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 functions such as engineering, product management, design, and sales. In the newsletter mentions, Factory appears both as a company philosophy and as the builder of agent-driven tools like Droid and PM-oriented skills like Eno. The core idea is that humans provide context, direction, and feedback loops while AI agents execute meaningful portions of the work.

For AI Product Managers, Factory matters because it offers a concrete view of what high-autonomy product development can look like in practice. Rather than using AI only for lightweight assistance, Factory represents a model where agents help with planning, specification, implementation, QA, and product thinking. This makes it a useful reference point for PMs designing AI-native workflows, experimenting with agent orchestration, or redefining team operating models around human judgment plus machine execution.

Key Developments

• 2026-02-14: Factory is cited alongside Ramp and Linear as an AI-native startup that delegates tasks to AI agents across engineering, PM, design, and sales, with humans focusing on context, systems, and feedback loops.
• 2026-02-15: Peter Yang previews Eno, a new AI-powered product management skill built at Factory. The skill includes product principles, positioning guidance, 11-star experience guidelines, PRD templates, review rubrics, and prioritization frameworks.
• 2026-02-16: Peter Yang uses Factory's Droid agent through the Ghosty CLI in high-autonomy spec mode. With Opus 4.5 used for planning and GPT-5.2 for execution, Droid helps build and QA a React speed-reading web app, including spec generation in VS Code, Chrome DevTools screenshots, linting, and type-checking.

Relevance to AI PMs

1. A reference model for AI-first team design: Factory shows how PMs can structure teams so agents handle execution-heavy tasks while humans own strategy, context-setting, and quality control. 2. A blueprint for agentic product workflows: The Droid example is useful for PMs exploring how AI can move beyond ideation into specs, implementation support, QA, and iterative refinement within a single workflow. 3. Practical PM enablement through embedded skills: Eno suggests that product knowledge, principles, templates, and review criteria can be packaged into AI-native tools, helping PMs standardize decision-making and scale good product practice.

Related

• droid: Factory's AI agent used for high-autonomy product and coding workflows.
• ghosty-cli: The CLI interface through which Droid was used in the newsletter example.
• opus-45: Model used for planning in the Droid workflow described by Peter Yang.
• gpt-52: Model used for execution in the same Droid workflow.
• eno: An AI-powered product management skill built at Factory, focused on principles, PRDs, review rubrics, and prioritization.
• ramp: Another AI-native startup mentioned alongside Factory as part of the AI-first operating model trend.
• linear: Also cited with Factory and Ramp as an example of delegating cross-functional work to AI agents.
• peter-yang: The newsletter author and operator who highlighted Factory's tools and operating model through hands-on examples.