Anthropic engineer says teams are moving from prompts to graph-orchestrated self-improving agents
colinmcnamara · x · 2026-07-24
A repost of an Anthropic engineer’s talk claims many engineers are already using self-improving loops, and that the next step is building agentic graphs to orchestrate those loops.
The post frames this as a practical shift away from prompt-only workflows: instead of just prompting models, builders will increasingly design graph-based systems that coordinate iterative, self-improving agents. It also promotes a short talk plus a companion article on becoming a “graph architect.”
Related event: Evolution of AI Agent Architecture: From Loops to Graph Engineering(8 posts)→
More from coding & agent
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11