Handling tool execution results in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to store the tool's output in a variable.

Agentic AI

tool_output = [1].execute(input_data)

Drag options to blanks, or click blank then click option'

Aexecute

Bresult

Ctool

Dinput_data

Attempts:

3 left

💡 Hint

Common Mistakes

Using the method name instead of the tool object.

Trying to assign input data instead of the output.

The tool object calls the execute method to run the tool and returns the output, which we store in tool_output.

2fill in blank

medium

Complete the code to check if the tool execution was successful.

Agentic AI

if tool_output.[1] == 'success':
    print('Tool ran successfully')

Drag options to blanks, or click blank then click option'

Amessage

Bresult

Coutput

Dstatus

Attempts:

3 left

💡 Hint

Common Mistakes

Checking the wrong attribute like message or output.

Comparing to wrong string values.

The status attribute usually tells if the tool ran successfully.

3fill in blank

hard

Fix the error in accessing the tool's output text.

Agentic AI

print(tool_output.[1]['text'])

Drag options to blanks, or click blank then click option'

Aresponse

Bresult

Coutput

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Using attributes that are strings instead of dictionaries.

Trying to access keys on non-dictionary attributes.

The tool's output text is stored inside the response attribute as a dictionary.

4fill in blank

hard

Fill both blanks to extract and print the tool's confidence score.

Agentic AI

confidence = tool_output.[1].get('[2]', 0)
print(f'Confidence: {confidence}')

Drag options to blanks, or click blank then click option'

Ametadata

Bconfidence

Cinfo

Dscore

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong attribute names like info or confidence as attribute.

Using incorrect key names.

The confidence score is stored inside the metadata dictionary under the key score.

5fill in blank

hard

Fill all three blanks to handle tool output safely with error checking.

Agentic AI

if tool_output.[1] == 'error':
    print('Error:', tool_output.[2])
else:
    print('Result:', tool_output.[3]['text'])

Drag options to blanks, or click blank then click option'

Astatus

Bmessage

Cresponse

Doutput

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up attributes for status and message.

Trying to access text on wrong attribute.

Check status for errors, print the message if error, else print the text inside response.