Recommendation guide

How to earn app recommendations from AI agents

Recommendations are downstream of retrieval and trust. The defensible path is to answer a real user intent with verifiable facts, observe which sources support the answer, and test whether the result repeats.

01

Start with the problem the user will ask

Branded prompts verify whether a model recognizes a known name; they do not measure spontaneous discovery. Generic-problem prompts are stronger controls because they state a job without telling the provider which product to find.

Keep a fixed control set and add bounded variants. If the prompt changes every day, a positive result cannot be compared with yesterday's absence. Record prompt fingerprints, provider, model, and observation time.

02

Separate mention, recommendation, and support

A mention places the product name in an answer. A recommendation connects it to the requested job with affirmative language. Evidence support identifies which consulted URLs contained enough product information to make that connection inspectable.

Owned documentation can support a correct recommendation, but it is not independent endorsement. Label the evidence as owned source, directory record, independent source, or mixed. Keep a single-provider result single-provider until another provider repeats it.

  • Quote the exact recommendation excerpt.
  • Link the first product source in the search trace.
  • Separate later branded verification from the original unbranded entry query.
03

Amplify a right path without copying noise

When an unbranded query leads to a product source and an explicit recommendation, preserve that route as a right-path receipt. Build deeper pages for adjacent intents, improve the facts on sources already consulted, and rerun the original prompt unchanged.

Do not turn one result into a promise. The useful claim is that a stated provider produced a recommendation under stated conditions on a stated date. Replication is the next experiment.

Verification layer

Primary sources

These links support the definitions and product facts above. They do not constitute independent endorsement.

Primary source ↗

Deploy to Agents public product facts

Machine-readable product facts, public surfaces, limitations, and verification links.

https://deploytoagents.com/llms.txt
Primary source ↗

OpenAI web-search response events

Primary reference for retaining search queries, opened pages, and consulted source URLs.

https://platform.openai.com/docs/api-reference/responses-streaming/response/refusal/delta?lang=curl
Measure before you claim

See what agents can observe today.

Start from one public URL. Keep technical readiness, retrieval, recommendation, and invocation as separate evidence.

Create your profile