Choosing the right framework in Agentic AI - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing a framework for real-time image classification

You want to build a real-time image classification app on a mobile device. Which framework is best suited for this task?

A TensorFlow Lite, because it is optimized for mobile and edge devices

B PyTorch Lightning, because it simplifies training on large clusters

C Scikit-learn, because it has many classical machine learning algorithms

D Keras with TensorFlow backend, because it is easy to prototype on desktop

💡 Hint

Think about frameworks optimized for mobile and low-latency inference.

TensorFlow Lite is designed specifically for running machine learning models efficiently on mobile and embedded devices, making it ideal for real-time image classification on mobile.

❓ Hyperparameter

intermediate

Selecting a framework for hyperparameter tuning

You want to perform automated hyperparameter tuning with distributed trials on a cluster. Which framework provides built-in support for this?

A OpenCV, because it processes images efficiently

B FastAI, because it has many pretrained models

C NLTK, because it is good for text preprocessing

D Ray Tune, because it supports distributed hyperparameter search

💡 Hint

Look for frameworks designed for scalable hyperparameter optimization.

Ray Tune is a framework specialized for scalable and distributed hyperparameter tuning, making it suitable for cluster environments.

❓ Metrics

advanced

Framework support for custom evaluation metrics

You need to implement a custom evaluation metric for a regression problem. Which framework allows easy integration of custom metrics during training?

A Matplotlib, because it can plot graphs

B Pandas, because it handles data manipulation well

C XGBoost, because it supports custom objective and evaluation functions

D Seaborn, because it provides statistical visualizations

💡 Hint

Consider frameworks that allow you to define your own loss or metric functions.

XGBoost allows users to define custom objective and evaluation functions, enabling flexible metric integration during training.

🔧 Debug

advanced

Debugging model deployment issues

You deployed a model using ONNX runtime but get errors about unsupported operators. What is the most likely cause?

A The model uses operators not supported by the ONNX runtime version

B The model was trained with too few epochs

C The model file is too large for the runtime

D The input data is missing normalization

💡 Hint

Think about compatibility between model operators and runtime support.

ONNX runtime supports a subset of operators; if the model uses newer or custom operators, errors occur during inference.

🧠 Conceptual

expert

Choosing a framework for agentic AI with multi-modal inputs

You want to build an agentic AI system that processes text, images, and audio simultaneously and can learn from interactions. Which framework best supports this complex multi-modal, interactive learning?

A OpenCV, because it specializes in image processing

B LangChain, because it supports building agentic AI with multi-modal capabilities and interaction loops

C TensorFlow 1.x, because it is stable and widely used

D Scikit-learn, because it has many classical algorithms for tabular data

💡 Hint

Look for frameworks designed for building AI agents with multi-modal and interactive features.

LangChain is designed to build agentic AI systems that can handle multiple data types and support interaction loops, making it ideal for complex multi-modal AI.

Practice

1. Which AI framework is best for beginners who want to learn with simple projects?

easy

A. Apache MXNet

B. PyTorch Lightning

C. Caffe

D. TensorFlow with Keras

Solution

1. Step 1: Identify beginner-friendly frameworks

   TensorFlow with Keras offers simple APIs and good tutorials for beginners.

2. Step 2: Compare with other options

   PyTorch Lightning and MXNet are more advanced; Caffe is less beginner-friendly.

3. Final Answer:

   TensorFlow with Keras -> Option D

4. Quick Check:

   Beginner-friendly = TensorFlow with Keras [OK]

Hint: Pick frameworks known for easy tutorials and simple APIs [OK]

Common Mistakes:

• Choosing complex frameworks for beginners
• Ignoring community support and tutorials
• Confusing advanced features with beginner ease

2. Which of the following is the correct way to import PyTorch in Python?

easy

A. import torch

B. import pytorch

C. from torch import pytorch

D. import Torch

Solution

1. Step 1: Recall PyTorch import syntax

   The official import statement is import torch.

2. Step 2: Check other options for errors

   'import Torch' uses incorrect capitalization; 'import pytorch' uses wrong module name; 'from torch import pytorch' tries to import a non-existent submodule.

3. Final Answer:

   import torch -> Option A

4. Quick Check:

   Standard import = import torch [OK]

Hint: Use official module name exactly as documented [OK]

Common Mistakes:

• Using wrong module names
• Trying to import submodules incorrectly
• Using uncommon aliases without reason

3. What will be the output of this code snippet using TensorFlow?

import tensorflow as tf
x = tf.constant([1, 2, 3])
y = tf.constant([4, 5, 6])
z = tf.add(x, y)
print(z.numpy())

medium

A. [1 2 3 4 5 6]

B. [4 10 18]

C. [5 7 9]

D. Error: TensorFlow add requires scalar inputs

Solution

1. Step 1: Understand tf.add operation

   tf.add adds element-wise values of two tensors of the same shape.

2. Step 2: Calculate element-wise addition

   [1+4, 2+5, 3+6] = [5, 7, 9]. The print statement outputs the numpy array.

3. Final Answer:

   [5 7 9] -> Option C

4. Quick Check:

   Element-wise add = [5 7 9] [OK]

Hint: Add tensors element-wise to get sum of each position [OK]

Common Mistakes:

• Confusing concatenation with addition
• Expecting scalar inputs only
• Misreading output format

4. You wrote this PyTorch code but get an error:

import torch
x = torch.tensor([1, 2, 3])
y = torch.tensor([4, 5])
z = x + y
print(z)

What is the main issue?

medium

A. Tensors have different shapes and cannot be added directly

B. You must convert tensors to numpy arrays before adding

C. PyTorch does not support tensor addition

D. You forgot to call .item() on tensors before adding

Solution

1. Step 1: Check tensor shapes

   x has shape (3,), y has shape (2,). They differ in length.

2. Step 2: Understand addition requirements

   PyTorch requires tensors to have compatible shapes for element-wise addition; these shapes are incompatible.

3. Final Answer:

   Tensors have different shapes and cannot be added directly -> Option A

4. Quick Check:

   Shape mismatch causes addition error [OK]

Hint: Check tensor shapes before adding [OK]

Common Mistakes:

• Assuming automatic broadcasting without matching shapes
• Converting unnecessarily to numpy
• Misusing .item() which extracts single values

5. You want to build an AI agent that can learn from text and images, and you want fast prototyping with easy debugging. Which framework should you choose?

hard

A. TensorFlow with low-level API

B. PyTorch with dynamic computation graphs

C. Scikit-learn

D. Theano

Solution

1. Step 1: Identify framework features needed

   Fast prototyping and easy debugging require dynamic computation graphs.

2. Step 2: Match features to frameworks

   PyTorch supports dynamic graphs and is popular for research and prototyping; TensorFlow low-level API is more complex; Scikit-learn is for classical ML, not deep learning; Theano is outdated.

3. Final Answer:

   PyTorch with dynamic computation graphs -> Option B

4. Quick Check:

   Dynamic graphs = PyTorch [OK]

Hint: Dynamic graphs help fast prototyping and debugging [OK]

Common Mistakes:

• Choosing static graph frameworks for prototyping
• Using classical ML libraries for deep learning tasks
• Picking outdated or unsupported frameworks