Optional, BYO key

AI assistant

Claude edits the canvas in plain English. Bring your own Anthropic API key, or point ICE at any OpenAI-compatible endpoint. Off by default. Your data stays on your server.

How you use it

The chat panel sits next to the canvas. The model sees your graph. You ask in English, it answers, and when changes are warranted they show up as ghost suggestions that you accept or reject.

Prompts that work today

Add a Postgres database and connect it to the backend.

Why is the API gateway showing a warning?

Migrate the queue from GCP to AWS, keeping the rest of the canvas as-is.

Explain the last failed deploy and propose a fix.

What it does today

Chat about the canvas

The model gets the current graph as context. Answers stream over SSE.

Propose changes as ghosts

New blocks and edges appear as dashed previews. You accept or reject them.

Diagnose deploy failures

Click "Explain" on a failed deploy and the assistant walks through it.

Read-level deploy context

A summary of what is deployed, drifted, or pending is injected into the system prompt.

What is coming

From the public roadmap.

Live cloud queries (AI Read L2 and L3) so the model sees current state, not just the last import.
Multi-step tool use: plan, read, propose, validate.
Full mutation surface: delete, rename, modify, group.
Proactive suggestions: unused blocks, missing secrets, cost outliers.
Per-provider prompt profiles.
Validated OpenAI-compat backends (Ollama, LM Studio, vLLM).

Privacy and control

The API key lives on the server. The browser never sees it.
ICE works fine without an AI key. The chat panel just stays disabled.
Every model proposal is gated by an explicit Accept click. No autonomous apply.
Run against a local Ollama, LM Studio, or any OpenAI-compatible endpoint if you would rather not send prompts off-machine.

Full AI assistant docs

Get started in two lines

# .env
ANTHROPIC_API_KEY=sk-ant-...

Get a key at console.anthropic.com. Restart ICE. The chat panel unlocks.