Branching and conditional logic in Agentic AI - Model Metrics & Evaluation

Metrics & Evaluation - Branching and conditional logic

Which metric matters for Branching and conditional logic and WHY

Branching and conditional logic in AI often control decision paths. To evaluate these decisions, accuracy is a key metric because it shows how often the logic leads to correct outcomes. However, if decisions split into categories with uneven importance, precision and recall become important to measure how well the logic handles specific cases.

Confusion matrix example

      Predicted
      |  Yes  |  No  |
    -------------------
    Yes |  40  |  10  |
    No  |  5   |  45  |

    TP = 40, FP = 10, FN = 5, TN = 45
    Total samples = 100
    

This matrix shows how many times the branching logic predicted "Yes" or "No" correctly or incorrectly.

Precision vs Recall tradeoff with examples

If the logic is used to approve loans, precision matters to avoid approving bad loans (false positives). High precision means most approved loans are good.

If the logic is used to detect fraud, recall matters to catch as many fraud cases as possible. High recall means few fraud cases are missed.

Good vs Bad metric values for branching logic

Good: Accuracy above 90%, precision and recall balanced above 85%, showing reliable decisions.

Bad: Accuracy high but recall very low (e.g., 20%), meaning many important cases are missed.

Common pitfalls in metrics

• Accuracy paradox: High accuracy can be misleading if classes are imbalanced.
• Data leakage: If future info leaks into logic, metrics look better but model fails in real use.
• Overfitting: Logic fits training data perfectly but performs poorly on new data.

Self-check question

Your branching logic model has 98% accuracy but only 12% recall on fraud cases. Is it good for production? Why or why not?

Answer: No, because it misses most fraud cases (low recall). High accuracy is misleading if fraud is rare but important to catch.

Key Result

For branching and conditional logic, balance precision and recall to ensure decisions are both accurate and meaningful.

Practice

1. What does branching in agentic AI primarily help with?

easy

A. Speeding up calculations without decisions

B. Storing large amounts of data

C. Visualizing data in graphs

D. Choosing actions based on conditions

Solution

1. Step 1: Understand the purpose of branching

   Branching allows AI to make choices depending on different conditions it checks.

2. Step 2: Match branching to its main use

   Choosing actions based on conditions is exactly what branching does in AI decision-making.

3. Final Answer:

   Choosing actions based on conditions -> Option D

4. Quick Check:

   Branching = Choosing actions [OK]

Hint: Branching means picking actions by checking conditions [OK]

Common Mistakes:

• Confusing branching with data storage
• Thinking branching speeds up calculations only
• Mixing branching with visualization tasks

2. Which of the following is the correct syntax to start a conditional branch in agentic AI code?

easy

A. if condition:

B. when condition then

C. check condition {}

D. condition if:

Solution

1. Step 1: Recall correct conditional syntax

   In agentic AI (like Python), conditions start with 'if' followed by the condition and a colon.

2. Step 2: Compare options to syntax rules

   Only 'if condition:' matches the correct syntax for starting a branch.

3. Final Answer:

   if condition: -> Option A

4. Quick Check:

   Correct syntax starts with 'if' and colon [OK]

Hint: Remember: 'if' + condition + colon starts a branch [OK]

Common Mistakes:

• Using 'when' instead of 'if'
• Missing colon after condition
• Placing condition after 'if' incorrectly

3. What will this agentic AI code print?

score = 75
if score >= 90:
    print('Excellent')
elif score >= 60:
    print('Good')
else:
    print('Needs Improvement')

medium

A. Excellent

B. Good

C. Needs Improvement

D. No output

Solution

1. Step 1: Check the score against conditions

   Score is 75, which is not >= 90, so first condition fails.

2. Step 2: Check elif condition

   75 is >= 60, so 'Good' will be printed.

3. Final Answer:

   Good -> Option B

4. Quick Check:

   75 >= 60 triggers 'Good' [OK]

Hint: Check conditions top to bottom, first true runs [OK]

Common Mistakes:

• Choosing 'Excellent' because 75 is high
• Ignoring elif and jumping to else
• Thinking no output if first condition fails

4. Identify the error in this agentic AI branching code:

if temperature > 30
    print('Hot')
elif temperature > 20:
    print('Warm')

medium

A. Missing colon after first if condition

B. Incorrect indentation of print statements

C. Using elif without else

D. Wrong comparison operator

Solution

1. Step 1: Check syntax of if statement

   The first if line lacks a colon at the end, which is required.

2. Step 2: Verify other parts

   Indentation and elif usage are correct; comparison operator is valid.

3. Final Answer:

   Missing colon after first if condition -> Option A

4. Quick Check:

   Colon needed after if condition [OK]

Hint: Every if/elif line must end with a colon ':' [OK]

Common Mistakes:

• Thinking elif needs else after it
• Confusing indentation errors with missing colon
• Believing comparison operators are wrong

5. You want an agentic AI to classify a number as 'Positive', 'Negative', or 'Zero'. Which branching structure correctly handles all cases?

hard

A. if num > 0:\n print('Positive')\nif num < 0:\n print('Negative')\nelse:\n print('Zero')

B. if num >= 0:\n print('Positive')\nelse:\n print('Negative')

C. if num > 0:\n print('Positive')\nelif num < 0:\n print('Negative')\nelse:\n print('Zero')

D. if num != 0:\n print('Positive or Negative')\nelse:\n print('Zero')

Solution

1. Step 1: Check if all cases are covered

   if num > 0:\n print('Positive')\nelif num < 0:\n print('Negative')\nelse:\n print('Zero') checks if number is greater than zero, less than zero, and else covers zero exactly.

2. Step 2: Verify exclusivity and correctness

   if num >= 0:\n print('Positive')\nelse:\n print('Negative') misses zero case as separate; C prints multiple lines incorrectly; D groups positive and negative together.

3. Final Answer:

   if num > 0:\n print('Positive')\nelif num < 0:\n print('Negative')\nelse:\n print('Zero') -> Option C

4. Quick Check:

   All cases handled exclusively in if num > 0:\n print('Positive')\nelif num < 0:\n print('Negative')\nelse:\n print('Zero') [OK]

Hint: Use if, elif, else to cover all number cases [OK]

Common Mistakes:

• Missing zero case
• Using multiple ifs causing multiple prints
• Grouping positive and negative together