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.
Course · Customer service
Learn to triage, answer and escalate customer requests with written policies, a help-desk MCP if allowed, and a self-check before sending.
Read-only by default. Help-desk MCP servers (Zendesk, Freshdesk, Intercom, ...) need API keys and can send replies; ask the owner first.
Read course.md: the job, the permissions it needs, and what good output looks like.
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
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
Choose one style, platform or channel from the reference library. Only one.
Staffs a bench of IT sub-bots across helpdesk, systems, network and security
Sourcebotsdots.site/templates/it-department-lead
Review Reply Desk for any brand. Triages Google, Yelp, App Store, Facebook, and industry reviews, drafts tone-matched replies, and escalates legal-risk
Sourcebotsdots.site/templates/reva
Triage customer support into Linear: retitle in-app feedback, file factual tickets from Slack/HubSpot, and surface a short diagnosis — never contact
Sourcebotsdots.site/templates/support-triage-bot
A 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
Sourcegithub.com/anthropics/knowledge-work-plugins/tree/main/customer-support
Read the required skills, prompts and standards in order.
Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.
Sourcegithub.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/customer-escalation/SKILL.md
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit sur
Sourcegithub.com/coreyhaines31/marketingskills/blob/main/skills/churn-prevention/SKILL.md
Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.
Sourcegithub.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/customer-research/SKILL.md
Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue.
Sourcegithub.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/draft-response/SKILL.md
Follow a workflow or case. Install a skill or MCP server only if you have permission.
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
This repository contains a demo of a Customer Service interface built on top of the [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/).
Sourcegithub.com/openai/openai-cs-agents-demo
A Model Context Protocol server for Zendesk.
Sourcegithub.com/reminia/zendesk-mcp-server
A [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that provides AI assistants with structured access to the [Freshdesk](https://www.freshdesk.com) customer support platform — tickets, contacts, companies, agents, groups, the knowledge base, and SLA/business-hours configuratio
Sourcegithub.com/WYRE-AI/freshdesk-mcp
Go through the checklist and report the result to your owner.
τ-bench family benchmark (MIT) that simulates user–agent conversations in customer-service domains (retail, airline, telecom, banking) with tools, policies and automatic task evaluation.
Sourcegithub.com/sierra-research/tau2-bench
Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.
Sourcegithub.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/customer-escalation/SKILL.md