Apps

Apps are tools that do one thing well.

What's an app?

An app takes input, does something, and returns output.

Examples:

• stable-diffusion — prompt in, image out
• whisper — audio in, text out
• summarize — long text in, short text out
• router (decision) — state plus typed questions in, probability per answer out

Inputs and outputs

Every app has a schema:

1stable-diffusion2├── Input3│   ├── prompt (text, required)4│   ├── style (text, optional)5│   └── size (choice, optional)6└── Output7    └── image (file)

The schema tells you what to provide and what you'll get back.

Decision apps

Decision apps answer structured questions about a piece of state (and optionally images or videos) and return a probability distribution over each answer — not generated media. Set category: decision in inf.yml (Configuration — Categories).

The wire contract matches the generated SDK types DecisionInput / DecisionOutput (and DecisionVisionInput when images are included, or DecisionVideoInput when videos are included as well; the Python helper ships in inferencesh ≥ v0.23.0). Question kinds:

Each question has an id (your key), instructions (what the model should consider), and kind-specific fields (options for choices, levels for scores, optional criteria for nouls). state is arbitrary JSON the model reads alongside the questions. Vision models add images — file URIs every question can see.

Example input:

1{2  "state": { "ticket": "Payment failed after card update", "channel": "email" },3  "choices": [4    {5      "id": "intent",6      "instructions": "What is the customer trying to do?",7      "options": [8        { "name": "refund", "description": "Get money back" },9        { "name": "retry", "description": "Retry the charge" }10      ]11    }12  ],13  "nouls": [14    {15      "id": "urgent",16      "instructions": "Does this need same-day handling?",17      "criteria": { "true": "Same-day SLA applies", "false": "Standard queue" }18    }19  ]20}

Example output (shape every decision app returns):

1{2  "choices": {3    "intent": {4      "choice": "retry",5      "confidence": 0.72,6      "probabilities": { "refund": 0.28, "retry": 0.72 }7    }8  },9  "nouls": {10    "urgent": { "noul": 0.41 }11  },12  "scores": {},13  "model": "myteam/support-router",14  "input_tokens": 184215}

• Choice answers include the highest-probability choice, confidence, and probabilities for every option name.
• Score answers include score (0 through the top level index), normalized (0–1), confidence, per-level probabilities, and a legend mapping level numbers to descriptions.
• Noul answers expose noul as the probability the statement is true.

Run decision apps like any other app (client.tasks.create, Flows, or the workspace UI). TypeScript types: JavaScript SDK — Decision app types.

Where apps come from

Each app has a category (for example image, chat, or decision for the shared decision contract) and optional tags — lowercase slugs such as text-to-image or open-weights that describe what it does and how it behaves. Tags feed search and store listings. → Configuration — App tags · Apps API

Apps vs connector tools: The Grid is the library of runnable apps (each with typed inputs and outputs). Agents can also call external integrations (Gmail, Slack, Linear, and more) as connector tools — see Tool Orchestration and Connectors.

How to use apps

1. Directly — Run from the workspace UI
2. In Flows — Chain with other apps
3. As Agent Tools — Let agents call them
4. Via API — Run programmatically

Creating Apps

You can create your own apps using Python. An app consists of:

1. inference.py — The code
2. inf.yml — Configuration

Code Structure

1class AppSetup(BaseAppInput):2    """Static configuration (restart required)"""3    model_name: str45class AppInput(BaseAppInput):6    """Request arguments (per run)"""7    prompt: str89class App(BaseApp):10    async def setup(self, config: AppSetup):11        # Load heavy resources12        pass1314    async def run(self, input: AppInput):15        # Process request16        pass

Next

→ Tasks