Generate a Whole Campaign with the Wizard

You can scaffold an entire Campaign — one unit of your course — in a single pass. The wizard generates structure inside a campaign that already exists, so create it first (here’s how), then let the wizard fill it with paths, nodes, vocabulary and checks.

The wizard’s widest scope is a unit, not a course: there is no course-level scope, so a House with four campaigns in it is four wizard runs, each grounded in the Lore the course already shares.

Scaffold the campaign

1. Open the wizard at Campaign scope

   In the Builder, open the AI Wizard and leave the scope button alone — at campaign scope it reads your framing concept, and the session is labeled Campaign Wizard. The wizard greets you with the framing concept and offers a card for each thing it can make here: Outline the paths and nodes, Draft vocabulary terms and Write every node’s checks.

   Capture pendingThe AI Wizard at campaign scope, its scope button reading the campaign's framing concept1440 × 900 · 16:10

2. (Recommended) Ask the wizard to plan first

   Ask the wizard to plan describes what you want in plain words and gets back a numbered list of proposed steps instead of content. The wizard reads what is already in the campaign, says what it found, shows which of your essential questions are already covered, and proposes changes.

   Every step is editable: rewrite a directive to say what you actually meant, or ✕ it out of the plan. Below them sit Step back, Dismiss, and Approve, which carries the number of steps you kept. Asking a question in the chat field leaves the plan — and your edits — intact.

   Some plans have two gates. The first, STEP 1 · STRUCTURE, changes paths and nodes (Approve structure). If moving a node’s objective means its content no longer matches, a second gate, STEP 2 · CONTENT, proposes the matching changes (Approve content). Approving applies the changes to your draft canvas, and you still review and save the draft.

   Capture pendingThe proposed structure plan at the approval gate, its What I found diagnosis above the editable per-path directives1440 × 900 · 16:10

   Planning is not free

   A plan spends credit like any other request — it is cheaper than a generation, not exempt from your balance. What it buys you is the chance to see and edit the steps before the expensive half runs, so a wrong assumption costs a plan instead of a whole campaign.

3. Or go straight to a draft

   Tap Outline the paths and nodes. Unlike the plan route, this one goes straight to a reviewable draft.

   Staging the card reveals the sentences that size the run — “I desire 3 paths, with 4 nodes each. Outline now — checks come later. Per node, align 2 new or reused vocabulary terms.” Every bold value is a pill you tap to change, and those numbers are what decide how long the run takes and how much of your credit it spends. Guidance below is optional.

   The second sentence’s leading pill is the depth control. Both depths build every path’s nodes at the count you set. Switch it from Outline now to Size the nodes too and the sentence grows a leaf clause — “…each to hold 4 checks and 5 questions after you save.” Those leaf counts are remembered for the fill that follows your save, not generated now: the run writes guiding questions and learning objectives. The card says so itself — “Guiding questions and learning objectives — checks come later.”

   Capture pendingThe staged Outline the paths and nodes card above the fill-in-the-blanks sentences with tappable count pills1440 × 900 · 16:10

4. Tune Context & settings (optional)

   The tune icon at the bottom of the composer (Context & settings) opens the Context Wizard. Choose which elements feed the prompt (the unit’s framing concept and vocabulary, the course’s Lore) and set the balance — for example “Balanced,” “Learning First,” or “Story Forward.” A dot on the icon means the session is running on non-default settings. The paperclip beside it attaches sources for the wizard to ground its work in.

5. Watch the segments, then review

   While the run is in flight, per-segment checkpoint tiles (Paths, Nodes, Vocabulary, Coaching) appear as each one completes, and they are the one place that reports what a segment actually cost. If a segment fails, only it shows a retry chip — the rest still land.

   A run that writes checks (the Write every node’s checks card) reports its own steps, such as Narratives — the passages students read in a History Check — then Evidence, Charts & Media, Reflections and Script. While it works, the status line reads, for example, “Writing narratives…”.

   Once the run settles those tiles give way to the durable record: a coaching summary, Next steps, and a changelog of what was created.

   Capture pendingThe settled review state with the pedagogical rationale expanded above the changelog and next steps1440 × 900 · 16:10

6. Save the whole structure

   Use the field to ask for a change, or tap Save to persist the entire tree in one transaction. The receipt shows Saved to: <campaign> with a count line. From there, run the Write every node’s checks card to give each node without checks its checks (nodes that already have checks keep them, and every node’s questions stay), or drill into one node and run object-level generation.

   If you don’t like the result, Undo this save on the receipt puts the campaign back as it was before the save: every AI save takes a restore point first. See Trash, restore points and undoing a delete.