Use this matrix before prompting a model or designing an agent workflow. The
machine-readable source for the public release state is
ai-capabilities.json.
| Capability | State | What is allowed |
|---|---|---|
| Copilot Ask | Released | Read-only answers about the open chart |
| New conversation | Released | Start with fresh conversation context; chart is unchanged |
| Coding-agent docs and toolkit | Released | Help implement SeatLayer in a repository using canonical docs |
| Designer MCP | Released | Design charts and set up events through OAuth, on one chart or one workspace. No holds, bookings, or payments |
| Copilot Edit | Released | Apply a reviewable revision to the open chart; publishing remains separate |
| Multistep chart creation | Released | Create a reviewable draft from written requirements; never publish automatically |
| Photo/reference creation | Released | Use a plan or reference image as input while disclosing uncertainty; never infer authoritative inventory |
| AI-led 3D improvement | Off | Do not claim automatic height or 3D improvement |
Authority does not move into the model
| Concern | Authority |
|---|---|
| Authentication, role, workspace, and chart scope | SeatLayer API |
| User confirmation and publish permission | SeatLayer API and human reviewer |
| Tool availability and spend limits | SeatLayer product configuration |
| Chart writes and canonical revision | SeatLayer chart service |
| Idempotency, retry, and conflict handling | SeatLayer execution records |
| Validation and rendered evidence | SeatLayer validators and renderers |
| Usage, billing, and terminal state | Canonical SeatLayer records |
| Narrative explanation and proposed plan | Copilot or connected model |
A model cannot authorize itself, invent a user confirmation, mark an action complete, or publish by returning a persuasive message.
Operating safeguards for write capabilities
Released Edit and Create workflows keep these safeguards:
- exactly-once or safely idempotent execution across retries and resumed runs;
- revision conflict detection and a full-scope rollback plan;
- renewed authorization and kill-switch checks when a run resumes;
- deterministic completion validation against the canonical chart;
- visible entitlement, token/model, rendering, and workspace spend controls;
- privacy rules for prompts, references, traces, evidence, and retention; and
- repeated real-user validation across representative chart types.
AI-led 3D also needs actual WebGL before/after evidence from the same chart revision on desktop and mobile, plus a complete 2D fallback.
Continue with Copilot overview, connect Codex, or Designer MCP.