Factory

Overview

Factory is an AI-native startup highlighted as an example of an AI-first operating model, where work is delegated to AI agents across multiple business functions rather than concentrated only in engineering. In the newsletter mentions, Factory appears both as a company building agentic tooling—such as the Droid agent used through the Ghosty CLI—and as an organization shaping practical AI workflows for product work, planning, and execution.

For AI Product Managers, Factory matters because it represents a concrete operating model for how teams may work in the near future: humans provide context, define systems, and manage feedback loops, while AI agents handle substantial portions of execution. The mentions also suggest that Factory is not just building coding agents, but packaging product management knowledge and decision frameworks into AI-powered skills, making it especially relevant for PMs thinking about how product, design, and engineering workflows evolve in agent-native companies.

Key Developments

• 2026-02-14: Factory was cited alongside Ramp and Linear as an AI-native startup delegating tasks to AI agents across engineering, product management, design, and sales, with humans focusing on context, systems, and feedback loops.
• 2026-02-15: Peter Yang previewed Eno's new AI-powered product management skill, built at Factory, which included product principles, positioning guidance, 11-star experience guidelines, PRD templates, review rubrics, and prioritization frameworks.
• 2026-02-16: Peter Yang demonstrated Factory's Droid agent via the Ghosty CLI in high-autonomy spec mode, using Opus 4.5 for planning and GPT-5.2 for execution to build and QA a React speed-reading web app. The workflow included prompting for inputs, generating an editable spec in VS Code, and running implementation and QA steps such as Chrome DevTools screenshots, linting, and type-checking.

Relevance to AI PMs

1. A model for AI-first team design: Factory shows how PMs can rethink team workflows so AI agents handle repeatable execution across functions, while humans spend more time on strategy, context setting, and quality control. 2. Spec-driven agent workflows: The Droid example is especially relevant for PMs because it starts with structured inputs and an editable specification before execution. This points to a practical PM pattern: use specs, constraints, and review gates to safely increase agent autonomy. 3. Codifying PM craft into reusable AI systems: The Eno skill suggests that PM best practices—principles, templates, rubrics, and prioritization logic—can be embedded into AI tools. PMs can apply this by turning their own playbooks into repeatable prompts, agents, or internal skills.

Related

• droid: Factory's agent used for planning, building, and QA workflows in the cited tutorial.
• ghosty-cli: The interface used to run Droid, including high-autonomy spec mode.
• opus-45: Used in the example workflow for planning.
• gpt-52: Used in the example workflow for execution.
• eno: Connected to Factory through an AI-powered product management skill that packages PM guidance and frameworks.
• ramp: Mentioned alongside Factory as an AI-native company delegating work to agents across functions.
• linear: Also cited as a peer example of an AI-native operating model.
• peter-yang: The creator/commentator who highlighted Factory in multiple newsletter mentions through examples and previews.