to Cut Claude Costs
A practical hybrid workflow that uses costly LLM APIs for planning and local models (via Ollama + OpenCode) for execution, guarded by deterministic evals.
Posts about developer tools
Browse 58 posts in this category
What the Warp Terminal Sends Home
We recorded Warp traffic to see what gets sent back to the home base. Spoiler: It's everything.
Beyond AI Vibes: Deterministic Foundations for Agentic Coding
AI coding adoption is high and trust is dropping. A testing pyramid for agents, plus reproducible production context that grounds AI in real behavior.
OpenTelemetry Trace Testing for CI Release Gates
Trace-based testing uses OpenTelemetry traces as replayable test input so CI catches production regressions before deploy, not after incident review.
Why You Should Stop Buying SaaS and Start Building It
LLMs have collapsed the cost of custom internal tools. Here's the startup distribution problem I've watched kill companies — and how I vibe-coded my way out.
Production Data Access for Developers: RBAC and DLP
RBAC and DLP let developers access production data safely—without configuration drift or PII exposure. Here's how to design it right.
FastAPI Testing: Mock LLM APIs for Free
Record real LLM traffic from a FastAPI app, mock it locally, and replay it in CI with proxymock.
The Hidden AI Bill: Why Non-Prod LLM Costs Spiral
Production AI spend gets attention. Non-prod LLM calls in development, CI, and load tests often do not. Simulation fixes that.
Prompt, Deploy, Pray Is Dead: Validating AI Code with Proxymock
AI-generated code is moving fast—but without behavioral validation, you're gambling with production stability. See how Proxymock changes the equation.