The best agents for software development are becoming the best agents for everything. Droids are the best software development agents in the world, reaching #1 on Terminal-Bench.
We have raised $50M from NEA, Sequoia Capital, J.P. Morgan, Nvidia, Abstract Ventures, and other industry leaders including Frank Slootman, Nikesh Arora, and Aaron Levie.
Today, Droids are available to anyone, with any model, in any interface: CLI, IDE, Slack, Linear, Browser.
Software development is more than just coding.
Introducing Droids -- the world's first software development agents. 🤖
Starting today, Droids are available for general access.
Factory integrates with your entire engineering system (GitHub, Slack, Linear, Notion, Sentry) and serves that context to your Droids as they autonomously build production-ready software.
Factory is the first platform that allows you to work with agents: local + synchronous and remote + asynchronous.
Reliable task delegation is the next frontier of software agents, and @FactoryAI 🤖🦾 is building the platform for it! @EnoReyes shares how:
- "We think this the point of time where there are the least number of software developers" but the definition will change to high level tasks
- Planning is tough to get right, but is a key step for reliability
- 93% of actions are accepted without revision!
- Environmental grounding (control over input/output from tools, AI-computer interfaces) is vital
INTRODUCING FACTORY
Factory is the Command Center where developers and agentic AI collaborate to understand, plan, and build enterprise software.
Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems powered by frontier LLMs. In your Factory,
• 🤖 Droid Mode unlocks cutting-edge agentic capabilities. Accelerate your development with AI that autonomously pulls in tickets, reads error logs, retrieves relevant context, executes code, and solves complex, long-running tasks.
• 🪡 Threads let you jump into deep work with all relevant context dynamically surfaced in front of you. No more crawling through Github, Slack, Google Drive, Notion, Jira, Slack, or context-switching between them.
• ⚡ Workflows transform and centralize your organization’s best practices into executable, AI-powered processes. Automate repetitive tasks like building integrations, bug-fixing, PRD creation, release notes, version updates, and more.
We're working with some of the most innovative organizations in software — from AI-forward enterprises like @MongoDB to high-growth organizations across the world. Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems using frontier LLMs like o3 and Claude 3.7 Sonnet
1/7
A fully autonomous software engineer is a matter of time!
I would have never believed this was going to happen in my lifetime. Over the last 12 months, I'm convinced I'll see software writing software.
A few days ago, @FactoryAI announced Code Droid. It beat everyone, including Devin, in the most popular AI coding benchmark out there.
Factory's Code Droid can do a few things without any human intervention:
1. Developing new features for an existing codebase
2. Modernizing a codebase
3. Creating proof of concepts
4. Building integrations
Here is what makes Code Droid work:
First, Code Droid decomposes high-level problems into smaller subtasks. It maps each subtask to an action space and finds the optimal trajectory to solve the original problem.
To find the optimal trajectory, Code Droid can simulate decisions, perform self-criticism, and reflect on real and imagined decisions.
Code Droid can access any development tools: editors, version control systems, debuggers, linters, and static analyzers. It also uses multiple models to do its job, including OpenAI's and Anthropic's latest models. It's not clear whether it uses any open-source model.
I'm attaching a picture of the SWE-bench results, a benchmark that tests an agent's ability to solve real-world tasks.
Code Droid outperformed everyone else by quite a margin.
@FactoryAI went into a lot more detail in their technical report: https://t.co/Q0Wubbm5SB
This is happening, folks!
We are watching how coding agents automate every step of the software development lifecycle.
THE MACHINE THAT BUILDS THE MACHINE
Today we are excited to announce the latest updates from Factory and the next steps in our mission to Bring Autonomy to Software Engineering.
Droids are autonomous systems that solve problems for engineers. Not just in demos. Not just in simple repositories. In complex, production settings. Testing, debugging, refactoring, migrating, reviewing, documenting — world class organizations are accelerating their software development with Factory’s Droids.
In addition to building out the Droid Fleet, we have some other exciting updates to share:
- New SOTA benchmarks. 31.67% on SWE-bench Lite. 19.27% on SWE-bench Full.
- New Fundraising. $15M Series A led by Sequoia Capital.
1/6
Devin was just the beginning...
@FactoryAI drops 'Droids' to bring autonomy to software engineering.
I believe this concept/idea is coming to EVERYTHING...
Machines that can think and act on their own for humanities benefit has been a dream since the first computer. It is now possible to make this dream a reality. If you want to work on the highest leverage problem in history, join us:
https://t.co/hDtcss7CLX
Factory is bringing autonomy to software engineering.
Excited to announce our $5M fundraise, led by @sequoia (@shaunmmaguire) and @Lux_Capital (@breeves08)
Read more here:
https://t.co/ldYQmqMZnw