AI for the Fortune 2000: How Tenex Builds an AI-Native SDLC — Alex Lieberman & CJ Hess
- ID
- 37742
- Status
- summarized
- Published
- 21 Oct 2026, 1:01 PM
- Fetched
- 23 Oct 2026, 6:04 PM
- Provider
- Latent Space
- Category
- developer-ai
- Original URL
- https://latent.space/p/tenex/
- Source URL
- https://www.latent.space/feed
Summary
- Score
- 6.5
- Created
- 23 Oct 2026, 6:04 PM
- Tags
- Audience
- developersvibe_codersai_ml_learnerssaas_founders
What happened
Latent Space interviews Tenex's Alex Lieberman and CJ Hess about scaling an AI-native SDLC: Tenex still ties engineering compensation partly to story points, has grown to 75 people serving Fortune 2000 and mid-market clients, and is shifting from an AI-powered dev shop toward company-wide AI transformation work. CJ describes MetaHarness—shared skills, project docs, and a CLI—with plans and decisions checked into Git so agents can read why code was built that way. The episode also cites a Kill My SaaS experiment where builders were asked to replace a speaker-management tool quoted at $43,000/year.
Why it matters
If you bill by the hour while using agents, this episode gives a concrete alternative: price delivered outcomes and keep decision rationale in Git so agents see not just code but the reasoning behind it. The $43,000/year SaaS replacement prompt is a practical benchmark for asking whether your own tool stack is worth rebuilding with agents—or whether cheaper builds should change what you charge.
Discussion angle
Debate whether checking plans and decision rationale into Git alongside code is the minimum viable memory layer for agents—and what from Tenex's 75-person setup you would copy first.