AI automation startups' huge FDE teams are a product gap, founder argues; winners will bake work-understanding into product
sorenrood · x · 2026-09-27
Every AI automation startup is too focused on "doing the work," argues sorenrood—the real challenge is understanding the work well enough to do it. That's why so many companies build huge FDE (forward-deployed engineer) teams: it's essentially a product gap. The product can't figure out the work on its own, so people must map processes, encode business rules, and maintain agents.
- The winner, he predicts, will make understanding the work part of the product itself.
- FDE is still valuable—his own team plans to 3x within 12 months.
- But if your FDEs spend all their time on process discovery and agent maintenance, that's a bad sign for the product.
More from coding & agent
- Codex power users say Astra burns $200 limits in days while Anthropic's cap is hard to hit — brandon_galang · 2026-09-27
- 575 PRs and counting: steipete uses an Astra /goal to refactor sync DB access into async workers — AlexTensor · 2026-09-27
- Agent auto-books calls from DM replies in minutes with zero human involvement — eptwts · 2026-09-27
- Claude Pro vs ChatGPT Plus at $20: a student asks which subscription lives up to real work — NooneAllAlone · 2026-09-27
- Dev's scheduling library jumps from 1.5M to 2.5M monthly installs — GabGarrett · 2026-09-27
- Hyperagent launches Rooms, a multiplayer space where agents and humans work together — rvp · 2026-09-27