Make AI agents your unfair advantage

Make AI agents your unfair advantage

With Claude, you can build AI agents that plan, act, and collaborate more effectively.

Start building
Contact sales
logologo
logologo
logologo
logologo
logologo
logologo
logologo
logologo
logologo
logologo

Powerful, collaborative, and safe AI agents

Get superior reasoning and human-quality responses.

Best model for AI agents

Claude outperforms other models in AI agent scenarios from customer support to coding.

AI agents with a human touch

Claude’s conversational style leads to true collaboration between AI agents and users.

AI that protects your brand

Claude ranks highest on honesty, jailbreak resistance, and brand safety.

Building effective agents

What the Anthropic Engineering team has learned from working with customers and building agents ourselves.

Read more
3x

Reduction in code churn

Prev
Next

Build AI agents with the Claude Developer Platform

Integrate Claude’s powerful AI capabilities into your apps and deliver production-grade agents faster.

View prompt

You are an AI assistant specialized in classifying customer support tickets. Your task is to analyze the content of a given ticket and assign it to the most appropriate category from a predefined list. You will also provide reasoning for your classification decision.

First, let's review the available categories:

<category_list>
{{CATEGORY_LIST}}
</category_list>

Now, here is the content of the support ticket you need to classify:

<ticket_content>
{{TICKET_CONTENT}}
</ticket_content>

Please follow these steps to complete the task:
– Carefully read and analyze the ticket content.
– Consider how the content relates to each of the available categories.
– Choose the most appropriate category for the ticket.
– Provide a detailed explanation of your reasoning process.

Use the following structure for your response:
<classification_analysis>
In this section, break down your thought process:
– Quote the most relevant parts of the ticket content.
– List each category and note how it relates to the ticket content.
– For each category, provide arguments for and against classifying the ticket into that category.
– Rank the top 3 most likely categories.
</classification_analysis>

<classification>
<category>Your chosen category goes here</category>
<reasoning>A concise summary of your reasoning for choosing this category</reasoning>
</classification>

Remember to be thorough in your analysis and clear in your explanation. Your goal is to provide an accurate classification with well-supported reasoning.

Deliver more effective
AI agents

  • Build agents and workflows with our API
  • Test and refine prompts in the Workbench
  • Build frontier capabilities into your agents
  • Empower any developer to build AI agents

Collaborate with Claude on coding tasks

Claude Code is an agentic tool where developers work with Claude directly from their terminal—delegating tasks from code migrations to bug fixes.

Learn more

See why industry leaders
choose Claude

Start building
See customer stories

“Claude Sonnet 4.5 amplifies GitHub Copilot's core strengths. Our initial evals show significant improvements in multi-step reasoning and code comprehension—enabling Copilot's agentic experiences to handle complex, codebase-spanning tasks better. We expect these gains to deliver meaningful value to developers moving from idea to implementation with confidence.”

Mario Rodriguez, Chief Product Officer

“Notion Agent saves our customers time by completing complex, multi-step workflows directly in their workspace. In testing, Claude Sonnet 4.5 showed meaningful improvements in reasoning, planning, and adapting, with precise instruction-following that makes Notion Agent feel truly personal. This foundation enables more reliable AI teammates that can independently execute complex, multi-step tasks, and deliver results in the tone and style you need.”

Sarah Sachs, AI Engineering Lead

“Sonnet 4.5 represents a new generation of coding models. It's surprisingly efficient at maximizing actions per context window through parallel tool execution, for example running multiple bash commands at once. We've also noticed it spontaneously writing and executing unit tests to validate its own work, making our parallel Cascade runs way more effective.”

Jeff Wang, CEO

Everything you need to 
succeed with Claude

Start building