IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
279 articles
18 Aug 2026 · 5 min read
agentic coding
Cursor's CVSS 9.8 RCE, AWS Kiro rewriting its own MCP config, a wiped Supabase production database, a private-repo leak via GitHub Agentic Workflows — August 2026's incident roundup, distilled into what to actually change in your team's agent permissions.
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 more17 Aug 2026 · 5 min read
ai
Stripe's reported $7B+ acquisition of OpenRouter — up from a $1.3B valuation three months ago — validates the model-gateway architecture. A Technical Lead's take on when to buy a gateway, when to build one, and what this deal signals for API-routing infrastructure.
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 more15 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 more15 Aug 2026 · 5 min read
agentic coding
Agent Plugins 1.0 packages skills and MCP servers into one installable plugin that works across Copilot, Claude, Cursor, and more. A technical lead's take on the packaging format, governance model, and where the 1.0 spec still has rough edges.
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 more13 Aug 2026 · 4 min read
ai
DeepSeek open-sourced an agent harness where the model, tools, memory, and even the loop itself are swappable plugins. A hands-on look at the pattern and how to apply it to your own agent stack.
Read more
