Enterprise AI, in everyone's hands.
Bud Studio is a desktop app that gives every employee a personal AI agent — connected to the tools their organisation has already approved, learning from their work, and coordinating with other agents to get things done.
The consumption layer of the Bud stack.
Studio is where the AI you build actually reaches the people doing the work. Instead of scattered chatbots and shadow AI, every employee gets one governed agent — running on the organisation's own models, tools, and permissions, inside its own environment.
- Bud Studio is Layer 07 of the eight-layer Bud stack — the consumption layer: one governed personal agent per employee, desktop-native on macOS, Windows and Linux, inheriting the models, connectors, guardrails and permissions set in Bud AI Foundry, governed by SENTRY.
- The agent network: you ask your agent in chat; it reaches a colleague's or a purpose-built agent, permission-checked before anything is shared; the answer returns in the background and the full exchange lands in the Inbox.
- Six capabilities: personal assistant, memory & personality, agent-to-agent network, Inbox, per-user connectors, canvas & auto-evolving skills.
- The result: enterprise AI, in everyone's hands — one governed agent, zero shadow AI.
Scattered chatbots become one governed agent.
Every employee gets a personal agent — independent memory, context and personality — that works for them and represents them to other agents. It runs on the organisation's own models, connectors and permissions, so the workforce gets powerful AI with zero shadow AI: there is no path around the organisation's approvals.
What comparable assistants don't do.
Standalone assistants exist. Studio's differentiators are the network between agents, the permission model underneath it, and the skills that write themselves.
Agent-to-agent network
Ask your own agent — it reaches a colleague's or a purpose-built agent, works in the background, and returns only the answer.
An observable network
The Inbox shows every agent exchange as an email-style thread — who asked whom, what was shared — and you can respond inside one directly.
Auto-evolving skills
Studio spots the procedures you repeat, draws them as a workflow on the canvas, and converts them into skills — one-off requests are ignored.
Per-user connector auth
Whatever the admin enables in Foundry, you authorise with your own account through a sign-in flow — email, Jira, calendars, docs, storage.
Governed consumption
Models, connectors, guardrails and permissions are set once in Bud AI Foundry; Studio inherits every restriction, with SENTRY on every action.
Desktop-native
A native app with local file-system access — it works with the files and applications on the machine, not just what lives in a browser tab.
The full story, in depth.
The agent-to-agent protocol, the connector auth model, the canvas-to-skill pipeline, and where Studio sits in the platform argument.
Product Brief
Bud Studio Product Brief
The deep-dive product reference
The one-agent-two-roles model, the agent network and its Inbox, per-user connector authorisation, the canvas-to-skill pipeline, and the desktop deployment envelope.
Read the product briefPlatform White Paper
The Enterprise AI Management Platform
Why consumption needs a governed layer
The platform-level argument — why the layer employees touch must inherit the governance, serving, and cost control of the layers beneath it, not bypass them.
Read the white paperPut your data on it.
The fastest way to see what an integrated AI operating system does for your enterprise is a proof-of-concept on your infrastructure, with your data.