Skip to main contentSkip to footer
Examples and implementation patterns

Study real implementations, then adapt them to your own product

Every example page states what the code demonstrates, which principles it supports, which libraries it uses, and how it fits into the learning and certification path.

Key Facts

Examples
96
Runnable
96 runnable scripts
Browse by
Principle, runtime pattern, difficulty, library, and product problem
Libraries
pydantic, python-dotenv, openai, requests, docling, gradio, streamlit, ipykernel
Use this for
Learning patterns, comparing implementations, and preparing your own product decisions

In this section

Start here

How the example library is structured.

Open →

By problem

Find examples by the failure mode they prevent.

Open →

By runtime

Filter examples to your library or framework.

Open →

Providers & libraries

AnthropicAnthropic
OpenAIOpenAI
Google GeminiGoogle Gemini
Mistral AIMistral AI
Meta LlamaMeta Llama
CursorCursor
Where should a new learner start?

Start with examples that match the product problem you are working on: approvals, orchestration, retrieval, tool use, or background work. Then follow the linked principle pages and course material.

Use easier examples first if you are building intuition
Jump to the linked doctrine pages when you want the design rationale behind a pattern
Use more complex examples when you are preparing for implementation or certification evidence
How should a product team use this page?

Use the example index as a working implementation map. It should help teams compare patterns, understand runtime tradeoffs, and connect code references back to product behavior and trust criteria.

Filter by difficulty when teaching a team or onboarding new contributors
Filter by runtime and libraries when evaluating technical fit
Use the linked certification and course paths when examples need to become guided practice

Find the right example

If you are still hunting for the correct pattern, activation can cut the noise and point you to the most relevant example family.

Instead of browsing the whole library, activation uses your context to narrow the field and prepare the most credible route across examples, doctrine, runtime, or review.

Connects your real case to the nearest patterns
Reduces random browsing and weak comparisons
Prepares a route you can apply to your workflow
Start activationOpen overview

Course stage

Module

Models & OpenAI31

MCP14

Agents12

Frameworks10

Knowledge11

Web Context10

Workflows8

How should agents use this library?

For humans, these pages remain the inspectable editorial view. For agents, the For agents surface is the stable entry point for retrieving the same examples and linking them to the right principles.

Agent entry point

Open For agents

Use the MCP endpoint, skill pack, and rules exports to retrieve examples directly.

Open surface

Doctrine

Reconnect examples to doctrine

When a pattern looks useful, return to the principles so you understand the design judgment supporting it.

Open principles

Runtime branch

Move patterns into runtime architecture

Use the runtime architecture branch when code patterns need to become triggers, schedules, context hubs, or runtime boundaries.

Open runtime architecture

Plan mapping

See the path by plan

Check how public access, protected validation, and shared governance connect to the pricing structure.

Open pricing

From agent demos to runtime discipline

A capable model is not a runtime architecture. If agents are going to trigger workflows, load files, use tools, delegate work, and act across channels, the runtime needs clear patterns for control, visibility, and recovery. This cluster helps teams design those patterns deliberately.

Explore runtime patternsOpen principles
What makes an example page useful?

It should tell the reader what the pattern does, why it matters, and where it belongs in the learning path. A strong example page is a concrete bridge between doctrine and implementation.

What should happen after someone reads an example?

They should know which principle page to read next, which course or lab deepens the concept, and how the example might translate into their own product or workflow.