IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
16 articles
04 Sep 2026 · 5 min read
agentic coding
OpenCode, the open-source terminal coding agent, grew past 170,000 GitHub stars by staying model-agnostic and monetizing through Zen, a zero-markup inference gateway. A Tech Lead's breakdown of the bring-your-own-model economics and when it actually beats a single-vendor coding agent subscription.
Read more01 Sep 2026 · 5 min read
ai-agents
Claude Sonnet 5's introductory pricing and GitHub Copilot Studio's promotional credits both expired on the same day. Here's the real math on what changed, why it happened simultaneously, and how to budget for the next one.
Read more30 Aug 2026 · 4 min read
ai-tools
GitHub's August 28 Visual Studio update adds Low/Medium/High thinking-effort controls per model, plus a model management view with context window and cost info. A Tech Lead's take on why per-call effort tuning matters more than picking 'the best model' — and how it compares to the reasoning-effort trap we already learned the hard way with open models.
Read more25 Aug 2026 · 5 min read
ai
GLM-5.3 just jumped from 4.6 to 28.3 on Terminal-Bench 3.0 at a fraction of frontier pricing. Here's the routing architecture we actually shipped to stop overpaying for tasks that don't need it.
Read more17 Aug 2026 · 4 min read
agentic coding
Qwen3.8-27B ships with reasoning effort defaulted to xhigh, and it shows: a trivial SVG request burns 22,000+ reasoning tokens and 21 minutes. A Technical Lead's guide to reasoning-effort as a hidden cost knob in agent pipelines.
Read more17 Aug 2026 · 4 min read
ai
DeepSeek-V4-Pro-0813 went GA with sharp benchmark gains over its preview — and API prices up to 12x higher. A Technical Lead's read on what this means for anyone who built a cost model around DeepSeek's 'race to zero' pricing.
Read more16 Jul 2026 · 7 min read
ai
GPT-5.6, Claude Sonnet 5, and Grok 4.5 all launched within 10 days of each other in July 2026. No single model wins every workload. Here's how to build a routing layer that cuts your AI bill by 40-80% without sacrificing quality.
Read more08 Jun 2026 · 5 min read
ai
GitHub switched Copilot from unlimited requests to token-based AI Credits on June 1, 2026. As a tech lead managing a team of 8, here's what changed, what it costs, and how to not get a surprise bill.
Read more26 May 2026 · 10 min read
agentic coding
Microsoft cancelled thousands of Claude Code licenses. Uber burned its entire 2026 AI budget in four months. The technical reason why - and what every engineering team should do about it.
Read more
