DocsGetting started

Uploading assets

You do not build a game from a blank canvas. Instead you upload your source material — the rulebook and the art — and an AI pipeline reads it and generates a first-draft table: a table surface with components, zones, seats, and rules text already laid out. That draft is a starting point, never the finished game. Remember the taybl model: the AI is arranging a physical scene, not writing a program, so the more clearly your assets describe what is on the table, the better the draft.

How to edit in the Studio

On a new or draft game you land on the uploader. Drop each file into the bucket that fits, optionally tell the AI a bit more, click Upload Assets, then Generate Game with AI. The uploader is non-blocking — it shows soft advisory warnings (e.g. no rulebook staged) but lets you proceed anyway.

The upload buckets

There are four drop targets. You do not have to pre-sort every image perfectly — board art, pieces, tokens, and dice all go into Components together, and the AI sorts them in the next step where you can correct anything it gets wrong.

BucketDrop hereAccepts
RulebookThe rules document — the AI reads it to extract rules text and objectivesPDF / TXT
ComponentsAnything that lives on the table: board art, pieces, tokens, dicePNG / JPEG / WebP
CardsCard faces (and backs)PNG / JPEG / WebP
Setup / Gameplay photosReference shots of a real table, for spatial layout. Tag each as Setup (initial layout) or Mid-gamePNG / JPEG / WebP

When you navigate back to a draft, an Already uploaded list shows the files on the server with thumbnails, and you can remove any of them before regenerating.

Optional: help the AI

Two optional fields below the buckets bias the generation toward the right kind of game. Neither is required.

FieldWhat it does
Game typeA category hint (Card game, Grid / abstract, Dice & tokens, Hand management, Area control, Other). The pipeline uses it to pick prompt variants and examples.
Notes for the AIFree-form text — describe anything the rulebook leaves implicit. It is spliced into the rule-extraction and generation prompts.

What happens while it generates

After you click Generate Game with AI, the pipeline runs through a series of steps. You watch a live checklist with a progress bar and an activity ticker; the status survives a reload, and a couple of steps may pause for your input (for example, confirming how the AI classified your component and card images).

StepWhat it does
Analyzing assetsReads every uploaded image and classifies it (board, piece, token, card, dice…).
Extracting rulesPulls the rules and objectives out of your rulebook into plain-language reference text.
Building game modelWorks out the components, zones, and seats the game needs.
Generating game definitionWrites the actual table: components, zones, layout, and setup.
Validating gameChecks the result against the schema and repairs structural problems.
Reviewing completenessAudits how fully the draft captures your rules before handing you the finished table.

When it finishes, the game becomes Ready and opens in the Studio. The generated game is a sandbox table — it never includes a procedures block; players resolve every rule by hand.

After the draft

Treat the first draft as exactly that. Open the Studio tour to find your way around, then refine the table on the Layout and Settings tabs — or describe changes in plain language and let the AI revise. See refining and regenerating for the refine loop and how to update a game when the schema advances.

Sign in to ask Pip about building games.
Sign in