Custom agent logic in LangChain - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ component_behavior

intermediate

What is the output of this custom LangChain agent logic?

Consider this LangChain custom agent code snippet. What will be printed when the agent runs the input 'Hello'?

LangChain

from langchain.agents import AgentExecutor, Tool
from langchain.schema import AgentAction, AgentFinish

class CustomAgent:
    def plan(self, intermediate_steps, **kwargs):
        if len(intermediate_steps):
            return self.finish(intermediate_steps, **kwargs)
        return AgentAction(tool="echo", tool_input=kwargs.get("input", ""), log="Echoing input")

    def finish(self, intermediate_steps, **kwargs):
        print("Done")
        return AgentFinish(return_values={"output": "Done"}, log="Finished")

class EchoTool:
    def run(self, input_text):
        print(f"Echo: {input_text}")
        return input_text

agent = CustomAgent()
tool = Tool(name="echo", func=EchoTool().run, description="Echoes input")
executor = AgentExecutor(agent=agent, tools=[tool])
executor.run("Hello")

A Echo: Hello

B

Echo: Hello
Done

C

Hello
Done

D Done

💡 Hint

Look at what the EchoTool prints and what the agent returns as output.

The EchoTool prints 'Echo: Hello' to the console and returns the input. The agent finishes with output 'Done'. So the printed output includes both lines.

❓ state_output

intermediate

What is the final output value of this LangChain custom agent?

Given this custom agent logic, what is the final output returned by the agent executor?

LangChain

from langchain.agents import AgentExecutor, Tool
from langchain.schema import AgentAction, AgentFinish

class IncrementAgent:
    def __init__(self):
        self.counter = 0

    def plan(self, intermediate_steps, **kwargs):
        self.counter += 1
        if self.counter < 3:
            return AgentAction(tool="increment", tool_input=self.counter, log=f"Increment to {self.counter}")
        else:
            return AgentFinish(return_values={"output": self.counter}, log="Done")

class IncrementTool:
    def run(self, input_num):
        return input_num + 1

agent = IncrementAgent()
tool = Tool(name="increment", func=IncrementTool().run, description="Increments number")
executor = AgentExecutor(agent=agent, tools=[tool])
result = executor.run(0)

A 0

B 4

C 2

D 3

💡 Hint

Count how many times the agent plans and what it returns at finish.

The agent increments counter each plan call. It plans twice with counter 1 and 2, then finishes at 3. The final output is 3.

📝 Syntax

advanced

Which option causes a syntax error in this LangChain custom agent code?

Identify which code snippet will cause a syntax error when defining a custom agent in LangChain.

A

class MyAgent
    def plan(self, intermediate_steps, **kwargs):
        return AgentAction(tool="search", tool_input=kwargs.get("query"), log="Searching")

B

class MyAgent:
    def plan(self, intermediate_steps, **kwargs):
        return AgentAction(tool="search", tool_input=kwargs.get("query"), log="Searching")
    def finish(self, intermediate_steps, **kwargs):
        return AgentFinish(return_values={"output": "done"}, log="Finished")

C

)"dehsiniF"=gol ,}"enod" :"tuptuo"{=seulav_nruter(hsiniFtnegA nruter        
:)sgrawk** ,spets_etaidemretni ,fles(hsinif fed    
)"gnihcraeS"=gol ,)"yreuq"(teg.sgrawk=tupni_loot ,"hcraes"=loot(noitcAtnegA nruter        
:)sgrawk** ,spets_etaidemretni ,fles(nalp fed    
:tnegAyM ssalc

D

class MyAgent:
    def plan(self, intermediate_steps, **kwargs):
        return AgentAction(tool="search", tool_input=kwargs.get("query"), log="Searching")

💡 Hint

Check the class definition syntax carefully.

Option A is missing the colon ':' after the class name, causing a syntax error.

🔧 Debug

advanced

Which option will cause a runtime error when running this LangChain custom agent?

Given this custom agent and tool setup, which option will cause a runtime error when the agent executor runs?

LangChain

from langchain.agents import AgentExecutor, Tool
from langchain.schema import AgentAction, AgentFinish

class FaultyAgent:
    def plan(self, intermediate_steps, **kwargs):
        return AgentAction(tool="missing_tool", tool_input="test", log="Trying missing tool")

agent = FaultyAgent()
tool = Tool(name="existing_tool", func=lambda x: x, description="A working tool")
executor = AgentExecutor(agent=agent, tools=[tool])
executor.run("input")

A RuntimeError: Tool 'missing_tool' not found

B TypeError: 'NoneType' object is not callable

C No error, returns 'test'

D SyntaxError: invalid syntax

💡 Hint

Check if the tool name used by the agent matches any tool in the executor.

The agent tries to use a tool named 'missing_tool' which is not in the tools list, causing a runtime error.

🧠 Conceptual

expert

How does custom agent logic affect LangChain's decision-making process?

Which statement best describes the role of custom agent logic in LangChain's agent execution?

A Custom agent logic replaces the entire LangChain framework and runs independently.

B Custom agent logic only formats the final output without influencing tool selection or planning.

C Custom agent logic defines how the agent chooses tools and processes intermediate steps to decide next actions.

D Custom agent logic is responsible for loading external data sources automatically without user input.

💡 Hint

Think about what planning and finishing methods control in an agent.

Custom agent logic controls the agent's planning and finishing steps, deciding which tools to use and when to stop.