AI

The platform includes a flexible, provider-agnostic AI layer that lets you connect your own language models and use them across the product. Instead of locking you into a single vendor, the platform is built around a few core concepts:

• LLM Providers - connections to the language model backends you want to use, whether that's a cloud API (OpenAI, Anthropic, Gemini, DeepSeek), an enterprise gateway (AWS Bedrock), or an external self-hosted model server (Ollama, llama.cpp, or any OpenAI-compatible endpoint).
• Agents - named, reusable configurations built on top of a provider. An agent pairs a specific model with custom instructions and capability flags, so you can shape how it behaves without touching code.
• Chats - streaming conversations with your agents. You can attach images and text files, dictate with your voice, and chat is context-aware: sessions opened from a Resource Item know about that item, and every Resource Item's data is indexed for natural-language retrieval.
• Tools & Connectors - give agents superpowers beyond text generation. Built-in tools let agents search your data, generate charts, create resource items, run workflows, and schedule recurring tasks. Connectors (MCP servers) bring in external tools from anywhere.

Once you've set up at least one provider and one agent, you're ready to start chatting.

How it fits togetherCopy Anchor Link

1. Connect a provider - Add connection details for an LLM backend. See Creating an LLM Provider.
2. Create an agent - Pick a provider, choose one of its available models, and give the agent a name, description, and instructions. See Creating an Agent.
3. Start chatting - Every chat session begins with a chosen agent, and you can switch agents mid-conversation without losing context. See Chatting with Agents.
4. (Optional) Extend capabilities - Enable built-in tools or add external tool servers via connectors to let agents act on your behalf.

Why providers and agents are separateCopy Anchor Link

Separating providers from agents keeps your setup flexible:

• You can register multiple providers for the same vendor - for example, two separate OpenAI providers, each with its own API key, to isolate billing or usage tracking on OpenAI's own dashboard.
• You can create multiple agents on the same model with different instructions - for example, a "Support Assistant" and an "Internal Docs Assistant" both running on gpt-4.1, but tuned for very different tasks.

Where AI shows up in the productCopy Anchor Link

Beyond the dedicated chat experience, agents and models power several features across the platform:

• Semantic search - Resource Items and their attached documents are automatically embedded into a vector index, so both the global search page and chat agents can find records by meaning rather than exact keywords. See Resources.
• Workflow automation - The Agent Call node lets any workflow reason over unstructured data, extract structured output, and make dynamic routing decisions. See the Agent Call node.
• Form generation - Workflows can ask an agent to generate dynamic form schemas for human-in-the-loop tasks. See User Task nodes.