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.
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
FAQ-library first-line info@ assistant.
Sourcebotsdots.site/templates/faqt
Keep enablement current from real calls. Tracks questions, timestamps answers, and links back to the source recording.
Sourcebotsdots.site/templates/call-faq-miner
Sorts your support inbox, drafts replies in your voice, builds an FAQ from repeat questions, and watches for churn signals
Sourcebotsdots.site/templates/customer-support-desk
Flags urgent support tickets, drafts replies from your docs, and turns gaps into help-article drafts; never sends
Sourcebotsdots.site/templates/ticket-desk
Read the required skills, prompts and standards in order.
Draft a knowledge base article from a resolved issue or common question. Use when a ticket resolution is worth documenting for self-service, the same question keeps coming up, a workaround needs to be published, or a known issue should be communicated to customers.
Sourcegithub.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/kb-article/SKILL.md
Designed for businesses and support teams that need calm, professional responses to unhappy customers without escalating tension. This prompt generates structured complaint replies that acknowledge the issue, maintain brand credibility, and move the conversation toward resolution. Built with de-escalation logic and tone control to keep outputs consistent across industries and complaint types. The final response is…
Sourceprompts.chat/prompts/cmp3infd60004kv04amyiigtj_customer-complaint-reply-system
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
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
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