Skip to content

Separate firsthand experience from attributed experience

Keep authors’ own public accounts distinct from reports about friends, customers or unspecified others when assessing experience claims.

Guides

Who actually experienced the event described in a post?

A comment saying my headset failed after an update differs from a comment saying everyone says the update breaks headsets. Both may be relevant to a discussion review, but only one presents the author as an experiencer. Preserve the relationship between speaker and reported event before drawing conclusions about documented user experiences.

Example research prompt
Classify supplied headset posts by the author’s relationship to the reported event. Preserve secondhand attribution and do not turn generalized hearsay into firsthand experience.
01 / Guides

Define experience categories

Use firsthand account, attributed secondhand account, generalized hearsay and unclear relationship as separate labels. Include explicit statements about the relevant failure; exclude unrelated opinions from experience counts. Do not infer firsthand use merely because an author is confident, knowledgeable or active in a product discussion, since expertise and experience are different claims.

02 / Guides

Preserve attribution language

Keep phrases such as my colleague reported or a reviewer said with the evidence excerpt. Record any linked origin without silently rewriting the account into the author’s own experience. Where quotation marks or thread context make attribution ambiguous, retain the full passage and classify the relationship as unclear until additional visible context resolves it.

03 / Guides

Check downstream summaries

Review whether an agent-generated synthesis accidentally turns attributed reports into direct accounts. Compare the summary’s subjects and verbs with the cited text. If the original says someone else might have experienced a problem, the summary should not say the author did experience it, nor present the possibility as an established event.

04 / Guides

Deliver separate evidence views

Show direct experience patterns separately from discussion about other people’s experiences. Explain what each view can answer: described use versus circulating accounts. If few firsthand passages remain, narrow the conclusion rather than merging hearsay into the direct set, and leave the prevalence of the underlying product problem explicitly unknown.

Keep the boundaries clear.

  • Confident wording does not establish that the author used the product.
  • Examples describe review methods, not live tests or guaranteed platform coverage.

Start with a read-only check: ask your agent to report actual source coverage before collecting records or exporting an audience.

Primary references

Documentation reviewed 2026-11-13. Product capabilities, client availability and plans can change. Third-party marks identify their products, not an affiliation.

Know what social media shows about you.
Start with a question.

Get started
montage