Tenex on AI-Native Engineering: Outcome-Based Pay, MetaHarness, and Kill My SaaS
Latent Space · youtube · 2026-10-21
Latent Space interviews Tenex's Alex Lieberman and CJ Hess at AI Engineer New York on organizing engineering teams when AI agents handle more implementation work.
Key topics:
- Outcome-based pay: Tenex charges clients for engineering outcomes rather than hours, breaking from hourly billing
- MetaHarness process: keeping plans, project context, and decisions in version control so agents stay coherent on long-running tasks
- Enterprise adoption gap: what blocks agent deployment in companies, plus the economics of token spend and ROI
- Kill My SaaS: where AI-built software can and cannot replace traditional SaaS
They also cover implications for workers and New York's AI ecosystem.
More from coding & agent
- Ethan Mollick's new book charts 30 months of AI progress, from cyborg to conjurer work — rseroter · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang details Vera Rubin agentic stack: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23