Skip to main content
bash TV

The Software Factory: From Bug Report to Production Code — Davis Palmie, Factory

AI Engineer

6.5K views7 Oct 2026

YouTube

Engineers are going from typing code to governing agents. The next step is a system that turns bug reports into production code. Davis Palmie, member of technical staff at Factory, explains the software factory: a system of agents that takes input signals like bug reports and user feedback and turns them into production code. He covers the questions every leader asks, from runaway costs and model choice to what happens to engineers and org charts, and argues coding was never the bottleneck: review, debugging, docs and testing are. He lays out the principles a factory needs (model-agnostic, sovereign deployment, integrated across the SDLC, available on every surface), why to start with something narrow like incident triage, and Factory's eight pillars of agent readiness. He closes with why token leaderboards are Goodhart's law in action, and the outcome metrics to track instead. In this talk: • What a software factory is, and why coding was never the bottleneck • Model-agnostic, sovereign and SDLC-wide: principles for a factory • Agent readiness: eight pillars that help agents and engineers alike • Metrics that matter: signal-to-production time, interventions, cost per PR SPEAKER Davis Palmie, Member of Technical Staff, Factory LinkedIn: https://www.linkedin.com/in/davispalmie/ X: https://x.com/davispalmie Website: https://davispalmie.com LINKS Factory: https://factory.com Factory on X: https://x.com/FactoryAI CHAPTERS 0:00 Intro 0:57 Three eras of AI engineering 1:42 Climbing the abstraction ladder 2:07 From typing code to governing agents 2:52 Question 1: cost overruns 3:36 Question 2: access to the best models 4:06 Question 3: what happens to engineers 4:31 Question 4: the organization 4:56 Coding was never the bottleneck 6:21 What a software factory is 7:16 Start narrow: incident triage 8:11 Principle 1: model agnostic 9:00 Principle 2: sovereign deployment 9:25 Principle 3: integrated across the SDLC 10:00 What it looks like in practice 11:20 From O(n) to O(1) 12:40 Agents on every surface 13:35 Agent readiness: eight pillars 14:44 Governance and incremental rollout 15:29 Humans still set direction 16:29 Measure outcomes, not tokens 17:09 Metrics that matter Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #SoftwareFactory #AIAgents #AIEngineer

Join the discussion

Sign in to join the discussion

Sign in