# Perceivo
> A governed operating layer for reusable AI components, orchestrations, infrastructure, and intelligence.
Documentation: https://perceivo.ai/docs/

## University

- [Why Components](https://perceivo.ai/registry/film/comp-01-why-components.md): Why split an orchestration into components: one big script cannot tell you which part made the answers worse.
- [From Experiment to Production](https://perceivo.ai/registry/film/infra-01-experiment-to-production.md): What production needs beyond an experiment, and how Perceivo keeps compute, services, storage and secrets together.
- [A Tour of Intelligence](https://perceivo.ai/registry/film/intel-01-tour-of-intelligence.md): What an intelligence is, and how its pipeline runs from features and drift to training, evaluation and serving.
- [How Perceivo Orchestrates](https://perceivo.ai/registry/film/orch-01-how-perceivo-orchestrates.md): Why Perceivo builds a workflow from swappable components, and why that matters once a step uses a language model.
- [A Tour of Orchestrations](https://perceivo.ai/registry/film/orch-02-tour-of-orchestrations.md): Walk the Orchestrations list, open one in the Builder, and see how nodes, ports and Roles fit together.
- [Import, Export and Lifecycle](https://perceivo.ai/registry/film/orch-03-import-export-lifecycle.md): Import an orchestration as a draft, bind its secret, save a version from the File menu, then export it again.
- [Components and Connection Rules](https://perceivo.ai/registry/film/orch-04-components-and-connection-rules.md): The three parts of a component, and the eight primitives with the rules for what each one connects to.
- [Building a Component](https://perceivo.ai/registry/film/orch-05-building-a-component.md): Create a tool in the component wizard, declare its typed ports, and let Perceivo check the script against them.
- [The Feedback Loop](https://perceivo.ai/registry/film/cap-01-the-feedback-loop.md): A capability bundles orchestrations that share an input and output, serves them at scale and benchmarks them live.

## Examples

- [Ask an Expert](https://perceivo.ai/registry/example/ask-an-expert.md): Send a profession and a question; a ChatGPT agent answers the way that professional would.
- [Finish Any Story](https://perceivo.ai/registry/example/finish-any-story.md): Type the opening of a story and a Claude agent writes the ending, as an artifact.
- [Production Line](https://perceivo.ai/registry/example/production-line.md): An agent sends a work order down a line of four tools, each doing its stage, with no model.