Anthropic says Claude now writes 80% of its code, guarded by human approval gates
rseroter · x · 2026-07-23
Anthropic’s CISO team outlines how the company keeps an AI-native SDLC moving fast while AI writes roughly 80% of the code.
- The diagram shows a closed loop across requirements, planning, coding, testing, deployment, monitoring, and governance.
- Human approval gates and cross-cutting governance are used at critical junctures.
- The post frames the system as an AI-powered cycle that extends from ideation through monitoring, rather than a one-way coding assistant workflow.
More from coding & agent
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11