Long-Running Agent Workflows in Claude Code
petergyang · x · 2026-07-19
This episode features Thariq from the Claude Code team, focusing on how he uses /loop, /goal, and workflows to keep agents running for extended periods. The discussion covers the differences between these modes, a live demo of editing and publishing a video using Claude, and leveraging HTML artifacts for planning and learning.
Key takeaways include the fact that system prompts have been slashed by 80% because smarter models require fewer constraints, and that planning is inherently an iterative process of exploration, investigation, and discovering the unknown. Additionally, a common failure mode is users hastily skimming the AI's plan, whereas plans actually require careful reading.
Related event: Claude Code Team Shares Long-Running Agent Workflows(5 posts)→
More from coding & agent
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Prompt turns Claude Code into a forensics tool finding deleted iPhone photos in backups — alex_verem · 2026-10-27
- Phones won't be mobile IDEs but control planes for agent fleets, argues Yuchen Jin — Yuchenj_UW · 2026-10-27
- FrontierCS 2 launches on Kaggle: 48 tasks make agents beat published CS papers — MeganRisdal · 2026-10-27