AI overview

Dalea exposes AI capabilities through two surfaces, with different audiences and different user-experience.

In-app chat

A side panel that lives inside dalea.app. Authenticated as you. Picks any of six supported model providers, or runs on the Dalea-hosted default with no setup.

External MCP

Your Claude Desktop/Code, Cursor or ChatGPT, connecting via OAuth to a specific workspace.

The in-app chat

Open it with by clicking the floating Dalea icon. The panel is multi-turn, streaming, tool-using, and aware of:

• the workspace you're in
• the document you're currently viewing (if any)
• the data model you're currently viewing (if any)
• etc.

It can do most operation you can do — find documents, read data records, create new documents, append blocks, register objects, run data queries, and compose follow-up questions about the results.

Approval cards

When the assistant proposes to run a tool (manage_documents:create, data_objects:bulk_create, placements:check_out, …), it pauses and emits an approval card. You see:

• the tool and action
• the arguments (resource name, payload summary)
• buttons: Approve once, Reject, Always approve this action type

The "always" toggle is per-workspace, that allows the given action to always auto-approve; you can revoke auto-approvals from the chat panel's settings menu → Tool Approvals.

Plan mode for multi-step work

For anything that isn't a one-shot question, the assistant writes a short prose plan first — explore the workspace, propose the steps, then wait. You see the plan as a card with Approve, Modify, or Abort buttons. No tools run until you choose. See Plan mode for the full flow.

Models and providers

Each user picks which providers to use from Settings → AI Providers — Anthropic, OpenAI, Google, Mistral, DeepSeek (each with your own API key), or simply the Dalea default which needs no setup. The same screen sets your default model. After activating a provider set with an API key, the models from that provider will appear in the model selector in the top left corner of the chat. See Models & providers for the full catalogue.

Skills

Skills are short markdown primers the assistant loads on demand — for example, the built-in data_python skill teaches the ai to use the in-platform python capabilities properly. You can also author your own skills at workspace or personal scope. See Skills.

Vision

On a vision-capable model (Claude 4.x, Gemini 2.5+, GPT-5.x, Gemma 4, Mistral), you can drag any picture (instrument photos, gel scans, or UI screenshots) straight into the chat for the model to read. The composer disables image attachment for text-only models so you can't silently send images that the model would reject.

Wiki-grounded answers

For "what is…" / "how do I…" questions, the assistant consults this wiki plus your workspace documents and data models for grounding — so terminology stays consistent with the official docs and references back to real workspace content where it exists.

Frontend tools

A small set of tools execute in the browser without server confirmation: navigate, register_plan, update_todos. These can't change anything; they just steer your UI and chat experience in response to a request like "open the IFN-γ protocol" or "create a plan for grounding our experiment setup with websearch".

The external MCP server

Dalea's MCP server exposes your workspace as a set of tools that any MCP-compatible LLM can call. The flow is OAuth 2.1; the connection is HTTP-streaming. See Connect Claude Desktop for the step-by-step setup.

External clients see roughly 25 tools grouped by domain — documents, blocks, data, queries, inventory, files, search — plus search_knowledge for grounding answers against the wiki and load_skill for pulling in domain primers.

External clients are bound by:

• Workspace scope — each token authorises exactly one workspace, enforced server-side on every call.
• Role intersection — the OAuth client is created with a role; effective permissions are the intersection of your role and the client's role.
• Audit — every tool call is logged with operator, timestamp and args.

Privacy

Tool inputs and outputs go to the LLM provider you configured. Dalea never sends data to a model unless you opted into a chat session that uses it. When you bring your own provider key, the request goes directly from Dalea's servers to that provider — Dalea never logs prompt content, only token counts and tool-call metadata for audit.

What's next