Output filtering and safety checks in Agentic AI - Model Pipeline Trace

Model Pipeline - Output filtering and safety checks

This pipeline shows how an AI agent filters and checks its outputs to keep responses safe and appropriate before sharing them.

Data Flow - 4 Stages

1Raw Output Generation

1 input prompt→AI model generates raw text output based on input prompt→1 raw text output

"Tell me a joke about cats." -> "Cats are dumb and annoying."

↓

2Output Filtering

1 raw text output→Filter checks for harmful, offensive, or inappropriate content→1 filtered text output or flagged

"Cats are dumb and annoying." -> flagged as inappropriate

↓

3Safety Checks

1 flagged output→Safety module reviews flagged output for policy compliance and ethical guidelines→1 safe text output or rejection

"Here's a funny cat joke instead: Why did the cat sit on the computer? To keep an eye on the mouse!"

↓

4Final Output Delivery

1 safe text output→Deliver safe and appropriate output to user→1 user-facing text output

"Here's a funny cat joke instead: Why did the cat sit on the computer? To keep an eye on the mouse!"

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 basic filtering rules, moderate accuracy
2	0.35	0.80	Improved filtering model reduces false negatives
3	0.28	0.87	Safety checks integrated, accuracy and safety improved
4	0.22	0.91	Fine-tuning reduces false positives, better user experience
5	0.18	0.94	Model converges with high safety and filtering accuracy

Prediction Trace - 4 Layers

Layer 1: Raw Output Generation

Layer 2: Output Filtering

Layer 3: Safety Checks

Layer 4: Final Output Delivery

Model Quiz - 3 Questions

What is the main purpose of the output filtering stage?

A To detect and flag harmful or inappropriate content

B To generate raw text from the input prompt

C To deliver the final output to the user

D To train the AI model

Key Insight

Output filtering and safety checks are crucial steps that help AI models provide responses that are safe, respectful, and appropriate. This layered approach improves user trust and experience by catching and correcting harmful content before it reaches users.

Practice

1. What is the main purpose of output filtering in AI systems?

easy

A. To stop unsafe or unwanted AI results from reaching users

B. To speed up the AI model training process

C. To increase the size of the AI model

D. To add more data to the training set

Solution

1. Step 1: Understand output filtering

   Output filtering is designed to prevent unsafe or unwanted content from being shown to users.

2. Step 2: Compare options

   Only To stop unsafe or unwanted AI results from reaching users describes stopping unsafe or unwanted results, which matches the purpose of output filtering.

3. Final Answer:

   To stop unsafe or unwanted AI results from reaching users -> Option A

4. Quick Check:

   Output filtering = stopping unsafe results [OK]

Hint: Output filtering blocks bad or unsafe AI outputs [OK]

Common Mistakes:

• Confusing filtering with training speed
• Thinking filtering adds data
• Assuming filtering changes model size

2. Which of the following is a correct way to check if an AI output contains a banned word in Python?

easy

A. if output_text.contains(banned_word):

B. if output_text == banned_word:

C. if output_text.index(banned_word):

D. if banned_word in output_text:

Solution

1. Step 1: Recall Python syntax for substring check

   In Python, to check if a substring is in a string, use the 'in' keyword.

2. Step 2: Evaluate options

   if banned_word in output_text: uses 'if banned_word in output_text:', which is correct. if output_text == banned_word: checks equality, not containment. if output_text.contains(banned_word): uses a method that doesn't exist in Python strings. if output_text.index(banned_word): uses index incorrectly and can cause errors.

3. Final Answer:

   if banned_word in output_text: -> Option D

4. Quick Check:

   Substring check in Python uses 'in' [OK]

Hint: Use 'in' keyword to check substring in Python strings [OK]

Common Mistakes:

• Using equality instead of containment
• Using non-existent string methods
• Using index without error handling

3. Given this Python code snippet for filtering AI output:

output = "Hello user!"
banned_words = ["bad", "ugly"]
filtered = any(word in output for word in banned_words)
print(filtered)

What will be the printed output?

medium

A. False

B. True

C. Error

D. None

Solution

1. Step 1: Understand the code logic

   The code checks if any banned word is in the output string using 'any()' with a generator expression.

2. Step 2: Check banned words in output

   Output is "Hello user!". Neither "bad" nor "ugly" is in this string, so 'any()' returns False.

3. Final Answer:

   False -> Option A

4. Quick Check:

   None of banned words in output = False [OK]

Hint: If no banned words found, 'any' returns False [OK]

Common Mistakes:

• Assuming 'any' returns True by default
• Confusing 'any' with 'all'
• Expecting an error from generator expression

4. This code is meant to filter AI output for banned words but causes an error:

output = "Safe text"
banned_words = ["bad", "ugly"]
for word in banned_words:
    if output.index(word):
        print("Banned word found")
        break

What is the error and how to fix it?

medium

A. Syntax error due to missing colon after for loop

B. index() raises ValueError if word not found; use 'in' instead

C. TypeError because output is not a list

D. No error; code works fine

Solution

1. Step 1: Identify the error cause

   Using output.index(word) raises ValueError if word is not found in output string.

2. Step 2: Suggest fix

   Replace 'output.index(word)' with 'word in output' to safely check containment without error.

3. Final Answer:

   index() raises ValueError if word not found; use 'in' instead -> Option B

4. Quick Check:

   index() error fixed by 'in' check [OK]

Hint: Use 'in' to check substring safely, not index() [OK]

Common Mistakes:

• Ignoring ValueError from index()
• Thinking output must be a list
• Missing colons in loops (not in this code)

5. You want to build a safety filter that blocks AI outputs containing banned words or outputs longer than 100 characters. Which approach correctly combines these checks in Python?

hard

A. if banned_words in output or len(output) == 100:
block_output()

B. if all(word in output for word in banned_words) and len(output) < 100:
block_output()

C. if any(word in output for word in banned_words) or len(output) > 100:
block_output()

D. if output.contains(banned_words) or output.length > 100:
block_output()

Solution

1. Step 1: Understand filtering conditions

   The filter should block if any banned word is present OR output length exceeds 100 characters.

2. Step 2: Evaluate options for correct logic and syntax

   if any(word in output for word in banned_words) or len(output) > 100: block_output() uses 'any' to check banned words and 'or' for length > 100, which is correct. if all(word in output for word in banned_words) and len(output) < 100: block_output() uses 'all' and 'and' incorrectly. if output.contains(banned_words) or output.length > 100: block_output() uses invalid methods. if banned_words in output or len(output) == 100: block_output() uses wrong containment and equality checks.

3. Final Answer:

   if any(word in output for word in banned_words) or len(output) > 100: block_output() -> Option C

4. Quick Check:

   Use 'any' + 'or' for combined filter [OK]

Hint: Use 'any' with 'or' to combine banned words and length checks [OK]

Common Mistakes:

• Using 'all' instead of 'any' for banned words
• Using 'and' instead of 'or' to combine conditions
• Using invalid string methods like contains()