How to Produce Stakeholder Podcasts Using AI

I turned 50+ pages of insights on 10 accounts into a 15 minute podcast using NotebookLM and ZoomInfo AccountAI. Here's how I was able to do it: The problem hit me last week. I was headed to dinner with a bunch of customers. Like many GTM leaders, I was staring at a mountain of account insights for dinner. Years ago, this meant frantically scanning Salesforce mobile in an Uber (which never worked). But the world has changed. The explosion of GTM data has created a new challenge. Between CRM records, ZoomInfo insights, earnings transcripts, intent signals and support tickets—we're drowning in information. The best reps somehow find time to synthesize all of this. The rest just wing it. At ZI Labs, we've been experimenting with using AccountAI to reimagine account summaries and meeting prep. The goal? Transform mountains of data into personalized briefings you can consume anywhere. Here's what we did: First, we aggregated everything:  📊 Account summaries  📝 Recent earnings call transcripts  🎯 Buyer intent signals  🔄 Customer support interactions  💼 CRM opportunity history  📧 Historical email/meeting notes Then we let AccountAI do the heavy lifting:  🧠 Extract strategic priorities  🔍 Surface competitive insights  ❗ Identify shared pain points  🎯 Map product-market fit signals  📈 Highlight recent org changes  🔢 Calculate propensity scores Finally, NotebookLM transformed this into audio:  🎧 Natural conversational flow  ⭐ Prioritized by relevance  🔄 Context preserved  💬 Key quotes included  📝 Clear narrative structure The result? A 15-minute personalized podcast covering everything I needed to know about all 16 accounts attending dinner. I listened to it on the way to dinner. No prep required. This feels like the future of GTM intelligence. The days of "winging it" are over. Every rep should have their daily meetings, accounts and opportunities summarized into audio briefs they can consume anywhere (this extends to every profession, but sales will be first). Think about it—your calendar automatically generating custom podcasts with everything you need to know about upcoming meetings. Your opportunities summarized with competitive insights and next steps. While you drive to work. 🤯 This isn't science fiction. We're doing it today. PS - Huge thanks to Millie Beetham who helped architect this. And to Henry Schuck for always pushing us to reimagine what's possible with AI + GTM data. DM me if you want the full podcast. It’s incredible. 

If you're only using AI to generate content, you're missing out. The real power? AI-powered processes. For example, I built a CustomGPT called MyShowrunner to streamline my podcast preproduction. It follows a step-by-step workflow I used to do manually: 👉 Researches the guest 👉 Finds unique angles for the episode 👉 Generates compelling headlines 👉 Drafts insightful questions What used to take me 45-60 minutes now takes 5-10 minutes. It’s not just automation—it’s collaboration. AI doesn’t replace me; it supercharges my workflow (with my guidance). The biggest AI wins come from optimizing repeatable processes. What’s a process in your work that AI could streamline? #danchez I teach marketers how to leverage AI to go faster, build better, & think smarter without the hype. PS - If you want to build your own MyShowrunner for your podcast or just see how it was created, you can get the instructions for free at MyShowrunner[dot]com

I built a research assistant to streamline my podcast preparation process. For each episode, I create a research brief with my insights, guest background, topic context, and potential questions. This involves researching the guest and their company, reviewing their podcasts, reading their blog posts, and diving into the discussion topic—quite a time-consuming and effort-intensive process. To save time, I built an agent to handle this work. The project also showcases how to design an event-driven AI architecture, decoupling AI workflows from the app stack, leveraging event streams for data sharing and orchestration, and incorporating real-time data. It's built with: ◆ OpenAI various versions of GPT and Whisper ◆ LangChain for prompt templates and LLM API abstraction ◆ Next.js by Vercel ◆ Kafka and Flink on Confluent Cloud for agent orchestration and stream processing ◆ Bootstrap and good ol' fashion hand coded CSS for styling Behind the scenes: 1. Create a podcast research bundle with the guest name, topic, and source URLs 2. The web app writes the research request to an application database 3. A source connector pulls the data into a Kafka topic and kick starts the agentic workflow 4. All URLs are processed, text is chunked, and embeddings created and synced to a vector database 5. Flink and GPT is used to pull potential questions from the source materials 6. A secondary agent compiles all the research material into a research brief I cover this in detail here: https://lnkd.in/gSSBuC3t You can checkout the code here: https://lnkd.in/gUpY-YgQ #llms #agenticai #kafka #flink #confluentcloud