/blog · playbook notes

Notes from the workshop floor.

Slow, careful posts on what we've learned shipping AI-native apps.

5 min

Shipping AI-Native Apps on a Two-Week Cycle

How we structure a KiteLabs build: week one is a vertical slice, week two is the eval flywheel.

May 30, 2026Read

7 min

Evals That Actually Catch Regressions

Why golden datasets, LLM-as-judge, and production traces are three different evals — and you need all three.

May 30, 2026Read

6 min

RAG Is Not a Vector Database

Retrieval quality lives in chunking, query rewriting, and rerankers — not in which vector store you picked.

May 30, 2026Read

8 min

Designing Planner–Executor Agents That Don't Drift

A pragmatic recipe for splitting reasoning from action so your agents stay on the rails in production.

May 30, 2026Read

4 min

The Agentic Infrastructure Shift: How CodeGraph, RMUX, and Gemini 3.1 Flash-Lite Are Re-Engineering Developer Toolchains

The software development lifecycle is undergoing a structural realignment. As autonomous AI agents move from experimental chat interfaces to production environments, developer toolchains are being rebuilt from the ground up. This shift focuses on overcoming the primary bottlenecks of agentic workflows: high latency, token consumption costs, state persistence, and programmatic media generation.

May 23, 2026Read

4 min

Beyond the Chatbox: The Rise of Sandboxed Execution, Stateless Protocols, and Local AI Pipelines

The developer ecosystem is undergoing a profound paradigm shift. We are moving rapidly past basic chat interfaces and traditional autocomplete extensions toward highly integrated, sandboxed desktop environments, persistent workspace context, and cost-effective local execution pipelines.

May 22, 2026Read

/newsletter · low-volume

New posts, straight to you.

One email when something new ships. No spam, unsubscribe anytime.