A buyer needs to make a purchase to they open an AI chat window and ask for recommendations. The AI comes back with four companies, each with their pros and cons, ultimately recommending one for their business. The buyer reaches out.

More purchases start this way now. In G2's March 2026 survey of 1,076 software buyers, 51% said they begin research in an AI chatbot more often than in Google, up from 29% in April 2025. Sixty-nine percent chose a different vendor than they'd planned based on a chatbot's guidance, and a third bought from a vendor they'd never heard of. For a young company, that last number is an opening. It also raises a question founders keep asking us: what is AI saying about us? We built Overheard AI to answer it, and we've released it free and open source.

One response tells you very little

The obvious test is to ask ChatGPT yourself. The trouble is that AI is probabilistic so the answer changes each time you ask. SparkToro and Gumshoe had 600 volunteers run the same prompts nearly 3,000 times. They found less than a 1 in 100 chance that ChatGPT or Google's AI returns the exact same list of brands twice in 100 answers, and the order repeated even less often.

What did hold up though, was how often a brand appeared across many answers. That matched what we'd seen building visibility trackers for our partners. One screenshot of an AI answer can make you feel great or terrible, but it's not really indicative of what buyers are seeing. That's why we built Overheard AI never to report a single answer. Every number it shows is an aggregate across LLMs and iterative prompting.

What it measures

You describe your brand, pick the questions your buyers ask and choose the AI providers. Overheard AI asks each question several times to each, with web search on for every answer, and stores the full response. A second, cheaper call reads each answer back and records the brands it named, their place in any ranked list and the sites it linked.

The dashboard shows how often you're mentioned, how often you make the top three and how often your site is cited, next to your competitors. Brands you didn't list but the assistants keep naming show up as discovered competitors. The app also asks each LLM what it knows about you and sums that up in four parts: what you do, who buys from you, what you're known for and what people criticize.

It runs on your machine

Overheard AI runs on your own computer with your own API keys for OpenAI, Anthropic or Google. Every answer is stored in one SQLite file that you own. There's no account and no hosted service, and nothing leaves your machine except the calls to the providers you have keys for.

Each answer takes two calls on your keys, one to ask and one cheaper one to parse the results. Before a run starts, the app shows the planned calls and an estimated cost. Treat that as a rough figure, since the number of web searches varies, and treat your provider's billing page as the real one.

One limit is worth knowing. It asks the assistants through their APIs, with search on. That's close to what people see in the ChatGPT, Claude and Gemini apps, but it isn't identical, and the apps can answer differently.

Try it before you add a key

We preloaded some fictional data so you can see it working without spending anything. The first launch opens a tutorial that builds a demo project with six months of history.

When you're ready, just point your LLM at the README and it will help you set it up. The agent never handles your keys. You have to add those yourself.

What's next?

Go try it! Then stay tuned for our website 'AI visibility' tool that helps you make the improvements we've made for others so AI mentions you more often to buyers.

Let us know what you think.

We worked hard on Overheard AI. It's free and open source but that doesn't mean we don't care what people think. If you love it (or hate it) please let us know! We love feedback.