AI to empower people in need
and those who help them
The first open-source AI agent platform built for public services.
chi ha bisogno di aiuto
possa riceverlo.
Un'IA sicura, efficace e sovrana per il servizio pubblico
1Sicura
Segue i tuoi protocolli invece dei riflessi del modello, cita le sue fonti riga per riga, e i tuoi esperti la convalidano prima della messa in servizio.
2Efficace
Si misura in produzione, su risultati concreti: tempo restituito ai team, risposte più rapide agli utenti, una conformità monitorata nel tempo.
3Sovrana
Funziona sulla tua infrastruttura, con i tuoi dati, in open source. Puoi riprenderne il controllo in qualsiasi momento.
L'IA generica non è stata pensata per i servizi pubblici e sociali
Milioni di persone dipendono ogni giorno dai professionisti sul campo. Ma le IA commerciali non sono state progettate per loro.
Non conoscono i loro protocolli.
Non proteggono i dati sensibili.
Allucinano proprio quando conta di più.
L'organizzazione no-profit di riferimento che usa l'intelligenza artificiale per reinventare i servizi pubblici su larga scala
Fondata nella Silicon Valley nel 2014, le nostre soluzioni open-source basate su IA sono usate da governi, organizzazioni internazionali e comunità locali in otto paesi, al servizio di milioni di cittadini.
Scopri di piùIntroducing 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 answers from your handbooks, protocols and official references: resource libraries, tagged documents, PDF import, a site indexed by crawl. Never from the open web.
The sources panel shows the document title and the extract used, so whoever reads the answer can check it. An answer nobody can verify has no place in a public service.
The agent's settings are your organisation's. Every reply has to report its own bookkeeping: session title, categories drawn from your list, sources cited. The platform enforces that when the model skips it.
Every change writes a draft. Publishing makes it the version that runs, named and dated in the history, and every reply carries its version badge. Nothing reaches the public that a human has not published.
Your frontline teams create and tune their own agents, with no code and no internal data team. Your IT keeps the path to production without being the bottleneck.
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. The topics your answers cover badly surface on their own, instead of waiting for a complaint.
Each agent exposes itself as an MCP server, so the assistant or portal your institution already runs calls it as a tool. A widget on your site or a public page when that is simpler. Nobody changes screen.
Managed cloud, or your own infrastructure from a single Docker image. Document isolation is written into the retrieval query itself rather than a checkbox, the retention period is yours, and the code is MIT-licensed.
AI grounded in your own protocols.
A general-purpose assistant answers plausibly but sometimes wrongly; grounded in your official, cited guidelines, it answers correctly.
DemoThe same clinical question, put at once to a generic assistant and to the MCP-verified platform.
A proactive AI work coach.
An agent that draws on the platform tools to answer, and stays within its remit: out of scope, it routes you to a human counsellor.
DemoA coach that calls tools, surfaces openings and benefits, and hands off to a counsellor when a request is out of scope.
A whole public service, by chat.
A full administrative procedure handled end-to-end on WhatsApp, without leaving the conversation.
DemoA diploma request: identity (e-ID), auto-fill from the official records, and payment.
Sulla stampa
Una selezione di articoli stampa sulla nostra missione e sul nostro lavoro.