> Executable examples and use cases for learning Tactus by running real procedures.

Canonical: https://tactus.anth.us/examples/

::band{size="hero" eyebrow="Examples"}
# Learn by Running Real Procedures

Tactus is designed for executable, verifiable workflows. Examples are the fastest way to learn: read a procedure, run it, then iterate with validation, specs, and evaluations as your guardrails.

::band{tone="muted"}
## Start with Use Cases

Use cases are the quickest way to see what you can build with Tactus. Start with the first two walkthroughs, then browse the rest.

:::card-grid{columns=3 label="Use case highlights"}
:::card{title="A copilot for anything"}
Embed agents in your app: chat UX, real tools, and explicit human checkpoints before side effects.

[Read](/use-cases/copilot-anything/)
:::

:::card{title="Text classification"}
A simple, high-signal workflow: route messy text into an explicit label set with guardrails.

[Read](/use-cases/text-classification/)
:::

:::card{title="More use cases"}
Browse the complete list, including business process automation and Level Zero Operators.

[Browse](/use-cases/)
:::
:::

::band
## Explore the Examples Library

Runnable, tested examples organized progressively from basics to advanced topics. Each example includes embedded specifications and can be executed directly.

:::card-grid{columns=3 label="Example chapters"}
:::card{title="Getting Started"}
Welcome to Tactus! This chapter introduces the fundamental concepts of the Tactus programming language through simple, self-contained examples.

*5 examples*

[Browse chapter →](/examples/getting-started/)
:::

:::card{title="Agents"}
This chapter focuses on working with AI agents in Tactus - the core abstraction for interacting with language models.

*3 examples*

[Browse chapter →](/examples/agents/)
:::

:::card{title="Classification"}
Real-world classification patterns: route messy text into a small, explicit set of labels.

These examples are designed to run in mock mode (fast, deterministic) and also in real mode (with API keys and/or optional ML dependencies) so you can iterate safely.

*5 examples*

[Browse chapter →](/examples/classification/)
:::

:::card{title="Human-in-the-Loop (HITL)"}
Patterns for integrating human decision-making into AI workflows. These examples show how to request human input, approval, and feedback during procedure execution.

*2 examples*

[Browse chapter →](/examples/human-in-the-loop/)
:::

:::card{title="Standard Library"}
This chapter explores Tactus's built-in standard library - utilities and primitives that make it easier to build robust AI workflows.

*3 examples*

[Browse chapter →](/examples/standard-library/)
:::

:::card{title="Specifications"}
This chapter covers behavior-driven development (BDD) with Tactus specifications - embedded tests that validate your AI workflows.

*3 examples*

[Browse chapter →](/examples/specifications/)
:::

:::card{title="Evaluations"}
This chapter explores Tactus evaluations - quantitative assessments of AI workflow performance across datasets.

*3 examples*

[Browse chapter →](/examples/evaluations/)
:::

:::card{title="Advanced Features"}
This chapter covers advanced Tactus capabilities for building sophisticated AI workflows with tools, composition, and external integrations.

*0 examples*

[Browse chapter →](/examples/advanced-features/)
:::
:::

### Also Explore

:::card-grid{columns=3 label="Also explore"}
:::card{title="Examples on GitHub" icon="svg-github"}
Clone the repository, run examples locally, and see the continuous integration tests in action.

[Open the repository](https://github.com/AnthusAI/Tactus-examples)
:::
:::

If you're new, start with [Guiding Principles](/guiding-principles/), then learn the guardrails stack: [validation](/validation/), [behavior specifications](/specifications/), and [evaluations](/evaluations/).

::band{columns="cta"}
## Ready to run your first procedure?

Start with a minimal workflow, then add guardrails as you iterate.

::button{href="/getting-started/" label="Get Started" size="lg"}
