Build and deploy an inference.sh app from a conversation — scaffold, implement, test, deploy, and configure pricing. Use when the user says 'appify', 'make an app', 'deploy this as an app', or when a working API integration, model wrapper, or processing pipeline should become a reusable cloud app.
Build and deploy an inference.sh flow — chain multiple apps into a pipeline with wired inputs/outputs. Use when the user says 'flowify', 'make a flow', 'chain these apps', 'build a pipeline', or when multiple apps should run in sequence with outputs feeding into inputs.
Build and deploy a custom AI agent on belt — define purpose, model, tools, system prompt, and deploy as a reusable agent. Use when the user says 'agentify', 'make an agent', 'create an agent', 'build a bot', or wants to turn a workflow into a deployed agent with tools.
Install and set up belt — the cloud platform CLI for AI agents
Run a simulated expert panel on a strategic question — brief 4-8 named experts in parallel, synthesize into consensus table
Search and run 250+ AI apps — image generation, video, TTS, web search, LLMs
Save and recall knowledge — discoveries, insights, references, preferences
Search, use, install, and publish skills from the belt registry