← Meet AI · What is an AI Agent?

Learning path · Step ④

How do Agents use tools?

Agents don’t only generate text—they call tools to search, read files, run code, hit APIs, and finish real work.

In simple terms:The LLM thinks, tools act, and the Agent decides when to use which tool.

  1. You
  2. "Research the AI agent market"
  3. Agent
  4. 🧠 Think: I need fresh sources
  5. 🔎 Web Search
  6. 🧠 Analyze results
  7. 📄 Read sources
  8. 🧠 Organize findings
  9. 📝 Deliver a report

Why do Agents need tools?

Without tools, an LLM mostly Understands → generates

Explain what an AI Agent is.

It can answer directly.

Find today’s latest AI Agent news.

🔎 Search — for up-to-date information.

Analyze this PDF.

📄 File tools — to read the document.

Write a Python script and run it.

💻 Code execution — to run and verify.

Tools turn AI from “knowing how to answer” into “getting data and taking action.”

What tools can Agents use?

  • Web Search

    Search the open web.

    • Latest sources
    • News research
    • Market scans
    • Competitive intel
  • Files / PDF

    Read and analyze documents.

    • PDFs
    • Docs
    • Reports
    • Data files
  • Code

    Run code and work with data.

    • Python
    • Analysis
    • Charts
    • File transforms
  • API

    Connect to external services.

    1. Weather API
    2. Agent
    3. Get forecast
    4. Database
    5. Agent
    6. Query rows
  • MCP

    An open way to plug in more tools and data.

    What is MCP →

How does an Agent pick a tool?

It’s not always a fixed script—the Agent reasons about the task.

Research AI startups in Tokyo.
  1. Task
  2. 🧠 Agent analyzes
  3. Need fresh info?
  4. Yes
  5. Use Web Search
  6. Results returned
  7. Need more?
  8. Yes → search again
  9. Analyze
  10. Report

Agents choose when—not just whether—to use tools.

What is Tool Calling?

Tool Calling — Tool calling is how an LLM asks an external tool to perform an action and then uses the result.

  1. LLM
  2. "I need to search"
  3. Tool call
  4. Search tool
  5. Returns data
  6. LLM continues

Example

  1. User:
  2. "What's the weather in Tokyo now?"
  3. Agent / LLM
  4. "Need weather data"
  5. Call Weather Tool
  6. Tool returns data
  7. Agent / LLM interprets
  8. Reply to user

The tool itself need not be AI—a search API, database, calculator, or script can all be tools.

The full tool loop

  1. User goal
  2. Understand task
  3. Plan next step
  4. Pick a tool
  5. Call tool
  6. Get result
  7. Analyze
  8. Decide next step
  9. Call again if needed
  10. Finish

🔎 Research Agent

  1. Understand task
  2. Plan research
  3. Search the market
  4. Read sources
  5. Compare companies
  6. Analyze trends
  7. Organize notes
  8. Write report

In progress

Research the AI agent market.
  • Understand the task
  • Create a plan
  • Search sources
  • Read materials
  • Analyze the market
  • Draft the report

Can one Agent use many tools?

Yes—and that’s where Agents get powerful.

  1. Research Agent
  2. 🔎 Search 📄 Files 💻 Code
  3. 🧠 LLM
  4. 📝 Report
  1. CSV file
  2. File tool
  3. Code tool
  4. Analysis
  5. Charts
  6. Report

Complex Agents orchestrate several tools—not just one.

Will Agents misuse tools?

Good systems put guardrails in place:

  • Permissions

    What can the Agent reach—files, DB, internet?

  • Parameters

    What inputs is each tool allowed to accept?

  • Scope

    Read-only vs modify vs delete—explicitly bounded.

  1. Agent
  2. Tool
  3. Permission check
  4. Allow → run
  5. Deny → stop

“I’m about to send this email—please confirm.”

This leads to permissions and human-in-the-loop on serious actions.

Tool vs Agent

ToolAgent
One capabilityOne goal
Waits to be calledPlans the next step
Search, calc, read fileResearch, write, build
A componentThe task system
“Do this action”“Help me finish this”

🔎 Search tool: run this query.

🧠 Research Agent: research this topic.

  1. Search → read → search again → compare → analyze → report

Tools are abilities; Agents orchestrate them toward an outcome.

How does MCP relate to Agent tools?

  1. Agent
  2. Tool
  3. MCP
  4. External tools / data / services

MCP standardizes how Agents discover and connect external tools and data—without a custom plugin per app.

What is MCP →

Why Agent + tools matter

Before

  1. You
  2. Find information
  3. Operate apps
  4. Call services
  5. Compile results

Now

  1. You
  2. State a goal
  3. Agent
  4. Uses tools
  5. Many steps
  6. Delivers outcome

Tools give Agents “hands and feet.”

The LLM supplies understanding and reasoning.

The Agent wires it together into finished work.

Try it for real

Try an Agent that searches, analyzes, and reports—not just chat.

Try Research Agent →

Keep exploring