Task 7 · 8 tasks

Agents as tools

Split the work: an orchestrator routes to a data specialist and a weather specialist.

30 minAdvanced

Alice’s ask

The “Overloaded Agent” problem

Alice now wants headcounts and the weather for her next business trip. One agent with every tool and every instruction gets confused. Build a small team instead.

You

Build it

Build the team

Challenge

Create two specialists, data_agent (database tools plus the approval hook) and weather_agent (HTTP requests to the US National Weather Service), and an orchestrator that routes to them.

Work in phase1/starter/t7_agents_as_tools.py (look for TODO; an unfinished one prints [starter] TODO …) and run it with uv run bootcamp.py phase1 t7 --starter. The reference solution is phase1/t7_agents_as_tools.py; uv run bootcamp.py phase1 t7 runs it.

Hint 1

Any function decorated with @tool is a tool, so a function that runs another agent is one too. This is the “agents as tools” pattern. See Strands: agents as tools.

Hint 2

Each specialist gets its own prompt and tools; its docstring tells the orchestrator when to use it. The weather agent uses http_request from strands.vended_tools and https://api.weather.gov/points/{lat},{lon}.

sketchread only

@tool
def data_agent(query: str) -> str:
    """<when to use me>"""
    return str(Agent(model=..., system_prompt=..., tools=db_tools, hooks=[...])(query))

Solution

phase1/t7_agents_as_tools.py

@tool
def data_agent(query: str) -> str:
    """Query and analyze the DataStream Corp database: employee counts, department statistics, any SQL question.

    Args:
        query: A database or data analysis question.
    """
    specialist = Agent(
        model=make_model(),
        system_prompt="You are a data specialist. Query the database to answer questions.",
        tools=db_tools,
        hooks=[ApprovalHook()],
        callback_handler=None,
    )
    return str(specialist(query))


# weather_agent: same pattern with tools=[http_request] and WEATHER_PROMPT

orchestrator = Agent(
    name="Executive Assistant",
    model=make_model(),
    system_prompt=ORCHESTRATOR_PROMPT,
    tools=[data_agent, weather_agent],
)

Run it

terminal · your starter file

uv run bootcamp.py phase1 t7 --starter "How many employees are in Engineering?"
uv run bootcamp.py phase1 t7 --starter "What is the weather in Seattle?"
uv run bootcamp.py phase1 t7 --starter "How many employees do we have and what is the weather in New York?"

terminal · reference solution

uv run bootcamp.py phase1 t7 "How many employees are in Engineering?"
uv run bootcamp.py phase1 t7 "What is the weather in Seattle?"
uv run bootcamp.py phase1 t7 "How many employees do we have and what is the weather in New York?"

Experiments
- Watch the [data_agent] / [weather_agent] lines: what question does the orchestrator actually pass down?
- Try MODEL_ID=claude-sonnet-5-5 for the combined question, then check uv run bootcamp.py llm. Was the better routing worth the spend?
- Add a third specialist, for example one that returns a DepartmentReport.

Check your work

Phase 1 has no automated test: you check it by running the task and looking for the result below.

Database questions go to data_agent, weather questions to weather_agent, and the combined question calls both and merges the answers.

Under the hood

A @tool is a function with a schema derived from its signature and docstring, so a function that runs another agent is a tool too. Each specialist has its own prompt, tools and context, which keeps prompts short and failures contained. This orchestrator is what you deploy to AgentCore Runtime in Phase 2, Task 4.