Input validation and sanitization in Agentic AI - Model Pipeline Trace

Model Pipeline - Input validation and sanitization

This pipeline ensures that the data entering the AI system is clean and safe. It checks the input for errors or harmful content and fixes or removes them before the AI uses the data.

Data Flow - 4 Stages

1Raw Input

1000 rows x 5 columns→User provides raw data with possible errors or harmful content→1000 rows x 5 columns

User inputs: ['John', '25', '<script>', 'NY', '100']

↓

2Validation

1000 rows x 5 columns→Check each data entry for correct type, format, and allowed values→1000 rows x 5 columns

Check if '25' is a number, '<script>' is invalid

↓

3Sanitization

1000 rows x 5 columns→Remove or fix invalid or harmful data entries→1000 rows x 5 columns

Replace '<script>' with '' (empty string)

↓

4Clean Data Output

1000 rows x 5 columns→Provide clean and safe data for AI model→1000 rows x 5 columns

Cleaned data: ['John', '25', '', 'NY', '100']

Training Trace - Epoch by Epoch

Loss
0.5 |****
0.4 |*** 
0.3 |**  
0.2 |*   
0.1 |    
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.70	Initial training with some invalid inputs causing noise
2	0.35	0.80	After input validation, model sees cleaner data, improving performance
3	0.28	0.85	Sanitization further reduces noise, model learns better
4	0.22	0.90	Model converges with clean, validated inputs
5	0.18	0.92	Stable low loss and high accuracy achieved

Prediction Trace - 4 Layers

Layer 1: Input Reception

Layer 2: Validation

Layer 3: Sanitization

Layer 4: Model Prediction

Model Quiz - 3 Questions

Why is input validation important before training the model?

A It makes the model run faster by skipping data

B It removes errors and harmful data to improve model learning

C It increases the size of the dataset

D It changes the model architecture

Key Insight

Input validation and sanitization are crucial steps that clean the data before it reaches the AI model. This cleaning helps the model learn better and make more accurate predictions by removing errors and harmful content.

Practice

1. What is the main purpose of input validation in machine learning systems?

easy

A. To train the model with new data

B. To clean the data by removing unwanted characters

C. To check if the input data is the correct type and format

D. To store data securely in a database

Solution

1. Step 1: Understand input validation

   Input validation means checking if the data is the right type and format before using it.

2. Step 2: Differentiate from sanitization

   Input sanitization cleans data, but validation focuses on correctness and format.

3. Final Answer:

   To check if the input data is the correct type and format -> Option C

4. Quick Check:

   Input validation = Check data type and format [OK]

Hint: Validation means checking data type and format [OK]

Common Mistakes:

• Confusing validation with sanitization
• Thinking validation trains the model
• Assuming validation stores data

2. Which of the following is the correct way to validate that an input is a positive integer in Python?

easy

A. if isinstance(input_value, int) and input_value > 0:

B. if type(input_value) == 'int' and input_value > 0:

C. if input_value.isdigit() and input_value > 0:

D. if input_value > 0:

Solution

1. Step 1: Check type correctly

   Use isinstance(input_value, int) to check if input is an integer.

2. Step 2: Check positivity

   Ensure the integer is greater than zero with input_value > 0.

3. Final Answer:

   if isinstance(input_value, int) and input_value > 0: -> Option A

4. Quick Check:

   Use isinstance and > 0 for positive integer check [OK]

Hint: Use isinstance() to check type, then compare value [OK]

Common Mistakes:

• Using type() == 'int' (wrong syntax)
• Calling isdigit() on non-string input
• Skipping type check before comparison

3. Given the code below, what will be the output?

def sanitize_input(text):
    return text.strip().lower()

user_input = '  Hello World!  '
cleaned = sanitize_input(user_input)
print(cleaned)

medium

A. Hello World!

B. !dlroW olleH

C. HELLO WORLD!

D. hello world!

Solution

1. Step 1: Understand strip()

   The strip() method removes spaces from the start and end of the string.

2. Step 2: Understand lower()

   The lower() method converts all letters to lowercase.

3. Final Answer:

   hello world! -> Option D

4. Quick Check:

   strip + lower = 'hello world!' [OK]

Hint: strip removes spaces, lower makes all letters small [OK]

Common Mistakes:

• Ignoring strip() effect on spaces
• Confusing lower() with upper()
• Expecting original casing in output

4. Identify the error in this input validation code snippet:

def validate_age(age):
    if age.isdigit() and age > 0:
        return True
    else:
        return False

medium

A. Comparing string with integer using > operator

B. Using isdigit() on a non-string type

C. Missing return statement in else block

D. Function name is invalid

Solution

1. Step 1: Check isdigit() usage

   isdigit() works on strings, so age should be a string here.

2. Step 2: Identify type mismatch in comparison

   Comparing age > 0 compares string to int, which causes error.

3. Final Answer:

   Comparing string with integer using > operator -> Option A

4. Quick Check:

   String > int comparison causes error [OK]

Hint: Check types before comparing values [OK]

Common Mistakes:

• Assuming isdigit() converts type
• Ignoring type mismatch in comparisons
• Thinking function name affects validation

5. You receive user data as a list of strings representing ages: ['25', ' 30', 'twenty', '40', '']. Which code snippet correctly validates and sanitizes this data to keep only valid positive integers?

hard

A. valid_ages = [age for age in ages if age.isdigit() and age > 0]

B. valid_ages = [int(age.strip()) for age in ages if age.strip().isdigit() and int(age.strip()) > 0]

C. valid_ages = [int(age) for age in ages if age.isnumeric()]

D. valid_ages = [int(age) for age in ages if age.strip() != '']

Solution

1. Step 1: Sanitize input by stripping spaces

   Use age.strip() to remove spaces before validation.

2. Step 2: Validate with isdigit() and positive check

   Check if stripped string is digits only and convert to int to check > 0.

3. Step 3: Convert valid strings to integers

   Use int(age.strip()) to convert valid strings to integers.

4. Final Answer:

   valid_ages = [int(age.strip()) for age in ages if age.strip().isdigit() and int(age.strip()) > 0] -> Option B

5. Quick Check:

   Strip spaces, check digits, convert to int > 0 [OK]

Hint: Strip spaces before isdigit(), then convert and check > 0 [OK]

Common Mistakes:

• Not stripping spaces before validation
• Comparing strings directly to numbers
• Including empty or non-digit strings