Using the Agentic Brain for AI Workflow Planning

1. 1Chat: review proposals
2. 2Guided: work through a gap
3. 3Agent: start a bounded run

These are control modes, not automatic stages. Review the guide for each mode’s boundaries.

The Agentic Brain is the connected understanding the app builds about one AI opportunity. It uses the Canvas, approved sources, conversation history, computed assessments, and open questions to help the team improve that opportunity over time.

Instant Chat and the saved Brain are different surfaces

The front-page Instant Chat is an intake and preview experience. Canvas AI gathers the initial business context, may research a public website, and seeds a first Canvas, systems map, readiness assessment, and remediation worklist. A sector benchmark depends on the available cohort data; a sparse sample supports only a directional preview. It does not expose the Chat, Guided, and Agent dial.

After the Canvas is saved, the Agentic Brain page can work across the whole Canvas. Section chat uses the same Brain but focuses on the active Canvas section. AI Readiness, Overview, Summary, Slides, and ordinary output conversations explain the work without editing it. ROI chat can save explicit baseline answers or reviewed baseline proposals, but cannot edit authored Canvas sections.

Chat, Guided, and Agent modes

The mode controls who approves application. Chat means the user drives every change; Guided means the Brain proposes and always asks before applying; Agent means the Brain applies autonomously within visible bounds.

Chat

Chat is the default and most review-heavy mode.

• Asking a question produces an answer, recommendation, or proposed refinement.
• A chat response alone does not update Canvas content.
• When an Apply action is available, the user reviews the proposed destination and chooses whether to apply it.
• In a Canvas section, quick actions such as Suggest, Review, Shorten, Expand, Rephrase, and Format remain user-directed.
• Chat is the best choice for sensitive language, uncertain evidence, or any change that should be considered individually.

Guided on the Whole Canvas

Whole-Canvas Guided works through one saved gap at a time.

1. Brain resumes an unanswered gap already on the Canvas. It discovers one new gap only when no saved gaps remain, and may find nothing new.
2. Guided drafts an update for the current gap, or asks for the information needed to draft it.
3. Review the proposed change and choose what to apply. The Canvas changes only after approval.
4. A successful save records that gap as resolved and offers the next step. Other gaps remain saved; progress survives leaving and returning to the Canvas.

The progress count separates resolved, open and dismissed questions. Skipping or cancelling does not resolve a gap. Finishing the known gaps does not mean every possible gap has been discovered. Existing multi-update review cards retain their exact-change approval and history behavior.

Guided in a Canvas section

Section Guided follows the same rule as the Whole Canvas: Guided always asks before applying. Selecting Run Guided has Brain review the active section with Canvas context and prepare the single highest-impact improvement — as a proposal. The proposed change appears in the chat as a Proposed Refinement card, and the section draft is untouched until the user chooses Apply Action.

Agent on the Whole Canvas

Whole-Canvas Agent is a visible, bounded gap-resolution loop.

1. The user chooses Run agent, authorizing work on the currently listed open gaps.
2. Brain shows a live plan and takes one gap at a time.
3. Each successful step updates the mapped Canvas content and resolves the corresponding Brain gap.
4. The loop ends when no open gaps remain or when the user chooses Stop. Errors and skipped steps remain visible.

Agent mode does not deploy production agents, contact external people, or continue outside the current Canvas. Starting the run replaces per-step approval with the visible bounded plan and Stop control.

Agent in a Canvas section

Section Agent stays deliberately small but is a real agent pass: Run Agent authorizes one bounded pass through the same orchestrator that powers the Whole-Canvas loop, focused on the active section and aware of the unsaved draft. Brain plans, improves the draft, shows the visible plan steps in the chat, applies that one update to the editor draft, and stops. It does not start the multi-gap Whole-Canvas loop.

Assessment and output conversations

AI Readiness, Overview, Summary, Slides and ordinary output conversations can explain evidence, critique an artifact and recommend a next step. They do not edit the Canvas or regenerate outputs. These explanatory surfaces use a Read-only chat indicator rather than the action dial.

ROI is a bounded exception: explicit answers to its active structured baseline question can be saved directly, and baseline proposals can be applied after review. ROI chat cannot edit authored Canvas sections. Canvas-derived numbers remain estimates until confirmed.

Where the optional Run the agents preview is enabled, its conversation can also offer explicit approved proof actions. That does not grant ordinary output chat permission to run agents.

Build mode is a guide, not another autonomy level

Build on the main Brain page sequences the 11 authored Canvas sections and points to the next unfilled section. A section can be skipped for the current session, but that skip is not persisted. Filling every section means the authored sequence is filled; it does not mean every claim is validated, every readiness gap is closed, or the Brain is "complete."

The score shown during Build mode is the AI Readiness score. Section count and readiness confidence are related signals, not the same measurement.

Fresh chats, History, and audit

The Brain opens with a fresh visible conversation. Earlier conversations remain available through History and are scoped to Whole Canvas, a Canvas section, AI Readiness, or Agentic ROI. The Brain history page also shows growth-log events so the team can distinguish conversation from changes to the model.

History provides context and accountability, but an old statement is not automatically current evidence. Correct the Canvas or detach stale memory when the underlying operation changes.

Inspect What I know

Open What I know from the Brain to explore recorded systems, connections, facts and people. The full memory page supports search and filters by kind and confidence. Select an item to inspect its source and available actions. Systems-model items that can be matched to a specific record can offer Confirm and Fix; Fix opens a correction conversation. Section-derived facts and people do not offer those controls, and an unmatched record explains the limitation.

Correct section-derived information in its Canvas section. Model memory is distinct from attached external sources and from conversation history.

Sources and attached memory

The Sources control accepts notes, pasted excerpts, a Canvas snapshot, and supported Google Drive links. Raw material must be reviewed and approved before its summary and facts become attached memory. See Sources and memory for the lifecycle and limits.

For the vocabulary used here, see the glossary. For the limits on what the Brain may change, see governance and safety. For the whole journey, see how the app works, and to test one workflow first, use the agentic AI readiness checklist.

Next: Canvas guide.