Human approval workflows in Agentic AI - Model Metrics & Evaluation

Metrics & Evaluation - Human approval workflows

Which metric matters for Human approval workflows and WHY

In human approval workflows, the key metrics are Precision and Recall. Precision tells us how often the system's approvals are actually correct, which helps avoid unnecessary human reviews. Recall tells us how many truly important cases the system catches for human approval, ensuring no critical decisions are missed. Balancing these metrics ensures the workflow is efficient and safe.

Confusion matrix for Human approval workflows

      |---------------------------|
      |           | Predicted    |
      | Actual    | Approve | Review |
      |-----------|---------|--------|
      | Approve   |   TP    |   FN   |
      | Review    |   FP    |   TN   |
      |---------------------------|

      TP = Correctly auto-approved cases
      FP = Incorrectly auto-approved cases (should be reviewed)
      FN = Cases sent for review but could be auto-approved
      TN = Correctly sent for review
    

Precision vs Recall tradeoff with examples

If the system has high precision, it means most auto-approvals are truly safe, so humans rarely need to fix mistakes. But if recall is low, many cases that could be auto-approved are sent to humans, causing extra work.

If recall is high, the system catches almost all cases that should be auto-approved, reducing human workload. But if precision is low, some unsafe cases slip through without review, risking errors.

Example: In a loan approval system, high precision avoids wrongly approving risky loans automatically. High recall ensures most safe loans are approved without delay.

What "good" vs "bad" metric values look like

Good: Precision and recall both above 90%. This means the system auto-approves mostly correct cases and catches nearly all safe cases, balancing safety and efficiency.

Bad: Precision below 70% means many unsafe cases are auto-approved, risking errors. Recall below 50% means many safe cases are sent to humans unnecessarily, increasing workload.

Common pitfalls in metrics for Human approval workflows

• Accuracy paradox: If most cases are safe, a model that always sends to review can have high accuracy but poor usefulness.
• Data leakage: Using future information in training can inflate metrics but fail in real use.
• Overfitting: Metrics look great on training data but drop on new cases, causing poor real-world performance.
• Ignoring class imbalance: If safe cases are rare, metrics must be carefully chosen to reflect true performance.

Self-check question

Your human approval model has 98% accuracy but only 12% recall on safe cases. Is it good for production? Why not?

Answer: No, it is not good. The low recall means the system misses most safe cases and sends them to humans unnecessarily, increasing workload despite high accuracy. This harms efficiency and defeats the purpose of automation.

Key Result

Precision and recall are key to balance safety and efficiency in human approval workflows.

Practice

1. What is the main purpose of a human approval workflow in AI systems?

easy

A. To have people check AI decisions for important or sensitive tasks

B. To replace AI models with human decision-making completely

C. To speed up AI processing by skipping checks

D. To train AI models without any human input

Solution

1. Step 1: Understand the role of human approval workflows

   Human approval workflows are designed to combine AI with human checks to ensure important decisions are correct and safe.

2. Step 2: Identify the correct purpose

   The main goal is to have humans review AI decisions when needed, especially for sensitive or critical tasks.

3. Final Answer:

   To have people check AI decisions for important or sensitive tasks -> Option A

4. Quick Check:

   Human approval = human checks on AI decisions [OK]

Hint: Human approval means people check AI decisions [OK]

Common Mistakes:

• Thinking human approval replaces AI fully
• Believing it speeds up AI by skipping checks
• Assuming it trains AI without humans

2. Which of the following is the correct way to write a condition that asks for human approval if the AI confidence is below 0.7?

easy

A. if confidence != 0.7: request_approval()

B. if confidence < 0.7: request_approval()

C. if confidence == 0.7: request_approval()

D. if confidence > 0.7: request_approval()

Solution

1. Step 1: Understand the condition logic

   We want to request human approval when confidence is less than 0.7, so the condition should check for values below 0.7.

2. Step 2: Match the correct syntax

   The correct syntax is if confidence < 0.7: followed by the approval request function.

3. Final Answer:

   if confidence < 0.7: request_approval() -> Option B

4. Quick Check:

   Less than 0.7 triggers approval [OK]

Hint: Use < for 'below' conditions in code [OK]

Common Mistakes:

• Using > instead of <
• Checking equality instead of less than
• Using != which triggers on all but 0.7

3. Given this code snippet, what will be printed if confidence = 0.65?

if confidence < 0.7:
    print('Request human approval')
else:
    print('Auto approve')

medium

A. Auto approve

B. No output

C. Request human approval

D. Syntax error

Solution

1. Step 1: Check the condition with given confidence

   Since confidence is 0.65, which is less than 0.7, the condition confidence < 0.7 is true.

2. Step 2: Determine which print statement runs

   Because the condition is true, the code prints 'Request human approval'.

3. Final Answer:

   Request human approval -> Option C

4. Quick Check:

   0.65 < 0.7 triggers approval print [OK]

Hint: Check if confidence is less than threshold to decide output [OK]

Common Mistakes:

• Choosing 'Auto approve' by confusing condition
• Thinking no output occurs
• Assuming syntax error without checking code

4. Identify the error in this human approval workflow code snippet:

def check_approval(confidence):
    if confidence < 0.7
        return 'Request approval'
    else:
        return 'Auto approve'

medium

A. Function missing return statement

B. Wrong comparison operator

C. Indentation error in else block

D. Missing colon after if statement

Solution

1. Step 1: Check syntax of if statement

   The if statement is missing a colon (:) at the end, which is required in Python syntax.

2. Step 2: Verify other parts of the code

   The comparison operator is correct, indentation looks fine, and return statements are present.

3. Final Answer:

   Missing colon after if statement -> Option D

4. Quick Check:

   Python if needs colon [:] [OK]

Hint: Check for colons after if/else statements [OK]

Common Mistakes:

• Ignoring missing colon syntax error
• Thinking indentation is wrong
• Assuming return statements are missing

5. You want to build a human approval workflow that requests approval only if the AI confidence is below 0.7 or if the task is marked as 'high risk'. Which condition correctly implements this logic in Python?

hard

A. if confidence < 0.7 or task == 'high risk': request_approval()

B. if confidence < 0.7 and task == 'high risk': request_approval()

C. if confidence >= 0.7 or task != 'high risk': request_approval()

D. if confidence > 0.7 and task == 'high risk': request_approval()

Solution

1. Step 1: Understand the logic needed

   Approval is requested if confidence is below 0.7 OR the task is 'high risk'. This means either condition triggers approval.

2. Step 2: Match the correct Python condition

   The correct condition uses the 'or' operator to combine the two checks: confidence < 0.7 or task == 'high risk'.

3. Final Answer:

   if confidence < 0.7 or task == 'high risk': request_approval() -> Option A

4. Quick Check:

   Use 'or' for either condition triggering approval [OK]

Hint: Use 'or' to combine conditions for approval [OK]

Common Mistakes:

• Using 'and' instead of 'or' which requires both true
• Reversing comparison operators
• Confusing task string equality