← Back to daily report

intro.md

Changed on 2026-08-12 16:49:17 EST

+5 lines added
-5 lines removed
Visual Diff
---¶
title: Intro to Claude¶
url: https://platform.claude.com/docs/en/intro¶
description: Claude is a highly performant, trustworthy, and intelligent AI platform built by Anthropic. Claude excels at tasks involving language, reasoning, analysis, coding, and more.¶
---¶

<Tip>¶
The latest generation of Claude models:¶

**Claude Fable 5** - Next-generation intelligence for long-running agents. Read the [Claude Fable 5 and Claude Mythos 5 announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5).¶

**Claude Mythos 5** - Shares Claude Fable 5's capabilities without the safety classifiers. Available in limited release through [Project Glasswing](https://anthropic.com/glasswing).¶

**Claude Opus 5** - For complex agentic coding and enterprise work. Read the [Claude Opus 5 announcement](https://www.anthropic.com/news/claude-opus-5).¶

**Claude Sonnet 5** - Frontier intelligence at scale, built for coding, agents, and enterprise workflows. Read the [Claude Sonnet 5 announcement](https://www.anthropic.com/news/claude-sonnet-5).¶

**Claude Haiku 4.5** - Fastest model with near-frontier intelligence. Read the [Claude Haiku 4.5 announcement](https://www.anthropic.com/news/claude-haiku-4-5).¶
</Tip>¶

<Note>¶
Looking to chat with Claude? Visit [claude.ai](https://claude.ai).¶
</Note>¶

Anthropic offers two ways to build with Claude, each suited to different use cases:¶

| | Messages API
| Claude Managed Agents |¶
| -------------- | -------------------------------------------
----------------------------------------------------- | ---------------- | ------------------------------------------------------------------------- |¶
| **What it is** | Direct model prompting access
| Pre-built, configurable agent harness that runs in managed infrastructure |¶
| **Best for** | Custom agent loops and fine-grained control
| Long-running tasks and asynchronous work |¶
| **Learn more** | [
|¶

To learn more about each, see [Using the
Messages API docs](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) |and the [Claude Managed Agents docsoverview](https://platform.claude.com/docs/en/managed-agents/overview) |.

## Recommended path for new developers¶

Follow these steps to go from zero to a working Claude integration.¶

<Steps>¶
<Step title="Make your first API call">¶
Set up your environment, install an SDK, and send your first message to Claude.¶

[Go to the quickstart](https://platform.claude.com/docs/en/get-started)¶
</Step>¶

<Step title="Secure your credentials">¶
Set an expiration when you create your API key. Keep the key out of source control, client-side code, and prompts. Check whether your workload can use Workload Identity Federation instead of a static key.¶

[Read the authentication guide](https://platform.claude.com/docs/en/manage-claude/authentication)¶
</Step>¶

<Step title="Understand the Messages API">¶
Learn the core request and response structure, including multi-turn conversations, system prompts, and stop reasons.¶

[Read the Messages API guide](https://platform.claude.com/docs/en/build-with-claude/working-with-messages)¶
</Step>¶

<Step title="Choose the right model">¶
Compare Claude models by capability and cost to pick the best fit for your use case.¶

[See the models overview](https://platform.claude.com/docs/en/about-claude/models/overview)¶
</Step>¶

<Step title="Explore features and tools">¶
Discover what Claude can do: extended thinking, web search, file handling, structured outputs, and more.¶

[Browse the features overview](https://platform.claude.com/docs/en/build-with-claude/overview)¶
</Step>¶
</Steps>¶

***¶

## Develop with Claude¶

Anthropic provides developer tools to help you build and scale applications with Claude.¶

<CardGroup cols={3}>¶
<Card title="Developer Console" icon="computer" href="https://platform.claude.com/">¶
Prototype and test prompts in your browser with the Workbench.¶
</Card>¶

<Card title="API Reference" icon="code" href="https://platform.claude.com/docs/en/api/overview">¶
Explore the full Claude API and client SDK documentation.¶
</Card>¶

<Card title="Claude Cookbook" icon="chef-hat" href="https://platform.claude.com/cookbook">¶
Learn with interactive Jupyter notebooks covering PDFs, embeddings, and more.¶
</Card>¶
</CardGroup>¶

***¶

## Key capabilities¶

Claude can assist with many tasks that involve text, code, and images.¶

<CardGroup cols={2}>¶
<Card title="Text and code generation" icon="text-aa" href="https://platform.claude.com/docs/en/build-with-claude/overview">¶
Summarize text, answer questions, extract data, translate text, and explain and generate code.¶
</Card>¶

<Card title="Vision" icon="image" href="https://platform.claude.com/docs/en/build-with-claude/vision">¶
Process and analyze visual input and generate text and code from images.¶
</Card>¶
</CardGroup>¶

***¶

## Support¶

<CardGroup cols={2}>¶
<Card title="Help Center" icon="help" href="https://support.claude.com/en/">¶
Find answers to frequently asked account and billing questions.¶
</Card>¶

<Card title="Service Status" icon="chart" href="https://status.claude.com">¶
Check the status of Anthropic services.¶
</Card>¶
</CardGroup>¶

Unified Diff

--- a/intro.md
+++ b/intro.md
@@ -24,11 +24,12 @@
 
 Anthropic offers two ways to build with Claude, each suited to different use cases:
 
-|                | Messages API                                                                                     | Claude Managed Agents                                                                     |
-| -------------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------- |
-| **What it is** | Direct model prompting access                                                                    | Pre-built, configurable agent harness that runs in managed infrastructure                 |
-| **Best for**   | Custom agent loops and fine-grained control                                                      | Long-running tasks and asynchronous work                                                  |
-| **Learn more** | [Messages API docs](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) | [Claude Managed Agents docs](https://platform.claude.com/docs/en/managed-agents/overview) |
+|                | Messages API                                | Claude Managed Agents                                                     |
+| -------------- | ------------------------------------------- | ------------------------------------------------------------------------- |
+| **What it is** | Direct model prompting access               | Pre-built, configurable agent harness that runs in managed infrastructure |
+| **Best for**   | Custom agent loops and fine-grained control | Long-running tasks and asynchronous work                                  |
+
+To learn more about each, see [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the [Claude Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview).
 
 ## Recommended path for new developers