A clear read on how models describe the brand, why they recommend it, and when a recommendation is flattering but wrong.

Repeated recommendation scenarios reveal tone, shortlist position, stated reasons, caveats, and non-fit cases. The result is useful when those reasons can be checked against documented buyer criteria and evidence. You can compare the stated recommendation reasons with approved buyer criteria and evidence, including cases where the brand should remain out of the shortlist. Product and content leads who need to know whether the brand is being recommended for reasons its evidence supports.

Some of the 500+ brands we've worked with

See all references

Documented decision criteria come first. Eligible and ineligible scenarios then run under fixed conditions, and any gain that creates more wrong-fit recommendations fails the test.

How we hold ourselves to it

Fit checked before praise
Reasons traced to evidence
Criticism isn't a defect
No tone dialed to order

Extract decision criteria from audience questions
Sales, support, and research questions are grouped by job, constraint, risk, and stage. Uncommon but material scenarios remain in the set. Client research, sales and product owners approve criterion provenance, priority and intended recommendation context.
Recommendation intent matrix with persona, need, constraints and expected decision.
Define fit, non-fit and evidence rules
Each criterion gets a support rule, a disqualifier, and an acceptable evidence standard before brand appearance is observed. Domain, legal and product owners approve fit, non-fit and evidence rules before scenarios run.
Criteria-to-evidence ledger with fit, non-fit and uncertain states.
Run repeated recommendation scenarios
Fixed eligible, ineligible, ambiguous, and competitor scenarios run repeatedly, preserving each shortlist and its stated reasoning. A monitoring operator validates run completeness and applies the same validity rule to every scenario.
Fit and non-fit decision table linked to complete answer captures.
Audit recommendation reasoning and sources
Every inclusion, omission, and caveat is compared with the approved criteria. Exposed sources are checked against the reason the model gave. Domain, editorial and legal reviewers approve evidence and harm labels or record an abstention.
Annotated shortlist evidence set with support and harm labels.
Close honest evidence and content gaps
Verifiable criteria pages, comparisons, limitations, or disclosures are strengthened only where the brand can substantiate the underlying fit. Content, product, brand and legal owners approve truthful corrections within their authority. No false-fit claim may ship.
Prioritized buyer-criteria content specification and evidence backlog.
Retest paraphrases and unseen personas
The original panel and unseen persona or wording variants run again to check whether the changes introduce recommendations for non-fit cases. An independent reviewer rejects any gain that increases unsupported or wrong-fit recommendations.
Retest report covering eligible and ineligible precision.

The handoff makes supported fit, non-fit cases, missing evidence, and unreliable recommendation reasons visible enough for product, content, and legal owners to decide.

Recommendation trigger baseline
A scenario-level baseline of eligible recommendations, false positives, omissions, rationale accuracy and ordinary variance.
Buyer-criteria content specification
Defines the questions, proof, limitations and comparison language each priority page must make inspectable.
Evidence-gap and exclusion roadmap
Separates proof the team can create, evidence requiring independent validation and contexts the brand should explicitly decline.
Retest report on unseen personas
Shows how the original and unseen personas changed, including new non-fit recommendations and unsupported reasons.
Eligible recommendation rate
Counts recommendations only where the approved fit rules are met, with raw mentions and ineligible recommendations excluded.

This method applies when recommendation answers omit the brand, place it with a poor-fit audience, or give reasons the product cannot honestly support.

A good fit when

Relevant shortlists omit the brand or misstate its fit — The brand may be absent from ChatGPT shortlists, or included for unsupported reasons or audiences.
A decision is waiting on fit criteria — The team needs to know which criteria the brand meets, where proof is missing and which contexts are unethical.
Buyer proof and recommendations are split — The team has research, product evidence and ChatGPT examples, but no shared rule for judging recommendation fit.
Buyer criteria define recommendation eligibility — We turn approved questions into use case, budget, location, risk and must-have conditions for each recommendation.
Brand fit and exclusions stay evidence-backed — We record where the offer fits, where it doesn't, and which approved proof supports each comparison criterion.
Recommendation reasons and shortlist position — We inspect why repeated shortlists include, omit or qualify the brand. A bare mention isn't a correct recommendation.
Reviews and proof stay traceable — Reviews, comparisons, credentials and outcome claims stay attributable, current and disclosed. We do not manufacture endorsements.

The situation before this work starts, drawn as a Zeo scene

Better handled as other work when

You want tone engineered to order — We can report how models currently characterise you and why. We cannot dial sentiment to a target figure on request.
Recommendations remain outside our control — We don't manipulate hidden prompts, fabricate reviews or manufacture consensus. Third parties make the recommendation.

GEO work starts with recording what AI answers actually say about a brand today, then moves to the parts you can influence. The consultants below work on the specific capability this page covers.

Content we've produced on this topic

Articleby Can MutioğluGenerative AI Optimization (GEO) for E-Commerce Sites Articleby Didem HimmetliThe Transformational LLMs on Search and Recommendations

Peec AI
tracks sentiment as its own metric, separate from whether the brand was simply mentioned
Profound
runs the buyer scenarios repeatedly, retaining the stated reasons beside each shortlist
Otterly.AI
connects a recommendation pattern back to the specific content gap causing it
OpenAI
the platform the fit and non-fit scenarios are replayed against, including held-back personas
Airtable
holds the documented buyer criteria a recommendation's stated reasons get checked against
Jupyter
computes the fit-precision rate as code, so a false-positive gain cannot be quietly dropped

One buyer question, its fit rules, and the supporting proof define the test case. We compare sampled recommendations and label each context as supported, uncertain, or out of scope.

Review recommendation fit

Does this method guarantee recommendations or citations?

Recommendations remain a third-party decision. We don't use hidden prompts or planted reviews. Manufactured consensus also sits outside the method. No recommendation or citation is guaranteed.

When is this the right method?

Use this method when the brand is absent from relevant shortlists or appears for the wrong reasons, audiences, or constraints, with fit confirmed before any change is proposed.

When should negative language stay on the record?

Supported criticism stays when the non-fit case or limitation is accurate. We separate tone from factual support and escalate only framing that is materially misleading or tied to an unsupported reason.

How are recommendation improvements checked for wrong-fit gains?

Eligible recommendations need to align with documented buyer criteria and evidence, while non-fit cases stay excluded. We replay the original scenarios plus personas that were never used in the work, and report false-positive gains as failures.

By team

By industry

By tool

Sentiment & Recommendation Analysis

From buyer criteria to fit and non-fit tests

Extract decision criteria from audience questions

Define fit, non-fit and evidence rules

Run repeated recommendation scenarios

Audit recommendation reasoning and sources

Close honest evidence and content gaps

Retest paraphrases and unseen personas

A recommendation map that values fit over flattering mentions

Recommendation trigger baseline

Buyer-criteria content specification

Evidence-gap and exclusion roadmap

Retest report on unseen personas

Eligible recommendation rate