How Trust Cue reads accounts

What we read

We read a sample of an account's public posts on X: their most recent posts and replies, plus a few of their own posts from each earlier stretch — months and, for older accounts, years back — so a rating reflects more than their last few days. A rating's findings never rest on reposts; those words are someone else's. When you check an account from one of its posts, we read that post too and say how it sits with the rest. That sample is the evidence for the rating, so a rating describes the posts we read, not an account's whole history.

Trust Cue may also open a public link from the account's profile to check an identity or credential claim. It does not access your private session, read DMs, or post for you.

The cue, and what a tap shows

A cue sits beside account names in your X feed. While a rating of the account is current, it shows what they usually post about and since when; otherwise it is just the quiet Trust Cue mark. Hovering a cue with a current rating previews it. An account you checked yourself keeps a dimmed, dated cue on your device for 30 days.

Tapping a cue is free and never uses a check. It opens the account in a side panel with quick facts, counted from the account itself rather than interpreted:

• On X since
• Posts a day
• Replies
• Reposts, last 7 days
• Posts linking a source
• Paid partnerships
• Identity verified
• Profile link

For the post you tapped, the panel shows whether it fits their usual topics and what it links to — the source itself, a news report, another post, or a website.

What a full check gives you

A full check reads the sample above and gives a rating:

• A one-line summary of what their posts show.
• Their topics — what they usually post about, and since when.
• Findings — what their posts show, each marked Positive, Note or Concern, with how many posts back it. Findings cover things like depth on a topic over time, whether the posts bear out what the profile claims, corrections of their own earlier claims, whether promotion is disclosed, their own analysis against passing on others', and how they engage.
• Points the other way — posts that cut against a finding, shown beside it.
• Coverage — how many posts were read, across which years, and when the check ran.

There is no mark, grade or score, and no level for anyone to reach. A rating states what the posts show and leaves the conclusion with you.

Every point, one tap from its posts

Every finding is one tap from the public posts behind it. If we can't point at the posts, the finding isn't stated, and some kinds of finding need posts from more than one stretch of time before they can be stated at all. Quotes are read from X when you open them, so a post deleted or edited on X drops out of the rating. A quote proves the account said something, not that the statement is true — which is why the posts that point the other way sit beside the finding rather than being left out.

Readers check the findings

Every kind of finding starts out marked “Being tested”. Under each one, the panel asks “Do the posts back this up?” Yes · Partly · No. Readers' answers decide which kinds of finding are shown publicly: a kind readers confirm is shown on share previews, public pages and hover previews; a kind that stops meeting the bar goes back to being tested. Until then it appears only in the panel of the reader who opened the rating, marked as being tested.

This is readers' judgment of whether the posts back a finding, not a guarantee that any finding is right. Read the posts yourself before you rely on one.

How language coverage works

Trust Cue reads posts in the language they were written in. It never translates a post into English and then judges the translation — too much of what makes a claim careful or careless dies in translation. A post in a language Trust Cue doesn't read yet is marked that way rather than guessed at.

What ratings are not

A Trust Cue rating describes what a sample of an account's recent public posts shows. It is not an endorsement, a character judgment, a comprehensive fact-check, or financial advice. A Positive finding means the posts we read show that thing; it does not mean every claim is true or that you should act on it.

A rating is about an account's recent posting, not about a person, and there are decisions it must never be used for. Do not use Trust Cue to decide whether to hire, fire, house, lend to, insure, admit, or otherwise qualify anyone. It is not a background check and it is not built to carry that weight — it reads a bounded sample of public posts and can be wrong. We also never derive or report anything about a person's health, finances, politics, race, religion, sexuality, or union membership.

What the rating can miss

Trust Cue can miss deleted posts, anything said outside the posts we sampled, private conduct, new information published after the rating was made, or a conflict of interest that was never disclosed publicly. Automated reading and interpretation can also simply be wrong. Evidence links let you inspect the basis of a finding, but they do not remove the need to verify an important claim against primary sources.

The result is designed for repeatable source triage: deciding where to look more closely. It is not a substitute for reporting, due diligence, or expert review when a decision carries material consequences.

How long a rating lives

A rating lives up to 7 days, or until the account posts again and a reader updates it. A rating reflects the posts we read when the check ran, and every rating says when that was. While a rating is current, anyone who taps that account can open it for one check instead of running a new one.

A completed check uses one check, however little the posts show; a check that fails or is cancelled before its rating arrives uses nothing. Whoever paid for a rating can share a link that opens the full rating while it lives, and turn that link off at any time.

The sample ratings on the welcome page are the deliberate exception. They are ratings of real accounts, dated to when they were captured, and they don't update — they show you what a rating looks like, not what those accounts are posting today.

Is this your account?

Every rating links to “Is this your account?”. An account's owner can sign in with X to prove the account is theirs, then object to being rated — which stops every new check of the account and removes any stored rating — or ask for a fresh check after they have posted since. Anyone can also object by email to [email protected].

Look-ups on a post (Pro)

On a post you tapped, Pro adds two look-ups. Earlier posts on this finds what the account said before on the same subject, each point linked to the posts it rests on. Origin and responses shows where similar wording appeared earlier — which can be a coincidence or a shared source — and how quote posts respond, which doesn't settle whether the post is true.

Same rules for everyone

There is no per-account tuning and no override, and no one edits a rating by hand. Every account is read the same way — including our own. If the rules change, the change is documented here on this page.

Common questions

How do I use Trust Cue on X?

Trust Cue puts a cue beside account names in your X feed: what the account usually posts about and since when, while a rating of it is current, or otherwise the quiet Trust Cue mark. Tap a cue and the account opens in a side panel with its quick facts and the post you tapped. Tapping a cue is free; only a full check uses one of your checks.

What does Trust Cue read?

A sample of an account's recent public posts on X, reaching back across the years it has posted. Trust Cue may also open a public link from that account's profile to check an identity or credential claim. It never reads your private session or DMs, and never posts for you.

What is in a Trust Cue rating?

A one-line summary, the topics the account usually posts about and since when, and findings: what their posts show, each marked Positive, Note or Concern with how many posts back it, and each one tap from the public posts behind it. Posts that point the other way are shown beside the finding they cut against. There is no mark, grade or score.

What does “Being tested” mean?

Every kind of finding starts out marked “Being tested”, and under each one the panel asks “Do the posts back this up?” Yes · Partly · No. Readers' answers decide which kinds of finding are shown publicly; a kind that stops meeting the bar goes back to being tested. Share previews, public pages and hover previews show only the kinds readers have confirmed. It is readers' judgment of the posts, not a guarantee that a finding is right.

Does Trust Cue fact-check every claim or endorse an account?

No. Trust Cue reads patterns across an account's recent public posting. It does not independently verify every claim, endorse a person, or replace checking an important claim against primary sources.

How long does a Trust Cue rating last?

A rating lives up to 7 days, or until the account posts again and a reader updates it. While it is current, anyone who taps that account can open it for one check instead of running a new one. An account you checked yourself keeps a dated cue on your device for 30 days.

Are the sample ratings current?

No, and they are labelled that way. The samples are ratings of real accounts, dated to when they were captured, and they don't update. They show you what a rating looks like, not what those accounts are posting today.

What does Trust Cue cost?

Adding the extension and tapping cues are free, and the sample ratings are free to read. A full check of any account is $3, a pack of 5 checks is $10, or Pro is $18/month for 20 checks a month. A completed check uses one check however little the posts show; a check that fails or is cancelled uses nothing.

Is a Trust Cue rating an endorsement or financial advice?

No. A rating describes what an account's recent public posts show — not an endorsement, not a judgment of the person, and not financial advice.