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.”
More from coding & agent
- High-school builder open-sources Hearth, a local AI that runs your PC and keeps 9B agents usable — T-90_Soviet · 2026-07-24
- Real-time Codex agents across calendar, Slack and shopping feel like an AGI moment — khademinori · 2026-07-24
- Muse Spark 1.1 scores 90.2% on Online-Mind2Web, edging past Claude Opus 4.8 — DhruvBatra_ · 2026-07-24
- One harness trained on a small model lifts Terminal-Bench scores across four models — Megadragon9 · 2026-07-24
- open-deepthink 0.1.11 adds qualitative self-attention and portable agent skills — causality-ai · 2026-07-24
- Automated AI Workflow Tracks Clothing Brand Restocks, Generates Ads & Sends Postcards — eptwts · 2026-07-24