Claude Code's Long-Running Workflows
trq212 · x · 2026-07-20
This is a podcast/interview snippet about Claude Code, focusing on how they design and use coding agents.
Key topics include:
- The differences between /loop, /goal, and workflows: they all let agents run for extended periods but serve different purposes
- Live demo: using Claude to edit and publish a video
- Using HTML artifacts for planning and learning
Overall, it discusses integrating agents into real-world development workflows rather than just talking about raw model capabilities.
Related event: Claude Code Team Shares Long-Running Agent Workflows(5 posts)→
More from coding & agent
- Goal-driven AI needs verifiable success signals, or it invents its own — daniel_mac8 · 2026-09-11
- Frontier models need ways to verify success — or they'll invent their own — daniel_mac8 · 2026-09-11
- Sakana AI launches Fugu Max: dynamic multi-agent routing across its largest open-model pool — graceisford · 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