Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Plugin
Original text · EnglishA customer support plugin primarily designed for [Cowork](https://claude.com/product/cowork), Anthropic's agentic desktop application — though it also works in Claude Code. Provides ticket triage, escalation management, response drafting, customer research, and knowledge base authoring for support t
https://github.com/anthropics/knowledge-work-plugins/tree/main/customer-support
claude plugin marketplace add anthropics/knowledge-work-pluginsRepublished in full under its license, with attribution. The source is authoritative.
A customer support plugin primarily designed for Cowork, Anthropic's agentic desktop application — though it also works in Claude Code. Provides ticket triage, escalation management, response drafting, customer research, and knowledge base authoring for support teams.
claude plugin marketplace add anthropics/knowledge-work-plugins
claude plugin install customer-support@knowledge-work-plugins
This plugin turns Claude into a customer support co-pilot. It helps you:
| Command | Description |
|---|---|
/triage | Categorize, prioritize, and route a support ticket or customer issue |
/research | Multi-source research on a customer question or topic |
/draft-response | Draft a customer-facing response for any situation |
/escalate | Package an escalation for engineering, product, or leadership |
/kb-article | Draft a knowledge base article from a resolved issue |
| Skill | Description |
|---|---|
ticket-triage | Category taxonomy, priority framework (P1-P4), routing rules, duplicate detection |
customer-research | Multi-source research methodology, source prioritization, answer synthesis |
response-drafting | Communication best practices, tone guidelines, templates for common scenarios |
escalation | Escalation tiers, structured escalation format, impact assessment, follow-up cadence |
knowledge-management | Article structure standards, writing for searchability, review cadence, maintenance |
> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](CONNECTORS.md).
Connect your support platform, knowledge base, and communication tools for the best experience. Without them, provide customer context manually.
Included MCP connections:
Additional options:
You: /triage Customer says their dashboard has been showing a blank
page since this morning — they're on the Enterprise plan
Claude: Analyzing the issue...
## Triage: Dashboard blank page — Enterprise customer
**Category:** Bug
**Priority:** P2 — High (core feature broken, enterprise customer)
**Product area:** Dashboard / Frontend
### Routing Recommendation
Route to: Tier 2 Support (investigate browser/account specifics,
then escalate to Engineering if reproducible)
### Suggested Initial Response
[Draft acknowledging the issue, asking clarifying questions
about browser and any recent changes, offering status page link]
You: /research Does our platform support SSO with Okta?
Claude: Let me check across available sources...
[Searches docs, knowledge base, previous conversations,
and web sources — synthesizes answer with confidence
level and source attribution]
You: /escalate API returning 500 errors intermittently — 3
Enterprise customers reported this week
Claude: I'll gather context and build the escalation brief...
[Pulls ticket history, identifies affected accounts,
structures reproduction steps, assesses business impact,
and generates a structured escalation for engineering]
You: /draft-response Customer escalation — their integration
has been down for 2 days and they're frustrated
Claude: [Generates empathetic, professional response acknowledging
the frustration, taking ownership, providing a clear action
plan with timeline, and offering a call]
You: /kb-article How to configure webhook notifications —
just resolved this for the third customer this month
Claude: [Generates a structured how-to article with prerequisites,
step-by-step instructions, verification steps, and common
issues — optimized for search]
The plugin works out of the box with the included MCP connections. For the richest experience, connect additional data sources through your Claude settings:
Without these connections, the plugin will ask you to provide context manually and offer frameworks and templates you can fill in with your own data.
A structured output agent demonstrating Pydantic schema-based responses for customer support ticket creation.
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/openai_sdk_crash_course/2_structured_output_agent/2_1_support_ticket_agent
A tutorial demonstrating how to implement a structured customer support ticketing system using Google's ADK (Agent Development Kit) framework. This example shows how to create type-safe, structured support tickets with priority levels, categories, and resolution estimates using Pydantic schemas and
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/google_adk_crash_course/3_structured_output_agent/3_1_customer_support_ticket_agent
This Streamlit app implements an AI-powered customer support agent for synthetic data generated using GPT-4o. The agent uses OpenAI's GPT-4o model and maintains a memory of past interactions using the Mem0 library with Qdrant as the vector store.
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/advanced_ai_agents/single_agent_apps/ai_customer_support_agent
Using Tool Required for Customer Service The ChatCompletion endpoint now includes the ability to specify whether a tool must be called every time, by adding tool_choice='required' as a parameter. This adds an element of determinism to how you build your wrapping application, as you can count on a to
Sourcegithub.com/openai/openai-cookbook/blob/main/examples/Using_tool_required_for_customer_service.ipynb
Creating a Customer Service Agent with Client-Side Tools In this recipe, we'll demonstrate how to create a customer service chatbot using Claude 3 plus client-side tools. The chatbot will be able to look up customer information, retrieve order details, and cancel orders on behalf of the customer. We
Sourcegithub.com/anthropics/claude-cookbooks/blob/main/tool_use/customer_service_agent.ipynb
Curated collection of AI agent use cases across industries (incl. Customer Service, E-commerce) with links to open-source implementations, e.g. a LangGraph customer-support agent tutorial.
Sourcegithub.com/ashishpatel26/500-AI-Agents-Projects