Generative AI and Automation Testing: The Future of Testing

November 3, 2023

The World of Automation Testing

Quality assurance is an important step in software development. It has fuelled growth and innovation, resulting in more efficient and accurate testing environments. From the initial days of manual testing – which involved manual selection of test cases, conducting the tests, recording of results and deriving conclusions – we’ve moved to the age of scripted and data-driven automation, where repeatable and consistent testing can be done driven by a wide range of data. Even with all this growth and evolution, the presence of unbiased and widely varying data with brand new scenarios in mind are hard to find. This is compounded by the additional amount of manual input required for testing, scripting and other processes.

The Advent of Generative AI

Generative AI is a powerful tool capable of revolutionizing most fields including software testing. Software testing requires the existence of robust data that can cover most testing scenarios and edge cases along with code that is well maintained to run all the test scenarios. Generative AI can be used to generate data and scripts by understanding patterns and user/stakeholder requirements.

How Would a Solution of Generative AI in Testing Work?

Generative AI can be implemented in various ways in testing like:

  • Generating Test Data

Having effective data that correctly tackle edge cases and finding possible vulnerabilities during testing is always hard. This is where Generative AI can help out. Generative AI can be utilized to generate diverse test data that covers all possible scenarios. This process is pretty cumbersome to be done manually. Such generated data can then be combined with information about usage patterns and application requirements to create effective test cases that can better detect vulnerabilities.

  • Generation of Test Scripts

Creation and maintenance of test scripts is one of the most resource-intensive tasks in automated testing. It requires considerable time and effort from a qualified group of individuals. It also limits the access of various stakeholders in generating effective and important test scenarios. With Generative AI, such individuals can give accurate descriptions of the testing to be performed while the AI can handle the job of generating efficient and accurate test scripts. The individuals once involved in creating and maintaining test scripts can now move to assisting the AI and helping out in getting a better understanding of the scripts/results generated.

  • Bug Detection

Generative AI can also be used to analyze previous testing patterns and occurrence of bugs to identify possible points of failures. This information can then be used to create new test cases tackling those exact scenarios. Bug detention and faulty area detection can be addressed.

These are just a few of the many ways in which Generative AI can help out in automation testing. Scaling test cases along with the core software, test code maintenance, consistent test quality etc. are other prominent benefits of using Generative AI for testing.

Challenges in Implementing Generative AI

Using Generative AI has its own set of challenges though. We will list them here.

  • Inability to generate meaningful test data/tests due to lack of understanding of the scenario at hand.
  • Generative AI models like GANs, large transformers etc. require huge amounts of compute resources, which can pose challenges for businesses.
  • Training/fine-tuning the Generative AI model requires large amounts of quality data to work with.
  • Interpreting AI-generated tests, data etc. require additional skilled individuals especially in cases of failures during testing.

Generation of Synthetic Test Data Using Generative AI

Synthetic test data is not mock data. Synthetic test data, created by Gen AI, which has been trained on real data, maintains the structure and referential integrity of the original data while supporting relational structures. 

This AI-generated synthetic data is not simply mock or fake data; it accurately reflects customer behavior as observed in production data. Unlike manually generated data, it is produced by a powerful AI engine that comprehensively learns the characteristics of its training dataset, achieving 100% test coverage. 

High-quality synthetic data generators can efficiently automate the process of test data generation, mitigating privacy concerns. It is crucial to utilize customer data in its synthetic form to uphold privacy standards while preserving the business rules inherent in the data.

Here’s the rough idea on how to do this: 

The rough idea is actually very simple:

  • Prompt a local running Llama2, Falcon or Mistral instance. Give it instructions regarding which type of request is expected (valid/non-valid request, XSS attack …).
  • Execute the requests.

We have written extensively on how to host your own local LLM on E2E Cloud in several blogs. As a first step, launch a GPU node to host your own LLM. 

We recommend using your own privately hosted LLM because it keeps your data safe, and you avoid incurring API costs in the long run with the proprietary ones (as your token sizes increase, so does your cost). 

So go ahead and register with E2E Cloud and spin up a GPU node. 

Next, you can follow the guide here to deploy Llama2. 

We also recommend using Visual Studio with Remote Explorer extension, to use the remote machine almost as a local development environment. 

Once you are connected and have your LLM running, try out a prompt like this: 

Create a CSV file with 50 random sales records for a restaurant.
Each record should include the following fields:
  - id (incrementing integer starting at 1)
  - date (random date between 1/1/2022 and 12/31/2022)
  - time (random time between 6:00am and 9:00pm in 1-minute increments)
  - product_id (incrementing integer starting at 1)
  - product
  - calories
  - price in USD
  - quantity (random integer between 1 and 3)
  - amount (price * quantity)

Generation of Scripts That Generate Test Data

While the above is one approach, the challenge you will face is that this will generate a limited amount of data. 

So, how do you solve this? Simple - use an LLM to generate a Python script, which then generates the test data. For this, it would be better if you use a code-tuned LLM. One such AI coding assistant is StarCoder.

StarCoder is an LLM model for code, designed by Hugging Face, and trained on permissively licensed data from GitHub. It has been trained on over 80 programming languages, Git commits, GitHub issues, and Jupyter notebooks. 

The model has approximately 15 billion parameters trained on over 1 trillion tokens​​. StarCoder and its variants, StarCoderBase and StarCoderPlus, are aimed at code generation tasks across a wide range of programming languages​​. 

StarCoderEx is a tool available for Visual Studio Code, created to generate code using StarCoder, and is positioned as an alternative to GitHub Copilot​​.

Follow the steps here to deploy StarCoder. Alternatively, you could deploy Code-Llama. 

Then prompt it like this:

Write a Python3 code to make a CSV file with 1000 sales records for typical restaurant items. The CSV file should have a header row and each record should have these details:
  - id (incrementing integer starting at 1)
  - date (random date between 1/1/2022 and 12/31/2022)
  - time (random time between 6:00am and 9:00pm in 1-minute increments)
  - product_id (incrementing integer starting at 1)
  - product
  - calories
  - price in USD
  - quantity (random integer between 1 and 3)
  - amount (price * quantity)


This will generate a Python script that you can then use for synthetic test data generation. 

Generation of Test Scripts

One of the most exciting applications of AI coding assistants is generating test scripts. AI coding assistants like StarCoder or Code-Llama can help any developer create unit tests for their Python code, without compromising company IP or customer data. 

What you need to do is provide a brief description of the class and its purpose, the methods you want to test, and any dependencies the class might have on external resources or other classes.

They can then be used to automatically generate unit tests using AI and metaprogramming techniques, ensuring comprehensive test coverage for your code. This feature can save a lot of time and effort, as writing test scripts can be a tedious and time-consuming task. 

Since you now have an AI-Coding LLM running, we can leverage that to generate test scripts as well. Here’s how you prompt that.

# Python class to test
class Calculator:
    def add(self, a, b):
        return a + b

# Prompt
prompt = "I'd like your help with creating unit tests for a Python class I have. [Paste the above class]. This class is a calculator that can add two numbers. I want to test the add method. Generate the test script for that."

Try this out, and play around with the prompt. This will give you a quick way to generate test scripts that you can then execute and test your code on. You can prompt it to vary the test scenarios.

Here’s a Python code to simplify this further (modify to use the right LLM function in your case): 

# Assume `code_llama` is a function provided by Code Llama for generating code
def generate_test_script(function_name, function_code):
    # Define the prompt for generating a test script
    prompt = f"Generate a test script for the following function:\n\n{function_name}\n{function_code}"
    # Call Code Llama to generate the test script
    test_script = code_llama(prompt)
    return test_script

# Example usage
function_name = "add"
function_code = """
def add(a, b):
    return a + b

test_script = generate_test_script(function_name, function_code)

Coding Assistants for Bug Detection

It doesn’t stop there. AI coding assistants can actually be incorporated in a lot of more advanced ways – for example, to improve testing processes through bug detection, analysis, code reviews and more. 

AI coding assistants can significantly expedite and enhance the bug detection process in software development in several ways:


AI can perform static analysis to scrutinize code without executing it to find common bugs, coding standard violations, or other potential issues. It can identify patterns associated with bugs and suggest corrections. This is becoming a potent approach in ensuring bugs are detected before even the code is pushed.

Code Review Automation

AI can automate code reviews, checking for bugs, inconsistencies, or violations of coding standards. It can also help in identifying sections of code that are likely to cause bugs based on historical data, and suggest better coding practices.

Automated Testing

As we saw above, you can use AI to generate and execute tests at scale to uncover bugs. It can also identify areas of the code that are under-tested and suggest additional tests. This is an area where more development is expected to happen in the near future.

Anomaly Detection

AI can also be used to analyze historical data and understand normal code behavior. This can help identify anomalies and point to issues with the code.

Natural Language Processing (NLP)

Utilizing LLM-NLP, AI models can process bug reports, extract relevant information, and even link bugs to code, helping to speed up the bug-fixing process. For instance, you can use natural language to talk to your code, and understand its flow and how it's working. For companies which have a ton of legacy code, this can prove to be extremely useful.

These features not only enhance bug detection but also contribute to a more efficient and effective software development process, saving time and ensuring higher code quality.


The advent of Generative AI has been revolutionary in many areas. Software quality testing has always been a continuously evolving field throughout its existence. Now as one enters the age of Gen AI, the possibilities are endless with huge leaps in automation testing to be expected.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure