Sentry cofounder David Cramer on the hardest part of running many parallel agents
zeeg · x · 2026-11-04
Sentry cofounder David Cramer (posting as zeeg) says his biggest challenge with agents is not LLM context but human context: too many tasks, too much ambition, dozens of threads in various states.
- His answer so far: consolidate decisions — let agents do as much as safely possible, then make it trivially easy to see what needs human attention
- He adopted Greg Chadev's "Review Desk" (renamed Inbox) pattern, now live in his product Junior, with a screenshot showing a triaged inbox item
- Still imperfect: models struggle to keep items concise/summarized, and peeling one onion layer reveals another similar problem
He's asking the community how they handle multi-task agent UX.
More from coding & agent
- Free no-sign-in MCP server compiles LaTeX (pdflatex/xelatex) and explains errors in plain words — PurplelinkPL · 2026-11-04
- Multi-agent review pipeline: Claude coordinates, Grok reviews, Codex fixes — PawelHuryn · 2026-11-04
- WoW x League of Legends Arena mashup: roguelike 2v2v2v2 PvP with per-round drafts — TAbrodi · 2026-11-04
- Kimi K3.1 Pro weights drop tomorrow: 2.8T params, 1M-token context — togethercompute · 2026-11-04
- 86% of orgs run AI agents, but under 18% can automatically stop a misbehaving one — amasad · 2026-11-04
- CMU Study: Harness Engineering Boosts Scientific Agents Without Retraining — niloofar_mire · 2026-11-04