Assistant Misstatement Repair

The instinct is to report the answer to the model vendor and wait. That rarely works alone, because most false claims are faithful reproductions of something still published: your own retired pricing page, a review of a version from two years ago, an old PDF, a press release nobody removed. While the source stays live the answer regenerates, and reporting a symptom whose cause is still on your own domain spends the one channel you have.

Die Skill-Datei

---
name: assistant-misstatement-repair
description: Use when an assistant repeatedly states something false about your product, such as a feature you never shipped, a retired plan or a price that changed.
---

# Assistant Misstatement Repair

The instinct is to report the answer to the model vendor and wait. That rarely works alone, because most false claims are faithful reproductions of something still published: your own retired pricing page, a review of a version from two years ago, an old PDF, a press release nobody removed. While the source stays live the answer regenerates, and reporting a symptom whose cause is still on your own domain spends the one channel you have.

## Was Sie vorher brauchen

- The exact prompt that produces the claim, with the assistant and date, since answers vary between runs
- Any URLs the answer cites, plus the answer text verbatim
- A dated record of what actually changed and when: pricing history, removed features, renamed plans
- Access to your own archived and unlinked pages, including PDFs, changelogs and old campaign landing pages

## Methode

1. Reproduce the claim three times in clean sessions before doing any work. A single odd answer is not a pattern and does not justify the effort that follows.
2. Follow the citations the answer gives, but treat the stated source as a lead rather than a fact. A model can attribute a claim to a page that does not contain it.
3. Search your own estate for the wording before looking outward. Retired pricing pages, stale help articles, old PDFs and press releases are the most common cause and the only one you can fix outright.
4. Correct the source itself rather than publishing a rebuttal elsewhere. A new page saying the claim is false leaves two contradictory documents in the corpus, and the older one usually carries more links.
5. Remove or redirect obsolete pages instead of leaving them live under a correction banner, since the banner is prose that extraction may simply not carry.
6. For third-party sources, request a correction with the evidence attached, and accept that a review site may only annotate rather than rewrite.
7. Use the vendor feedback control as well, but after the source is fixed, so that a re-crawl finds a page that agrees with your complaint.
8. Re-test the same prompt monthly and record the date the answer changes. Correction lag runs from weeks to months, and without a dated log nobody can say whether the fix worked or the model simply moved on.

## Was dabei herauskommt

A short correction record per false claim holding the prompt, the traced source, the fix applied, the date, and monthly re-test results until the answer changes.

## Wo es schiefgeht

- Reporting the answer to the vendor while the page that caused it is still live, so the claim returns after the next crawl
- Publishing a correction page and leaving the wrong page indexed, which gives the corpus two answers and no basis to choose
- Judging the fix on one re-run, when answers vary between runs and a single clean result proves nothing
- Assuming the source must be external when it is most often your own retired content

---

Aus der QuQi-Skill-Bibliothek - https://www.quqi.io/de/skills/assistant-misstatement-repair

Was Sie vorher brauchen

• The exact prompt that produces the claim, with the assistant and date, since answers vary between runs
• Any URLs the answer cites, plus the answer text verbatim
• A dated record of what actually changed and when: pricing history, removed features, renamed plans
• Access to your own archived and unlinked pages, including PDFs, changelogs and old campaign landing pages

Methode

1. 01 Reproduce the claim three times in clean sessions before doing any work. A single odd answer is not a pattern and does not justify the effort that follows.
2. 02 Follow the citations the answer gives, but treat the stated source as a lead rather than a fact. A model can attribute a claim to a page that does not contain it.
3. 03 Search your own estate for the wording before looking outward. Retired pricing pages, stale help articles, old PDFs and press releases are the most common cause and the only one you can fix outright.
4. 04 Correct the source itself rather than publishing a rebuttal elsewhere. A new page saying the claim is false leaves two contradictory documents in the corpus, and the older one usually carries more links.
5. 05 Remove or redirect obsolete pages instead of leaving them live under a correction banner, since the banner is prose that extraction may simply not carry.
6. 06 For third-party sources, request a correction with the evidence attached, and accept that a review site may only annotate rather than rewrite.
7. 07 Use the vendor feedback control as well, but after the source is fixed, so that a re-crawl finds a page that agrees with your complaint.
8. 08 Re-test the same prompt monthly and record the date the answer changes. Correction lag runs from weeks to months, and without a dated log nobody can say whether the fix worked or the model simply moved on.

Was dabei herauskommt

A short correction record per false claim holding the prompt, the traced source, the fix applied, the date, and monthly re-test results until the answer changes.

Wo es schiefgeht

• Reporting the answer to the vendor while the page that caused it is still live, so the claim returns after the next crawl
• Publishing a correction page and leaving the wrong page indexed, which gives the corpus two answers and no basis to choose
• Judging the fix on one re-run, when answers vary between runs and a single clean result proves nothing
• Assuming the source must be external when it is most often your own retired content

Diese Skill in Ihrer eigenen KI nutzen

Die Datei ist einfaches Markdown, mit Name und Auslöser im Frontmatter. Wo ein Assistent Skills selbst laden kann, liest er genau dieses Frontmatter, um zu entscheiden, dass diese hier passt.

Mehr in AI-Suche (GEO)