Instruments
Reading the gauges — before you trust an agent, you need instruments that show you when it's lying.
A short issue, all signal, and a turn in the run: from building to instrumenting. Two AI Engineering Summit reports find the models got smart and the tools got simple — the circle of who builds is expanding. "AI tools fail loudly where humans failed quietly" notices that messy codebases finally show up on the meter, and "You're absolutely right" names the context-window dumb zone: sycophancy as a gauge reading. The middle question of the whole run surfaces here — the demos all work, so how do you know? Instruments precede proofs.
The Quarterly Retrospective
A short issue, all signal. Two summit reports read the same gauges from different seats and agreed: the models got smart, the tools got simple, and the circle of who gets to build is widening — the industry got bash-pilled.
The other two needles mattered just as much. Messy codebases finally have a visible cost — AI tools fail loudly where humans failed quietly — and sycophancy became an instrument reading: when your assistant starts agreeing with everything, check the context window, because you're in the dumb zone.
AI Engineering Code Summit 2025: Deep Dive Report
A comprehensive analysis of the state of AI engineering tools, frameworks, and best practices from the November 2025 Code Summit. Exploring cutting-edge developments in AI-assisted development, infrastructure, and production deployment strategies.
"You're absolutely right" and other AI warning signs
When your AI assistant starts agreeing with everything, you've hit the dumb zone. Practical techniques for managing context windows and keeping AI useful.
Build Your Own Coding Agent
A step-by-step tutorial for building an AI coding assistant from scratch. Bootstrap it with an existing agent, then use it to improve itself.
The Smallest Coding Agent
A complete agentic coding loop in 25 lines of Bun. No frameworks, no dependencies, just bash and a model.
AI Engineering Summit 2025: Bash-Pilled and Building for Everyone
The models got smart. The tools got simple. The circle of who builds is expanding.
AI tools fail loudly where humans failed quietly
AI coding tools don't work well in messy codebases. The fix is doing what should have been done all along - and that's good for everyone.
AI Engineering Code Summit 2025
Summit report — talks, sessions, and takeaways from Miami.