IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
35 articles
15 Aug 2026 · 5 min read
agentic coding
DoorDash's Flux platform runs 130,000 agent tasks a month with 25,000+ automated code reviews a week, all inside Firecracker microVM sandboxes. A technical lead's breakdown of the architecture pattern behind it.
Read more14 Aug 2026 · 5 min read
agentic coding
Google's new Flash model jumped from 34.4% to 43.6% on FrontierCode 1.1 at half the price of its predecessor. A technical lead's take on when to route agentic coding work to the fast, cheap tier — and when not to.
Read more14 Aug 2026 · 4 min read
agentic coding
Opus 5 shipped a five-level effort parameter, and Claude Code now lets every subagent set its own model and effort in frontmatter. A practical guide to mapping your agent fleet to a cost curve instead of a flat rate.
Read more11 Aug 2026 · 5 min read
agentic coding
Thoughtworks ran a controlled experiment on TDD inside an AI agent loop: red-green cycles cost up to 8.5x more tokens than spec-first prompting, and blind quality judging preferred the non-TDD output. Here's what that means for how you should actually prompt coding agents.
Read more05 Aug 2026 · 7 min read
agentic coding
Alibaba's Qwen3.8-Max ran autonomously for 16 days, producing 265 commits, 127 PRs, and 151 issues on a public GitHub repo. The tech lead question isn't whether AI can do this — it's whether you can trust it, verify it, and build a team process around it.
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 more04 May 2026 · 12 min read
agentic coding
From vibe coding to software craftsmanship. 84% of developers use AI tools, but only 29% trust the output. Here is the maturity model that separates the amateurs from the engineers.
Read more17 Mar 2026 · 14 min read
agentic coding
How Spec-Driven Development (SDD) transforms agentic AI from a vibe-coding toy into a production-ready engineering discipline. Real project experiences, frameworks, tooling, and hard lessons from leading teams with Claude Code, Kiro, and BMAD.
Read more
