interface futures · orchestration 101

No model pickers. No parameter sliders. Just describe the goal.

“AI should adapt to you” sounds like marketing — but there's real machinery behind intent-based interfaces. Pick a goal, press run, and watch the orchestration pipeline light up: parse → route → tools → execute. Then flip to Classic UX and count how many decisions get pushed back onto you. Drag the scene to orbit.

drag to orbit · scroll / pinch to zoom
User decisions
1

1 · State your intent

5
pipeline stages
routed model
rel. cost

2 · Orchestration log

// choose a goal and press run…

🧭Intent parsing

The first stage turns fuzzy language into structure. A classifier (often a small, fast LLM) maps “build me a website” to something like intent: create.web_app with extracted slots — audience, style, constraints. If confidence is low, good systems ask one clarifying question rather than guessing. This is the modern descendant of intent+slot NLU from voice assistants — just with LLMs doing the parsing.

🔀Model routing

Not every request deserves the biggest model. A router scores each request on difficulty, needed capabilities, latency and budget, then dispatches: translation → a fast cheap model; a research synthesis → a long-context model; data analysis → a reasoning model with code execution. Production routers can cut cost dramatically while keeping quality — you pay for the powerful model only when the request needs it.

🧰Capability & tool matching

Models alone can't ship results. The orchestrator matches the parsed intent to tools via function-calling schemas: a code generator and live preview for the website; a document parser and retrieval index for the research summary; a sandboxed Python runtime for the dataset. The model decides when to call each tool; the orchestration layer decides which tools exist and enforces permissions.

⚖️The honest tradeoffs

Intent UX trades control for simplicity. Experts lose precision (maybe you wanted that specific model or temperature); debugging is harder when routing is invisible; and cost-based routing has an incentive problem — the vendor profits when the router picks the cheap model. Good intent systems stay inspectable (show what was routed and why) and overridable (a power-user escape hatch) — exactly what the log panel here simulates.

Enjoy this tool? Build your own with Super