Deep research and analysis

Combine Team modes, Workflow steps, grounding, and typed research outputs.

Research, strategy, and investment teams use deep research systems when a question requires several independent investigations and a decision-ready deliverable. Agno combines specialist teams, explicit workflows, parallel execution, knowledge, and typed outputs so each stage and final result can be inspected.

These are composition examples adapted from the Investment Team application. Follow its clone, database, credentials, and research-loading setup for a complete application. Its agents/, teams/, and workflows/ define the components referenced here; agents/settings.py supplies shared knowledge and paths.

Import those components into your application module, or define your own before composing them. The application uses Gemini; the OpenAI variants on these pages require uv pip install "agno[openai]" and OPENAI_API_KEY as well. Shared knowledge/storage still needs the application's database and embedding-provider setup. Prose context, analyst-output variables, and local archives must be supplied by your application.

from agno.workflow import Parallel, Step, Workflow

# The analyst agents are defined separately. See the investment-team repo
# under Developer Resources for the full set.
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.
# result.step_results holds the output from each outer step.

This review has five stages, with fundamental and technical analysis running in parallel. Replace the investment agents and prompt to apply the pattern to another research mandate. Attach a database to the Workflow to keep each run's input, step outputs, and final result.

Deep research patterns

Orchestration patterns

Route, coordinate, broadcast, task, and explicit Workflow pipelines.

Parallel investigation

Run independent specialists concurrently, then synthesize their results.

Grounding research

Give each specialist a mandate, a research library, and access to prior work.

Structured deliverable

Return a typed decision and preserve its supporting memo.

Institutional learning

Share reviewed learnings through a common store and namespace.

Serve and embed

Expose the pipeline through AgentOS for applications, schedules, and dashboards.

Developer Resources