Charts that explain the run
Bar and pie charts alongside prose — quick visual sanity checks before you ship specs to an agent.
Studio · Workspaces & run artifacts
Ship specs your coding agent can execute.
Xenonflare Studio queues work from a short brief. When generation completes, you review files, charts, and tables in the dashboard — everything organized per workspace, ready for Cursor, Copilot, or any agentic flow.
- Rich artifacts
- Charts & tables
- Markdown outputs
- Multi-file
- Scale throughput
- Parallel
- Plans & portal
- Stripe
Product surface
One results view: prompts, visuals, grids, and account controls.
Everything below is reflected in the app today, except the deeper per-run cost explorer — we call that out explicitly so you know what is live versus in flight.
Dataset tables
Structured tables (datasets) ride alongside prose — great for scores, checklists, or comparing options.
| Phase | Tokens | Status |
| Plan | 1.2k | OK |
| Build | 8.4k | OK |
| Review | 2.1k | … |
Multi-file outputs
Each completion is a library of markdown files — Frontend, Backend, agents, and more. Copy one file or the whole set.
Frontend.md●
Backend.md○
Agents.md○
Billing & plans
Upgrade with Stripe, open the customer portal for invoices, and keep terms acceptance in sync with checkout.
ProStripe
Invoices & customer portal
Cost breakdown (next)
We are wiring richer usage and spend views per workspace so you can reconcile tokens against real invoices.
Per-run economics
Deeper cost & token breakdown per workspace is on the roadmap — today you get clear tiers, limits, and billing in one place.
Flow
Three steps. No credits spreadsheet.
- 01
Describe the build
Paste a product idea, stack hints, and constraints — we queue a structured job tied to a workspace thread.
- 02
Get structured output
We turn your brief into multi-file markdown, charts, and tables you can review and copy from the dashboard.
- 03
Review in the studio
Open results: copy per-file prompts, scan charts and dataset tables, then paste into Cursor or any agentic workflow.
Why this shape
Cloud queues. Your hardware generates.
Free, Plus, and Pro
Daily message limits by tier; Plus and Pro are Stripe subscriptions with usage shown in Settings → Billing.
Keys stay local
Model calls run on hardware you control. The cloud queues work and stores outputs, charts, and tables for review.
Fair ordering
Work is processed in order with clear states from queued through complete — no mystery inboxes.
Your hardware
Run more capacity on infrastructure you control so queued work finishes faster, without sharing credentials across hosts.
Your next repo starts as one good brief.
Passwordless login, dedicated workspaces, and a results surface built for builders — not slide decks. Queue a run, skim charts and tables, then iterate until the agent output feels right.