# Catch AI models spreading false claims about your brand

> Every weekday at 8am, spot new false claims AI models are making about your brand, see which sources feed them, and get the fix to the right person.

- Workflow type: agent
- Services: Profound, Slack, Notion
- Categories: Marketing
- Published: 2026-08-09

## What it does

- Checks the last seven days of AI answers for the false claims that come up most often about your brand, plus the themes behind them.
- Only flags claims that are new since the last run or clearly climbing in frequency, so you are not re-reading the same five issues every morning.
- Traces each claim back to the web pages feeding it, so you can see which source the model is actually repeating.
- Decides whether the fix belongs on your own website, in your documentation, or in an outreach email to a third party site, then posts an alert to Slack and logs the claim in a Notion tracker.

## What you'll need

- A Profound account on a plan that includes API access, with accuracy tracking already set up for your brand.
- A Slack workspace and the channel where you want the alerts to land.
- A Notion database to act as the tracker, shared with your Notion connection, with columns for the claim, theme, affected models, source links, recommended fix, and status.

## Prompt

Every weekday at 8am, watch for AI models stating things about my brand that are simply not true, and get my team on it before the claim spreads.

Start by pulling the most frequent false claims from the last 7 days with Profound's Accuracy Top Inaccurate Claims report, and pull the ranked themes and their response share with Accuracy Inaccurate Themes. For each claim cluster worth reporting, use Accuracy Claim Citations to fetch the specific URLs backing that cluster. If the claim data does not already tell me which AI models are repeating a claim, use Accuracy Inaccurate Clusters to get the per model breakdown.

Surface only claims that are new since the previous run or clearly rising in frequency. This filter is the difference between a useful alert and a daily wall of the same five claims, so apply it strictly. Establish it two ways. First, run the same accuracy reports over the previous 7 day window and compare frequencies, so a claim whose count is climbing counts as rising. Second, query my Notion tracker with Query a Data Source to see which claims have already been logged, so anything already recorded and flat is skipped. If nothing is new or rising, post a short note saying the check ran and found nothing new rather than staying silent.

For each surfaced claim, judge where the fix belongs and say so explicitly. Pick one of three routes: a page update on our own site when the claim traces back to our marketing pages or to content we never wrote, a correction in our documentation when the model is reading our docs and drawing the wrong conclusion, or outreach to the third party source when an external site is feeding the model bad information. Base this on the citing URLs rather than guesswork, and name the specific page or domain that needs to change.

Post an alert to my Slack channel with Send a Message. For each claim, state it in plain language the way a person would say it, then give which models repeat it, how often it came up in the window, whether it is new or rising, the citing URLs, and the recommended fix route. Lead with the highest frequency claims and keep the message scannable.

Log every surfaced claim as a row in my Notion tracker using Create a Page as a child of the tracker database. Capture the claim, its theme, the affected models, the source URLs, the recommended correction, the date it was first seen, and a status starting at open, so we keep a running record of what we fixed and what is still wrong.

Two rules to hold to. If Profound returns no accuracy data for the window, say so plainly instead of inventing claims. And never restate a false claim as though it were true in the Slack message or the Notion row, always frame it as a claim a model is making about us.

## How to customize

- Change the schedule. Weekday mornings at 8am is the default, but a Monday and Thursday check is plenty for slower moving brands.
- Tune how sensitive the rising threshold is. Raise it if you only want claims that are spreading fast, lower it to catch problems earlier.
- Route by severity. Send everything to one channel, or tag a specific owner when the fix lands on your own site versus a third party.

## FAQ

### Will I get an alert every single morning?

Only when something is actually new or picking up steam. The whole point of the filter is that a claim you already know about and already logged does not get re-sent. On a quiet day you get a short note saying the check ran and found nothing new.

### What counts as a new claim?

Two things trigger an alert. Either the claim has never been written to your tracker before, or it appeared in an earlier window and is now coming up noticeably more often. The second case is how you catch a small problem before it becomes a common answer.

### Which AI models does this cover?

Whichever ones Profound is tracking for your brand, which typically includes assistants like ChatGPT and Perplexity along with AI search results. The alert names the specific models repeating each claim so you know how widely it has spread.

### Does this fix the false claims automatically?

No, and that is deliberate. It tells you what is wrong, where the model is getting it from, and which of the three fixes is the right one. A person still makes the edit or sends the outreach email, because correcting the record is a judgment call.

### Do I need a paid Profound plan?

Yes. Accuracy reporting is available through Profound's API on their Enterprise plan, so you will need an account with API access before this can run.

Use this prompt in General Input: https://www.generalinput.com/prompts/catch-ai-models-spreading-false-claims-about-your-brand