> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc-agui.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Deep research and analysis

> Orchestrate agents for grounded, auditable research and structured deliverables.

The gap between an agent using tools and a deep research system is orchestration, grounding, and auditable deliverables. Agno lets you build a deterministic, step-based research pipeline in a few lines. Run steps in parallel, in loops, or one after the other.

```python theme={null}
from agno.workflow import Parallel, Step, Workflow

investment_workflow = Workflow(
    id="investment-workflow",
    name="Investment Review Pipeline",
    steps=[
        Step(name="Market Assessment", agent=market_analyst),
        Parallel(
            Step(name="Fundamental Analysis", agent=financial_analyst),
            Step(name="Technical Analysis", agent=technical_analyst),
            name="Deep Dive",
        ),
        Step(name="Risk Assessment", agent=risk_officer),
        Step(name="Investment Memo", agent=memo_writer),
        Step(name="Committee Decision", agent=committee_chair),
    ],
)

result = investment_workflow.run("Run a full investment review on NVDA")
# result.content holds the Committee Decision. Same steps, every run.
```

That is an auditable five-step review with a parallel deep-dive. Swap the agents and the mandate and the same shape researches anything.

## Learn How To

| Concern                      | Page                                                                      |
| ---------------------------- | ------------------------------------------------------------------------- |
| Pick the orchestration shape | [Orchestration patterns](/use-cases/deep-research/orchestration-patterns) |
| Run specialists in parallel  | [Parallel investigation](/use-cases/deep-research/parallel-investigation) |
| Ground every agent           | [Grounding research](/use-cases/deep-research/grounding-research)         |
| End in an auditable artifact | [Structured deliverable](/use-cases/deep-research/structured-deliverable) |
| Make research compound       | [Institutional learning](/use-cases/deep-research/institutional-learning) |
| Put it behind a surface      | [Serve and embed](/use-cases/deep-research/serve-and-embed)               |

## Explore

<CardGroup cols={2}>
  <Card title="Orchestration patterns" icon="diagram-project" href="/use-cases/deep-research/orchestration-patterns">
    Route, coordinate, broadcast, task, and deterministic pipelines.
  </Card>

  <Card title="Parallel investigation" icon="arrows-split-up-and-left" href="/use-cases/deep-research/parallel-investigation">
    Fan specialists out at once, synthesize the results.
  </Card>

  <Card title="Grounding research" icon="book-open" href="/use-cases/deep-research/grounding-research">
    Mandate in the prompt, a library in RAG, prior work on disk.
  </Card>

  <Card title="Structured deliverable" icon="file-contract" href="/use-cases/deep-research/structured-deliverable">
    End in a memo and a decision, with citations and conviction.
  </Card>

  <Card title="Institutional learning" icon="arrows-rotate" href="/use-cases/deep-research/institutional-learning">
    Shared learnings so the next review starts ahead.
  </Card>
</CardGroup>

## Developer Resources

* [Workflows](/workflows/overview)
* [Teams](/teams/overview)
* [Workflows cookbook](https://github.com/agno-agi/agno/tree/main/cookbook/04_workflows)
* [Investment committee on GitHub](https://github.com/agno-agi/investment-team)