Today, FutureHouse is releasing the first dedicated AI Agents for Science, via our Platform. These agents are able to perform a wide variety of scientific tasks better than humans. With the platform, we are bringing these capabilities to the wider community. 1/2

The plan at FutureHouse has been to build scientific agents for discoveries. We’ve spent the last year researching the best way to make agents. We’ve made a ton of progress and now we’ve engineered them to be used at scale, by anyone. Free and on API.

We can't wait to see how scientists use and build on top of these agents! You can read more by checking out our blogpost
www.futurehouse.org/research-an..., and try it out for free at platform.futurehouse.org/

Phoenix is FutureHouse's deployment of ChemCrow, an agent with access to specialized tools that allow it to help researchers in planning chemistry experiments.

Owl (formerly HasAnyone) is specialized to answer the question “Has anyone done X before?”

Falcon is specialized for deep literature reviews. It can search and synthesize more scientific literature than any other agent we are aware of, and also has access to several specialized scientific databases, like OpenTargets.

Crow is a general-purpose agent that can search the literature and provide concise, scholarly answers to questions, and is perfect for use via API.

Today, FutureHouse is launching the FutureHouse Platform, bringing the first-ever superintelligent scientific AI agents to scientists everywhere via a web interface and API. The Platform is launching with four agents, each with their own specialization:

Blog: bit.ly/4km2zdd
Paper pdf: bit.ly/41pclCz
Eval code on GitHub: bit.ly/3QPHF8x
Agent code on GitHub: bit.ly/3QKbpE8

Introducing BixBench, a benchmark for AI agents in bioinformatics, built with ScienceMachine. We've created 53 scenarios with 296 questions testing AI on computational biology challenges. BixBench includes evaluation metrics and an open-source LLM environment.