# Agno market research

- **Agent pattern:** Bounded tool loop
- **Search surfaces:** Web, news, and shopping
- **Saved artifact:** `agno-market-research.md`


# What you'll build

An Agno agent that assesses the US market for home espresso grinders under USD 800. It separates durable category and manufacturer facts from recent launches and time-sensitive marketplace signals, then writes a decision-ready market report.

**Default brief:** Map the category, representative products, gaps, and risks. Treat live price and availability as signals--not permanent product facts--and include source URLs.


# How the agent works

1.  **Frame the category.** Web search establishes segments, manufacturers, and durable product facts.
2.  **Check current signals.** News finds launches while shopping search captures live prices and availability.
3.  **Reconcile the market.** The agent compares the evidence, calls out gaps, and stays within a ten-call tool budget.


# Core agent setup

This abridged excerpt keeps the Agno agent and tool boundary in view. The full script also handles model configuration, environment validation, and Markdown output.

``` python
agent = Agent(
    name="SerpApi market researcher",
    model=model,
    instructions=[
        "Search before making market claims.",
        "Use the most specific SerpApi tool for each question.",
        "Separate live listing signals from durable category facts.",
    ],
    tools=[
        web_search(provider="agno", allowed_engines=["google_light", "bing"]),
        news_search(provider="agno"),
        shopping_search(provider="agno"),
    ],
    markdown=True,
    tool_call_limit=10,
)
response = agent.run(PROMPT)
```

[View the complete `main.py` →](https://github.com/serpapi/serpapi-search-tools-python/blob/main/cookbook/agno/main.py)


# Run the recipe

Set `SERPAPI_API_KEY` and `XAI_API_KEY` in the repository-root `.env`, then run:

``` bash
uv run --isolated --no-project --with 'serpapi-search-tools[agno]' --with python-dotenv cookbook/agno/main.py
```

Optional controls: `XAI_MODEL`, `XAI_BASE_URL`, `COOKBOOK_PROMPT`, and `COOKBOOK_OUTPUT_DIR`.

**Portable environment:** `--isolated --no-project` runs the local recipe against the published `serpapi-search-tools[agno]` package instead of importing this checkout.


# Inspect the result

The recipe writes `cookbook-output/agno-market-research.md`. Expect category segments, representative products, current price signals, market gaps, risks, and direct source URLs.

The same report is printed to the terminal. Set `COOKBOOK_OUTPUT_DIR` to move the saved artifact, or `COOKBOOK_PROMPT` to research another category.


# SerpApi tools used

[web_search](../../reference/web_search.md#serpapi_search_tools.web_search) supplies category and manufacturer facts, [news_search](../../reference/news_search.md#serpapi_search_tools.news_search) tracks recent launches, and [shopping_search](../../reference/shopping_search.md#serpapi_search_tools.shopping_search) captures current prices and availability. Keeping these result types separate helps the agent label which signals are durable and which may change quickly.

**Framework pattern:** The agent structure is inspired by Agno's parallel market research cookbook; this recipe applies it to three SerpApi evidence surfaces.

- [Open the runnable recipe](https://github.com/serpapi/serpapi-search-tools-python/tree/main/cookbook/agno)
- [View Agno's source example](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/parallel/market_research.py)