> Source: https://builder-docs.ema.ai/agent-reference/core/respond-using-search-results
> Title: Respond using Search Results Agent

# Respond using Search Results Agent

> [WARNING]
> **Deprecation Notice:** This agent is deprecated. Use the Respond to a Query Agent instead.

The Respond using Search Results agent generates a response grounded in provided search results. It combines the query and search results, generates an answer using that context, and returns a single `response_with_sources` output containing both the response text and the retained sources.

## Use Cases

-   Your workflow searches a knowledge base and needs to generate a cited response.
-   You want responses that are grounded in source documents, not based on the LLM's training data alone.
-   You want the output to preserve the specific sources used to support the answer.

## Inputs

Input

Type

Required

Description

`query`

TextWithSources

Yes

The query or prompt to answer. Any sources already attached to the query are merged with `search_results`.

`search_results`

SearchResults

Yes

The search results used as the grounding context for the response.

`user_instructions`

Text

No

Optional instructions for tone, format, or response behavior.

## Outputs

Output

Type

Description

`response_with_sources`

TextWithSources

The generated response. The text is returned in `text` and the retained sources are returned in `sources` on the same object.

## Configurations

Parameter

Description

Default

`user_instructions`

Additional instructions for how the response should be written.

Empty

`se_guidelines`

Additional hidden search experience guidance appended to the system prompt.

Empty

`process_entire_document`

Use entire matched documents instead of only matched segments or chunks.

`false`

`glossary`

Glossary terms to guide terminology and domain language.

None

`user_tags`

User tags that can help prioritize more relevant results.

None

`reranking_percentile_threshold`

Filters retained sources by semantic similarity to the generated answer.

`0` (disabled)

`use_citation_based_filtering`

Uses structured output so the model identifies which sources it actually used.

`true`

`no_search_results_response`

Fixed fallback response used when no search results are available.

Built-in default message

`use_clarifying_question`

Allows the model to return a clarifying-question style response when the query is too ambiguous.

`false`

`clarify_question_user_instructions`

Additional instructions for clarifying-question behavior.

Empty

`disable_sources`

Clears sources from the final output even though search results are still used during generation.

`false`

## How to Use This Agent

```
chat_trigger -> knowledge_search -> respond_using_search_results -> workflow_output
```

## Related Agents

-   [Knowledge Search](/legacy-docs/agent-reference/core/knowledge-search) -- the standard upstream provider of search results.
-   [Respond to a Query](/legacy-docs/agent-reference/core/respond-to-a-query) -- for general response generation from any inputs.
-   [Combine Search Results](/legacy-docs/agent-reference/core/combine-search-results) -- for merging results from multiple searches.
-   [Rerank Search Results](/legacy-docs/agent-reference/core/rerank-search-results) -- for improving result relevance before response generation.