AI should empowerpeople, not replace us.

A mistake I often see from people new to Generative AI is mixing up a chatbot with an agent. A chatbot just talks to you, while an agent can actually take action. If you’ve ever used a support bot that keeps apologizing but never checks your account, you know what I mean. Real industry solutions need AI that can think, get real-time data, and know when to let a human step in. I recently built a fully functional customer support AI agent using LangGraph.

In this article, I’ll show you how I built it. We’ll go over the architecture, state management, tool use, and how to hand things off to a human.

Train Fin to support your customers—just like your best agent.

Fin Guidance lets you train Fin to speak in your brand’s voice, follow your policies, and handle conversations the way you want—using simple, natural-language instructions.

This means faster resolution times, more consistent support quality, and a better customer experience.

You can set clear rules for what Fin should say and do, from using the right content and terminology to escalating sensitive issues.

Built-in reporting shows how well Fin is following your guidance, with AI-powered suggestions to help you fine-tune responses over time.

Zendesk is excited to announce the early access program (EAP) for AI-powered action flow creation with admin copilot. This feature lets admins generate complete, production-ready action flows using plain-language prompts in admin copilot. No coding or deep technical expertise required.

Admin copilot can now generate entire action flows from a natural-language description. Simply describe what you want to automate, and the AI builds the flow, including triggers, first-party Zendesk actions, third-party connector steps, custom actions, and custom code steps, directly in the action builder. You can then review, edit, test, and activate the flow without writing a single line of code.

hireEZ rebuilds its entire platform on agents. What your best recruiter knows, your whole team gets. The boring half of the job disappears, and the hunt and the close come back. See it live on stage at SpeakEZ Summit on August 27.

The power of PCRecruiter is getting a massive upgrade: we are bringing the Model Context Protocol (MCP) directly to your recruitment database.

Every recruiter knows the hassle; you need information, a report, a change to the data, or even a complex custom workflow, and you need it quickly. Often that means having to build a search query, run an export, create a spreadsheet, develop an integration, or countless other uses of precious time you'd rather spend talking to clients and candidates.