Skip to main content
Plan a Perplexity Search action that returns sources for a factual question. This design retrieves evidence; it does not change the model assigned to your agent.
There is no native Perplexity connector in the current catalog. Search tool preparation does not establish model-catalog support, custom-model execution, or a working agent runtime.

​
Prepare a search action

You need a provider account, an approved API credential, and a policy for which queries may leave your application.
1

Choose search rather than an assumed model route

Review the Search API quickstart for its query, result-count, and Bearer-token requirements. Define a small result limit and the exact question to investigate. Do not assume that a search credential is an agent model configuration.
2

Review the data sent and returned

Remove unnecessary personal or internal details from the query. Return relevant source titles, URLs, and available date information. Keep provider text separate from the agent’s instructions and retain the evidence behind any resulting answer.
3

Define a bounded failure result

Distinguish no relevant sources from an unavailable provider, expired credential, or quota error. Limit retries and cost. Require separate authorization before any downstream action suggested by the research, such as contacting a person or modifying a record.
Review compatible credential storage in auth connections and the proposed action in tool configuration. Saving either resource establishes configuration only.

​
Frequently asked questions

No. Tool references and model selection are separate configuration. Consult models for the current authoring and execution limits.
Keep the sources that support the answer available to the reviewer. If the result lacks usable evidence, report that limitation rather than inventing a citation.