Stanford lecture breaks down always-on agent architecture: workflows, VMs, subagents
stanfordnlp · x · 2026-10-13
In Stanford CS146S, leerob explains key architectural decisions behind always-on proactive agents like Grokbot: durable resumable workflows with Temporal instead of job queues, giving agents a full Linux VM with skills/memories as markdown files, steering rather than approving (a separate review model checks commands), and one main agent delegating to fresh-context subagents. Covers the harness and context engineering with timestamped lecture video.
Related event: Vercel's Lee Rob Explains Persistent Agent Architecture at Stanford(2 posts)→
More from coding & agent
- Intent Launches: Manage Swarms of Coding Agents From Your Phone — Wattenberger · 2026-10-13
- Give agents a next step: embed fix steps and doc links in API error responses — SucceededMind · 2026-10-13
- Temporal agent falls for prompt injection but scoped authority blocks the .env read before it runs — daniel_tenuo · 2026-10-13
- Simple config.toml tweak reportedly lifts 272k coding context cap to 872k — JayJeds · 2026-10-13
- EpochGo: local-first multi-agent AutoML on Ollama, $0 API costs and 100% offline — Grouchy-Excitement28 · 2026-10-13
- Ramp CTO to Discuss Internal Coding Agent Behind ~75% of Merged PRs — graceisford · 2026-10-13