You tell us what is true
Your prices, your plans, your integrations, your certifications. One short session, and we read most of it off your own site first.
You, onceAnswer integrity
Quality control for what AI says about your company.
Your buyers stopped opening ten links. They ask an assistant, get one answer, and act on it. When that answer is out of date, you lose the deal before anyone reaches your site.
We find the wrong answers across ChatGPT, Claude, Gemini and Perplexity, fix the page they came from, then ask again to check the answer changed.
- We ask
- OpenAI · Anthropic · Google · Perplexity
- Every number shows
- the rate, the error bar, the run count
- Under 5 runs
- no number at all
Does Slack's free plan keep our message history?
Slack's free plan works well for a small team. It keeps your 10,000 most recent messages, so nothing is lost while you stay under that. Paid plans add unlimited history and Slack Connect.
| top10teamchat.example.com/best-slack-alternatives | does not support it |
| slack.com/pricing | supports it |
Your approved fact says otherwise
Contradicted
The Slack free plan keeps 90 days of message history. The 10,000-message limit ended on 1 September 2022.
in force 2022-09-01 → current · sensitivity material · approved by pricing-ops
9%95% CI 5%–15%n=116
Critical
Why counting mentions misses this
A wrong answer that looks like a win.
The brand is named, the tone is positive, and one of the two citations is Slack's own pricing page. Every share-of-voice tool scores that as a win. The limit it quotes ended in 2022.
Check it yourself: ask any assistant what Slack's free plan keeps, then open slack.com/pricing.
Slack's free plan works well for a small team. It keeps your 10,000 most recent messages. Paid plans add unlimited history and Slack Connect.
01
One answer, no second opinion
Search handed your buyer ten links to compare. An assistant hands them one answer. If they act on the wrong one they never reach your site, so nothing in your analytics records it.
02
It used to be true
Slack really did keep 10,000 messages until September 2022, and thousands of comparison pages still say so. Every fact you give us carries a start date and an expiry, because an answer can be correctly sourced and still wrong.
03
The fix is upstream
A stale comparison page carried the old limit and the pricing page did not outrank it. Publish a dated correction, fix the doc, ask again, and see whether the answer moved.
How it works
Five steps, and you only do two.
No tags to install, no tracking code, nothing to plug into your stack. Tell us what is true about your company and we do the asking, the checking and the proving.
We ask what your buyers ask
The real questions people type before they buy from you, asked over and over across ChatGPT, Claude, Gemini and Perplexity.
Us, every weekWe show you what is wrong
Every answer that contradicts a fact you gave us, with the transcript, the date and the page the assistant leaned on.
Us, with receiptsYou fix the page it came from
Usually one paragraph on a page you already own. We tell you which page and what it needs to say.
You, ten minutesWe check whether it worked
We ask again, compare against questions we deliberately left alone, and tell you plainly whether the answer moved or the model just changed.
Us, and we will say if it failedWhat we find
Most wrong answers used to be true.
Assistants are not inventing your company. They are repeating a version of it you have moved on from.
A price you changed last year
Assistants keep quoting the old one, often citing your own pricing page.
A plan or limit you retired
Buyers arrive expecting a tier that no longer exists, and blame you for the surprise.
A feature you never shipped
Somebody is being sold something you cannot deliver, and it lands in your renewal calls.
An integration you sunset
The answer says you connect to a tool you dropped two releases ago.
A competitor named as your alternative
On questions specifically about you, not about the category.
A claim your own docs contradict
Two pages of yours disagree, so the assistant picks one, and it is often the older one.
Every one of these is fixable, because every one of them traces back to a page. Usually a page you own.
Six refusals, enforced in code
Six things we will not do.
Each one is a failing test. If a release ships a blended score or a bare percentage, the build goes red before you see it.
One score you can screenshot
Ask about you by name and you get mentioned. Ask for a vendor recommendation and you might not. Averaging the two makes a flattering number that means nothing. We keep them apart.
assertNoBlending() throws · tests/unit/intent.test.ts
A percentage with no sample size
Every rate ships with its error bar and its run count. Under five runs you get "insufficient data".
domain/stats.ts · tests/unit/stats.test.ts
An alert because a number wobbled
A change is reported only if it clears a significance test, moves at least ten points, and survives a correction for everything else tested that round.
two-proportion z-test, BH at q=0.1 · services/dashboard.ts
A made-up impact estimate
A fix gets a predicted range only if your workspace already holds comparable experiments. Otherwise it ships as an experiment.
deriveExpectedRange() · tests/unit/priority.test.ts
Reviews and posts we manufacture
There is no connector for posting anywhere, and none for generating reviews. The one review action asks your real customers.
ACTION_TYPES closed enum · tests/unit/product-copy.test.ts
A promise to make the models obey
Nobody outside a lab decides what a model says. We measure it, fix what it reads, and test whether the answers moved. A lint fails the build if this page says otherwise.
banned-claims lint over src/ · tests/unit/product-copy.test.ts
Why you can trust the numbers
Six promises, and what backs each one.
You are going to take these numbers into a meeting and someone will push back on them. Here is what holds up when they do.
We will not show you a number we cannot stand behind
If we have asked a question fewer than five times in a window, you get "not enough data" instead of a percentage.
5-run floor per cluster per windowEvery number tells you how sure it is
A rate never appears without the range it could really be and how many times we asked. 40% from ten asks and 40% from a thousand are different findings.
95% Wilson interval, always with its nWe will not email you about noise
A change has to be big enough to matter and survive a statistical test before it reaches you, so your inbox is not a random number generator.
Two-proportion z-test, p < 0.05, 10-point minimum moveWatching more questions will not create false alarms
Test enough things and something always looks significant by chance. We correct for that, so tracking more does not mean panicking more.
Benjamini-Hochberg at q = 0.1We will tell you when your fix did not work
We hold back a set of questions and change nothing about them. If they move as much as the ones you fixed, the model changed, not your page, and we say so.
Matched controls, difference-in-differencesThere is no single score
Being named when someone asks about you and being recommended when they ask for a vendor are different results. Averaging them makes a flattering number that means nothing.
Metrics keyed by intent family, never blendedIf you want the arithmetic rather than the promise, we published it: how many times you have to ask before a percentage means anything. Asking fifty question clusters across four assistants for a month costs $400 to $1,000 in model and search spend before anything else, which is why this is not a $49 tool. At $49 nobody can ask often enough to know whether the answer is right.
Pricing
Priced by how many buyer questions we watch.
We load your facts, ask your highest-intent questions, and hand back every wrong answer we can evidence. The report is yours either way.
Start the audit50 question clusters across four assistants, sampled weekly. Alerts have to clear a significance test.
Talk it through100 clusters, sampled daily, plus the full fact registry, the action list and the experiment ledger.
Talk it throughMultiple brands or clients in one place, CRM handoff, approval trails and full export.
Talk it throughStart with the free audit
See what assistants tell your buyers.
The audit is the whole product, run once by hand on your domain. Most teams have never read a transcript of what the assistants say about them.
- We load your facts from your docs. You approve each one before we ask anything.
- We ask your highest-intent questions across every assistant this deployment has a key for.
- You get every wrong answer we can evidence, with transcripts, setups and citations.
- If we find nothing worth fixing, we say so and you owe us nothing.