Creating an AI System with Gong Transcripts

Hello,

This is Simon with the latest edition of The Weekly. In these updates, I share key AI related stories from this week's news, list upcoming events, and share any longer form articles posted on the website.

If you've joined an online call recently, on Zoom or Teams, you'll have noticed at least one recording bot joining alongside you. Tools like Gong, Otter, and Fireflies are now everywhere. They listen, transcribe, and summarise your meetings automatically for you.

The problem with these tools though is that most of them tools are built for salespeople. The summaries they produce are optimised for tracking deals, not for the rest of us. If you're in Operations, Finance, or Project Management and you want to extract something useful, you're left scrolling through pages of transcript trying to find the bits that matter to you.

But there's a solution to this, and it’s something you can set up yourself quite easily.

Every one of these tools gives you access to the full written transcript and that text can be copied and pasted elsewhere.

Before you just paste this in ChatGPT, make sure you know which AI tools you're allowed to use at work. Many companies now have an approved generative AI solution, with MS Copilot and Google Gemini among the most common, ensuring that no data leaves your corporate environment.

Instead of just pasting the transcript into ChatGPT and asking a question, you should consider using something like the Google Gem feature where you can instruct it with a system prompt tailored to your role:

"You are analysing customer call transcripts from Gong. Your job is to extract insights relevant to an Operations Manager. Specifically, extract: 1) Implementation Timeline, 2) Resource Requirements, 3) Key Risks, 4) Deliverables. Format as a numbered list with action items in bold."

A real advantage here, is that people in different roles can create their own Gems and write their own instructions, all using the same call transcript. And because a Gem can be shared, your whole team benefits.

Sarah in Finance configures her version to extract deal size and contract terms. Mark in Project Management configures his to pull out timelines and owners. Everyone pastes the same Gong transcript and gets a role-specific extraction in seconds.

You might be wondering if you have the technical ability to create your own Gem. Here's the good news: if you can write down exactly what information you want from a call, you can instruct a Gem to find it.

Think about the last call you were on. What were the points, facts, and action items you scribbled down? That list is your system prompt. Turn it into a Gem, and you'll get that information quickly and easily from every call you're on.

Connect your email, and you’ll instantly get a CRM with enriched customer insights and a platform that grows with your business.

With AI at the core, Attio lets you:

Join industry leaders like Granola, Taskrabbit, Flatfile and more.

👉 Try Attio Pro for free

Exclusive for subscribers.

In this section, I’m going to bring to you a real world example of AI use. This week, we take a look at UK insurance giant, Aviva.

OpenAI has started a global rollout of a new ChatGPT feature that estimates a user’s age to help keep minors safe when “adult mode” launches later this year. The feature will be introduced in the EU soon and comes as part of wider changes including ads and expansion of services.

Why this matters: It shows how major AI platforms are balancing safety with monetisation and regulatory pressures in 2026.

Here in the UK, a cross-party group of MPs has urged financial regulators to introduce AI-specific stress tests for banks and insurers, warning that opaque algorithms and AI-driven fraud could harm consumers and markets.

Why this matters: As AI becomes part of everyday financial decision-making, governments are realising old rules aren’t enough and stronger safeguards may affect businesses and customers alike.

A key panel in the U.S. House advanced a bill to give Congress authority over exports of AI chips — a central component for training and running advanced AI models — amid geopolitical concerns about technology leadership and national security.

Why this matters: Controlling the flow of AI hardware could influence which countries lead the next wave of innovation

Thanks for reading, and see you next Friday.

Simon,

Was this email shared with you? If so subscribe here to get your own edition every Friday.

Enjoying Plain AI? Share it and get a free gift!

If you find this newsletter useful, why not share it with a couple of friends or colleagues who would also benefit? As a special thank you, when two people subscribe using your unique referral link, I’ll send you my "Exclusive Guide: Supercharge Your Work with NotebookLM." It’s a practical, no-nonsense guide to help you turn information overload into your secret weapon.

You can also follow me on social media: