> ## Documentation Index
> Fetch the complete documentation index at: https://aisa.one/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Build a Research Agent with AIsa

> Choose AIsa search APIs, research Skills, evidence rules, and model synthesis for a source-backed research agent.

A research agent usually needs two distinct capabilities:

1. Retrieval of current or authoritative sources.
2. Model reasoning to compare, summarize, and explain the evidence.

Do not use model inference alone for claims that depend on current information.

## Choose the research surface

| Requirement                      | Start with                                                    |
| -------------------------------- | ------------------------------------------------------------- |
| Reusable multi-source workflow   | [Multi-source Search Skill](/docs/agent-skills/search)             |
| Recent cross-source brief        | [Last 30 Days](/docs/agent-skills/last30days)                      |
| Citation-backed deep research    | [Perplexity Deep Research](/docs/agent-skills/perplexity-research) |
| Academic papers                  | [Scholar Search](/docs/agent-skills/scholar-search)                |
| Application-controlled retrieval | [Direct API Reference](/docs/api-reference)                        |
| Final synthesis or formatting    | [Model inference](/docs/guides/models)                             |

Use a Skill when the workflow is reusable and the agent should follow an established process. Use direct APIs when the application needs to control source selection, sequencing, caching, or ranking itself.

## Recommended workflow

### 1. Define the research question

Specify:

* The exact decision or claim the research should support.
* The required time range.
* Preferred source types or domains.
* Geographic or language constraints.
* The expected output and citation format.

### 2. Retrieve before synthesizing

Use search results for discovery, then fetch the source pages needed as evidence.

```text theme={null}
Search results are discovery.
Fetched pages are evidence.
Generated summaries are synthesis.
```

Do not treat snippets, model memory, or a generated answer as equivalent to a primary source.

### 3. Compare sources

For material claims:

* Prefer official documentation, filings, original announcements, or primary datasets.
* Record publication dates and source URLs.
* Identify contradictions instead of silently merging them.
* Mark claims that remain uncertain or depend on one source.

### 4. Use a model for synthesis

After retrieval, pass the relevant evidence to a supported model. Ask it to separate:

* Verified facts.
* Interpretation.
* Open questions.
* Recommendations.

The model should not invent citations or claim access to sources that were not retrieved.

### 5. Verify the output

Before delivering the result:

* Confirm each important citation resolves to the intended source.
* Recheck time-sensitive numbers.
* Remove unsupported claims.
* State the research cutoff time.

## Minimal documentation set

An agent building this workflow should normally read only:

* [Agent Quickstart](/docs/agent-quickstart)
* [Capabilities by Goal](/docs/by-goal)
* The selected Skill or API pages
* [Authentication](/docs/guides/authentication)
* [Models](/docs/guides/models) if model synthesis is required

Do not ingest the entire API reference unless the task truly needs broad endpoint discovery.

## When AIsa may not be necessary

A single specialized search provider may be simpler when the workflow uses one source type, does not need reusable Skills, and already has an established model and billing integration.

For product-fit guidance, see [When to use AIsa](/docs/evaluate/when-to-use-aisa).