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

# Research

> Competitive intelligence, due diligence, and market analysis with cited briefs

**Research** agents answer complex questions: how a company is positioned, what the risks are in a deal, what changed in a market last quarter. The agent plans the task, works dozens of sources, and returns a brief with [every claim cited](/nimble-sdk/web-search-agents/trust).

## Example Request

A due-diligence task using the `due-diligence` template:

<CodeGroup>
  ```python Python theme={"system"}
  agent = nimble.agents.create(template="due-diligence")

  run = nimble.agents.runs.create(
      agent.id,
      input=(
          "Research Acme Corp before a deal or investment: financial health, "
          "leadership team, legal and regulatory history, and key risks."
      ),
  )
  ```

  ```typescript TypeScript theme={"system"}
  const agent = await nimble.agents.create({ template: "due-diligence" });

  const run = await nimble.agents.runs.create(agent.id, {
    input:
      "Research Acme Corp before a deal or investment: financial health, " +
      "leadership team, legal and regulatory history, and key risks.",
  });
  ```

  ```go Go theme={"system"}
  agent, err := client.Agents.New(ctx, nimble.AgentNewParams{
      Template: param.NewOpt("due-diligence"),
  })

  run, err := client.Agents.Runs.New(ctx, agent.ID, nimble.AgentRunNewParams{
      Input: "Research Acme Corp before a deal or investment: financial health, " +
          "leadership team, legal and regulatory history, and key risks.",
  })
  ```

  ```bash CLI theme={"system"}
  AGENT_ID=$(nimble agents create --template due-diligence | jq -r .id)

  nimble agents:runs create \
    --agent-id "$AGENT_ID" \
    --input "Research Acme Corp before a deal or investment: financial health, leadership team, legal and regulatory history, and key risks."
  ```

  ```bash cURL theme={"system"}
  curl -X POST "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs" \
    --header 'Authorization: Bearer <YOUR-API-KEY>' \
    --header 'Content-Type: application/json' \
    --data '{
      "input": "Research Acme Corp before a deal or investment: financial health, leadership team, legal and regulatory history, and key risks."
    }'
  ```
</CodeGroup>

## Example Response

The result is a brief with numbered callouts, plus a trust report grading every claim and quoting the page it came from:

```json theme={"system"}
{
  "type": "text",
  "content": "Acme Corp is in stable financial health. Net sales for fiscal 2025 were $194 million, up 4% year over year [1]. Leadership is stable around a long-tenured CEO [2]. The key risks are customer concentration — the five largest customers account for a significant share of net sales [3] — and pending litigation disclosed in the latest 10-K [4]...",
  "trust": {
    "confidence": "high",
    "reasoning": "Financial and risk claims backed by SEC filings; leadership confirmed by the latest proxy statement.",
    "claims": [
      {
        "callout": 1,
        "confidence": "high",
        "reasoning": "Backed by a primary source (official)",
        "citations": [
          {
            "url": "https://www.sec.gov/.../acme-10k-2025.htm",
            "title": "Acme Corp Form 10-K",
            "excerpts": ["Net sales in 2025 were $194.0 million, an increase of 4%"],
            "source_category": "official"
          }
        ]
      }
    ]
  }
}
```

A `low`-confidence flag marks the claims that need human review.

## Configuration

* **Goals** define the requirements. *"Provides an overall sentiment score with a clear methodology"*, *"Includes recent product announcements from the past 6 months"* — the agent checks each on every run.
* **Skill** defines the analysis approach. The `competitive-intelligence` template ships a full analyst briefing: pricing architecture, ICP, GTM motion, differentiators. Write your own to match how your team analyzes.
* **[Effort](/nimble-sdk/web-search-agents/efforts)** sets the depth. `low` for a daily news sweep, `x-high` for pre-deal diligence.
* **Sources** set the evidence bar. *"prioritize: SEC filings and official statements"* controls which sources the agent trusts, not just which it reads.

## Templates

| Template                   | Built for                                                           |
| -------------------------- | ------------------------------------------------------------------- |
| `competitive-intelligence` | Pricing, positioning, and feature comparison across competitors     |
| `due-diligence`            | Pre-deal company investigation: financials, leadership, legal, risk |
| `brand-intelligence`       | Sentiment and themes across social and news, with incidents flagged |
| `company-profile`          | Fast, sourced company one-pagers                                    |
| `price-comparison`         | Cross-retailer price and availability checks                        |
| `real-estate-research`     | Property and market research                                        |

<Card title="Quickstart" icon="rocket" href="/nimble-sdk/web-search-agents/quickstart">
  The create → wait → retrieve flow works for every research agent
</Card>