Budibase Agents Beta – model-agnostic AI agents for internal workflows
Hi there, Mike here from Budibase. We’ve recently launched AI Agents into Beta, alongside our existing open-source app-building and automation tools. We built Budibase Agents for teams that want to leverage AI within real-world workflows, using their own LLMs, data, and APIs. Because of this, our Agents can be powered by any LLM with an OpenAI-compatible API, including open-source and locally-hosted models. This means you can build Agents that connect to your existing toolstack, within your own environment. Some more details: - Agents' behavior is configured using natural language instructions, within existing Budibase Workspaces. - You explicitly control which data sources, APIs, and automations an agent can access. - End-users can interact with your agents via Budibase Chat, or using existing chat tools like Slack and Discord. - Agents can be called from Automations, and vice versa, enabling complex workflows, including interacting with end-user apps for manual human approvals. The Budibase Agents Beta is available now for all self-hosted and cloud users. As this is a Beta release, we’re actively looking for input and feedback on how we can improve Agents, in terms of experience and functionality for building using AI within real-life workflows. Feel free to let us know via our GitHub Discussions: https://github.com/budibase/budibase/discussions
- AI Agent
- Cloud Native
- Integrations
✨ AI Summary
Budibase Agents Beta is a model-agnostic platform for building AI agents that integrate with internal workflows, allowing teams to use their own LLMs, data, and APIs. Agents are configured with natural language, can access controlled data sources and automations, and are available for both self-hosted and cloud deployments.
Best For
Teams needing to integrate AI into existing internal workflows, Organizations requiring AI agents that work with proprietary or local LLMs, Developers building automated workflows with human-in-the-loop approvals
Why It Matters
It enables the creation of customizable, secure AI agents that operate within a company's own environment and toolstack, avoiding vendor lock-in.
Key Features
- Configure agent behavior using natural language instructions within Budibase Workspaces
- Connect to any LLM with OpenAI-compatible API, including open-source and locally-hosted models
- Explicitly control which data sources, APIs, and automations each agent can access
- Interact with agents via Budibase Chat or existing tools like Slack and Discord
Use Cases
- An IT support team deploys an agent that monitors internal Slack channels for common technical queries. When a user asks about resetting a password or accessing a shared drive, the agent automatically provides step-by-step instructions by pulling data from the company's knowledge base API, reducing the need for manual intervention.
- A project manager in a software company sets up an agent to handle routine status updates. Team members can ask the agent in Discord about the progress of specific tasks, and the agent fetches real-time data from the project management tool's API, summarizing current milestones and upcoming deadlines without requiring the manager to manually compile reports.
- A finance department creates an agent to assist with expense approval workflows. Employees submit reimbursement requests via a Budibase app, and the agent automatically reviews the submissions against company policy data, then either approves straightforward cases or flags exceptions for manual human review by a finance officer, streamlining the entire process.