Use the chat builder

The AI Chat Builder lets you describe a workflow in plain English. It opens as a floating, draggable, resizable window over the canvas.

Opening it

• Ctrl/Cmd+L toggles it open/closed.
• Click the AI Builder button in the canvas controls (purple gradient button with a star icon).

What it does

You type a message describing what you want, "Build a 3-agent research → writing → publishing pipeline" or "Add a reviewer that critiques the writer's output", and the chat builder applies structured edits to your workflow.

Behind the scenes, it emits typed operations (add agent, connect, set instructions, etc.) which Cerevisor applies the same way you'd apply them by clicking. Every edit goes through the same undo stack as your manual edits; Ctrl+Z works.

The window

Position

Drag the header bar of the window (not the buttons) to reposition. Position is clamped to the viewport: the window can't disappear off-screen.

Resize

Drag the bottom-right corner handle (cursor becomes nwse-resize). Constraints:

• Minimum: 320 × 320 px.
• Maximum: 960 × 1000 px.
• Further clamped to your current Cerevisor window size minus a small margin.

Minimize

Click the minimize button in the header. The window collapses to a 240 × 44 strip. Click again to restore to your last size.

Reset

There's no dedicated reset button. If the window ends up in a weird state, restarting Cerevisor re-clamps it.

The chat input

A standard textarea with these behaviors:

• Enter submits.
• Shift+Enter inserts a newline.
• The placeholder text suggests what to try.
• The input grows vertically as you type, up to a cap.

Attachments

Below the input, two buttons:

+Skill

Opens a skill picker. Pick skills to stage; they appear as chips below the input. When you submit, the staged skills are included as context: the chat builder considers them when proposing edits.

Useful when you want it to design a workflow around specific skills you have.

+File

Opens a file picker. Pick any file, markdown, PDF, text, image, code. The chat builder reads it and uses the content as part of the message context.

For images: included as a base64 image block (vision-capable models will see them). For PDFs: text-extracted via pdf-parse. For markdown/code/text: included as a text block wrapped in <attachment> tags so the model knows it's an attachment, not user prose.

Staged attachments show as chips. Click the X on a chip to remove.

Trust mode

A dropdown above the input. Three levels:

Level	Behavior
Full trust	Chat builder applies every edit immediately. Fastest, lowest friction.
Ask me	Chat builder previews each edit; you approve or reject before it applies.
Restricted	Chat builder only proposes — no edits are applied. You read the proposals and copy what you want.

Default is Full trust. Lower trust if the chat builder keeps making changes you don't want, or you're using it as a brainstorm tool rather than an editor.

Response mode

Mode	Behavior
Apply edits	The chat builder uses its tools (add agent, etc.) — actually edits your workflow.
Discuss only	The chat builder talks about your workflow but doesn't change it.

Useful for "how would I structure this?" conversations where you want advice, not changes.

Model picker

Click the model badge in the header to open the model picker. Lists every model on your chat-builder provider (configured in Settings → Chat Builder).

The picker shows a source label:

• From workflow override: this workflow has a specific model set for the chat builder.
• From global override: the chat-builder config has a model set.
• Provider default: using whatever model the provider defaults to.
• Unset: using the chat-builder provider's auto pick.

Run report

When a workflow run completes, the chat panel auto-appends a markdown Run report message showing every terminal agent's output. This makes the chat window double as a "what did my workflow produce?" log.

The report:

• Concatenates every leaf agent's output under per-agent headers.
• Truncates at ~12,000 characters with a footer pointing back to the agent card.

Stalled detection

If the chat builder's generation stalls (no progress for several seconds), a "Generation stalled, Rephrase?" chip appears below the message. Click it to focus the input and try a different wording.

Workflow-incomplete hint

If your workflow has obvious gaps (no agents, no input configured, missing required fields), a "Workflow incomplete" chip appears above the input. Click it to jump to the relevant settings.

What the chat builder is good at

• Sketching the rough shape of a workflow from a description.
• Adding agents you'd otherwise add by hand.
• Connecting agents you'd otherwise wire manually.
• Filling in role descriptions and instructions.
• Quick edits ("rename the second agent to 'Senior reviewer'").

What it's not good at

• Long, multi-step refactors. Do them in pieces.
• Setting up MCP servers, providers, or other configuration outside the workflow.
• Deciding what your workflow should do. It builds the structure you describe; it doesn't pick the goal.

Provider caveat

The chat builder needs a chat API. Codex CLI and Cursor Agent providers can't drive the chat builder; they have no chat-only mode. If your default provider is one of those, configure a different provider for the chat builder under Settings → Chat Builder.