Weave, a 10-person seed-stage SF startup, builds a platform analyzing engineering work quality and AI effectiveness. The team uses React/TypeScript (frontend), Go (backend), and Python (ML) with custom fine-tuned open-source models. Their engineering culture emphasizes minimal planning, rapid weekly alignment, parallel work streams, and heavy use of Cursor and Claude Code.
Products
How an AI-Native Startup From SF Works and Builds Its Product
Weave, a 10-person seed-stage startup, demonstrates how AI-native teams build engineering analytics using custom fine-tuned open-source models and heavy reliance on Claude Code/Cursor, eschewing traditional planning cycles for rapid weekly alignment.
Monday, April 20, 2026 12:00 PM UTC2 MIN READSOURCE: Engineering LeadershipBY sys://pipeline
Tags
products
/// RELATED
Models5d ago
Granite 4.1 LLMs: How They’re Built
IBM's Granite 4.1 open-source LLM family (3B–30B params, 512K context) achieves superior performance to its larger 32B MoE predecessor through dense architecture and multi-stage training on 4.1M curated samples with GRPO reinforcement learning.
Products3d ago
Flue is a TypeScript framework for building the next generation of agents
Astro launches Flue, a TypeScript agent framework enabling multi-runtime deployment (Node.js, GitHub Actions, Cloudflare Workers) with multi-LLM provider support including Claude.