Sequential step execution in Agentic AI - ML Experiment: Train & Evaluate

Experiment - Sequential step execution

Problem:You want to build an AI agent that completes a task by following steps one after another in the right order.

Current Metrics:The agent completes 60% of tasks successfully but often skips or repeats steps, causing errors.

Issue:The agent does not reliably follow the sequence of steps, leading to mistakes and lower task success.

Your Task

Improve the agent so it executes steps strictly in order, increasing task success rate to at least 85%.

You cannot change the task steps themselves.

You must keep the agent's step execution logic simple and interpretable.

Hint 1

Hint 2

Hint 3

Solution

Agentic AI

class SequentialAgent:
    def __init__(self, steps):
        self.steps = steps
        self.current_step = 0

    def execute_next(self):
        if self.current_step < len(self.steps):
            step = self.steps[self.current_step]
            print(f"Executing step {self.current_step + 1}: {step}")
            self.current_step += 1
            return True
        else:
            print("All steps completed.")
            return False

    def reset(self):
        self.current_step = 0

# Example usage
steps = ["Gather ingredients", "Mix ingredients", "Bake", "Cool down", "Serve"]
agent = SequentialAgent(steps)

while agent.execute_next():
    pass

# Output shows steps executed in order without skipping or repeating

Added a current_step tracker to remember which step to do next.

Implemented execute_next method to run steps strictly in order.

Prevented skipping or repeating by only moving forward one step at a time.

Results Interpretation

Before: 60% success, steps skipped or repeated.
After: 90% success, steps executed strictly in order.

Tracking the current step and enforcing order helps the agent complete tasks reliably without mistakes.

Bonus Experiment

Now try adding the ability for the agent to go back one step if an error is detected.

💡 Hint

Add a method to decrement current_step safely and re-execute that step.

Practice

1. What is the main benefit of using sequential step execution in AI tasks?

easy

A. It allows AI to skip steps randomly for faster results.

B. It combines all steps into one complex function for efficiency.

C. It breaks tasks into clear, ordered actions making them easier to understand.

D. It removes the need for debugging AI processes.

Solution

1. Step 1: Understand the concept of sequential step execution

   Sequential step execution means breaking a task into small, ordered steps.

2. Step 2: Identify the benefit in AI tasks

   This approach makes AI tasks easier to build, understand, and debug by following clear steps.

3. Final Answer:

   It breaks tasks into clear, ordered actions making them easier to understand. -> Option C

4. Quick Check:

   Sequential steps = clear, ordered actions [OK]

Hint: Think: clear steps make tasks easier to follow [OK]

Common Mistakes:

• Thinking steps can be skipped randomly
• Believing all steps combine into one complex function
• Assuming debugging is not needed

2. Which of the following is the correct way to represent sequential steps in Python for an AI task?

easy

A. def step1(): pass
step1
step2()

B. def step1(): pass
def step2(): pass
step1()
step2()

C. def step1(): pass
step1()
step2()

D. step1 = step2 = pass
step1()
step2()

Solution

1. Step 1: Check function definitions and calls

   def step1(): pass def step2(): pass step1() step2() defines two functions and calls them in order, which is correct syntax.

2. Step 2: Identify syntax errors in other options

   step1 = step2 = pass step1() step2() assigns pass incorrectly; def step1(): pass step1() step2() calls undefined step2; def step1(): pass step1 step2() misses parentheses in step1 call.

3. Final Answer:

   def step1(): pass\ndef step2(): pass\nstep1()\nstep2() -> Option B

4. Quick Check:

   Correct function definition and call = def step1(): pass def step2(): pass step1() step2() [OK]

Hint: Functions must be defined and called with parentheses [OK]

Common Mistakes:

• Calling functions without parentheses
• Using invalid assignments like step1 = pass
• Calling functions not defined

3. What will be the output of this code?

def step1():
    return 5

def step2(x):
    return x * 2

result = step2(step1())
print(result)

medium

A. 10

B. None

C. 5

D. Error

Solution

1. Step 1: Execute step1()

   step1() returns 5.

2. Step 2: Pass result to step2()

   step2(5) returns 5 * 2 = 10.

3. Final Answer:

   10 -> Option A

4. Quick Check:

   step2(step1()) = 10 [OK]

Hint: Follow function calls inside out to find output [OK]

Common Mistakes:

• Confusing return values
• Forgetting to pass step1() output to step2()
• Expecting print to show None

4. Identify the error in this sequential step code:

def step1():
    print("Step 1 done")

def step2():
    print("Step 2 done")

step1
step2()

medium

A. Print statements are incorrect

B. step2 is not defined

C. Syntax error in function definitions

D. Missing parentheses when calling step1

Solution

1. Step 1: Check function calls

   step1 is referenced without parentheses, so it is not called.

2. Step 2: Confirm other parts

   step2() is called correctly; function definitions and print statements are correct.

3. Final Answer:

   Missing parentheses when calling step1 -> Option D

4. Quick Check:

   Function calls need parentheses [OK]

Hint: Always use () to call functions [OK]

Common Mistakes:

• Forgetting parentheses on function calls
• Thinking print statements cause errors
• Assuming function definitions are wrong

5. You want to build an AI agent that processes data in three steps: load data, clean data, and analyze data. Which sequence of function calls correctly follows sequential step execution?

hard

A. load_data()
clean_data()
analyze_data()

B. analyze_data(clean_data(load_data()))

C. clean_data(load_data())
analyze_data()

D. load_data()
analyze_data()
clean_data()

Solution

1. Step 1: Understand the data flow

   Data must be loaded first, then cleaned, then analyzed in order.

2. Step 2: Check function call order

   Calling load_data(), then clean_data(), then analyze_data() in sequence preserves the correct order and clarity.

3. Final Answer:

   load_data() clean_data() analyze_data() -> Option A

4. Quick Check:

   Sequential calls preserve step order clearly [OK]

Hint: Call functions in order to keep correct step sequence [OK]

Common Mistakes:

• Calling analyze before cleaning data
• Calling steps out of order
• Not passing data between steps