AI to empower people in need
and those who help them
The first open-source AI agent platform built for public services.
Everyone who needs help
can receive it.
AI that is safe, effective and sovereign, for public services
1Safe
It follows your protocols rather than the model's defaults, cites its sources line by line, and your experts validate it before it goes live.
2Effective
It is measured in production, on field results: time given back to teams, faster answers for the public, compliance tracked over time.
3Sovereign
It runs on your infrastructure, with your data, in open source. You can take over at any time.
Generic AI wasn't built for public & social services
Millions of people depend every day on frontline professionals. But commercial AI wasn't built for them.
It doesn't know their protocols.
It can't protect sensitive data.
It hallucinates when it matters most.
The leading nonprofit for AI in public services
We believe AI can help solve the capacity gap between the number of people who need help and those on the frontlines. This is why we partner with public services and NGOs to build AI agents that address societal needs. Founded in Silicon Valley in 2014.
Learn moreIntroducing the Bayes Platform
The first open-source AI agent platform built for public services. Here is what it does, in the real product.
The agent is tied to no model and no supplier. Changing either means retesting and recalibrating the harness, with no business logic to rewrite, and open models remain an option when the case calls for one.
Managed cloud or your own infrastructure, from a single Docker image. The retention period is yours, health data is hosted on HDS-certified infrastructure, and your data never trains a third-party model.
The code is MIT-licensed: you deploy it, change it, and keep it if Bayes disappears. What one institution funds benefits the next, with no licence to buy.
The agent answers from your handbooks, protocols and official references, never from the open web. Every answer cites the document and the extract it used, and the platform enforces your rules when the model skips them.
A model alone does not make a public-service agent. What matters is everything around it: sources, rules, evaluation, monitoring. The Bayes Platform is that harness, built for public service and nothing else.
Your frontline teams create and tune their own agents, with no code. Every change writes a draft, and nothing reaches the public that a human has not published.
Evaluation campaigns replay conversation and extraction datasets against a chosen version. Reviewers rate the answers blind, an LLM judge gives the scale, and two runs compare side by side.
Every exchange is filed under the life situations you defined, and the topics your answers cover badly surface on their own. You complete the corpus, re-evaluate and publish: the agent improves with every version.
Each agent is exposed over API and MCP, an open standard: the assistant or portal your institution already runs calls it as a tool. A widget or a public page when that is simpler. Nobody changes screen.
In the press
A few selected press features about our mission and work.