How to Build Software Powered By Artificial Intelligence

Vertscend applies 32 years of experience in software development and data science to develop software with artificial intelligence (AI) capabilities.

The Essence of Developing Software with AI Capabilities

Development of software with AI capabilities implies building new software or evolving existing software to output AI analytics results to users (e.g., demand prediction) and/or trigger specific actions based on them (e.g., blocking fraudulent transactions).

Supported by AI, an application can automate business processes, personalize service delivery and drive business-specific insights. According to Deloitte, 90% of seasoned AI adopters say that “AI is very or critically important to their business success today”.

Use Cases for Software with AI Capabilities

Business process automation

Chatbots
Search engines
Automated document generation
Optical character recognition engine for data extraction from paper documents
Job candidates screening and shortlisting

Production management

Predictive maintenance
Demand and throughput forecasting
Process quality prediction
Production loss root cause analysis

Customer analytics

Sentiment analysis
Customer behavior prediction
Sales forecasting

Risk management

Counterparty risk analytics
Potential damage prediction
Fraud detection

Supply chain management

Demand forecasting
Lead time forecasting
Inventory optimization

Personalized service delivery

Customer segmentation
Recommendation engines

Roadmap: Developing Software with AI Capabilities

The duration and sequence of the development stages will depend on the scale and the specifics of both basic software functionality and artificial intelligence you want to enrich it with. Below we present a generalized process outline based on Vertscend 32-year experience in software development and data science.

Feasibility study

Duration: 1 month

Outlining high-level software requirements (in case of new software).
Creating a proof of concept (PoC) for AI to check the technical and economic feasibility of enriching software with it, estimate the scope of work, timeline, budget, and risks.
Calculating ballpark ROI of AI implementation.

Vertscend best practice: To save on time and budget resources and increase the ROI of AI, we deliver a PoC to uncover possible AI-related roadblocks, such as low-quality data, data silos, data scarcity.

Business analysis to elicit AI requirements

Duration: 1-6 weeks

Defining detailed functional and non-functional requirements to AI, such as the required level of AI accuracy (in some cases, the value can be driven already with 65-80% of accuracy), explainability, fairness, privacy, and the required response time.

Vertscend best practice: When choosing a machine learning model AI will leverage, we carefully consider the trade-offs between requirements to AI (as, for example, some models can be less accurate but more explainable and fair).

Solution architecture design

Duration depends on the overall complexity of software functionality

Selecting integration patterns and procedures. Designing the architecture of the solution with integration points between its modules, including integration with an AI module.

Business processes preparation (in case of software development for internal use)

Duration: 1-3 months

Launching an initiative of integrating AI in business-critical software may require organizational changes to increase the chances for its successful implementation and adoption:

Shifts in data policies to break down data silos across the departments to enable easy access to data and avoid duplicated or contradicting data that decreases AI accuracy.
Determining a plan on adapting employees’ workflows to the use of updated (or new) software (e.g., user training and refreshed user guides and policies).
Promoting continuous collaboration between business and tech stakeholders.

Software development (non-AI part)

Duration: 3-36 months

Developing the front end and the back end of software (the server side and APIs, including necessary APIs for AI module integration). Running QA procedures throughout the development process to validate software quality.

AI module development

1. Data preparation

Duration: 1-2 weeks (this process can be reiterated to increase the quality of AI deliverables)

Consolidating data from relevant data sources (internal and external, which can be acquired via one-time purchase or a subscription).
Performing exploratory analysis on data to discover useful patterns in it, detect obvious errors, outliers, anomalies, etc.
Cleansing data: standardizing, replacing missing or deviating variables, removing duplicates, and anonymizing sensitive data.
The resulting data is split into training, validation and test sets.

Vertscend best practice: To significantly streamline this time-consuming stage, we use automation tools (e.g., Trifacta, OpenRefine, DataMatch Enterprise, as well tools within leading AI cloud platforms – Amazon SageMaker, Azure Machine Learning, Google AI Platform).

2. ML model training

Duration: 1-4 weeks (depending on the model’s complexity)

Selecting fitting machine learning algorithms and building ML models. The models are trained with training data and tested against a validation dataset, then their performance is increased by fine-tuning hyperparameters. The most high-performing models can be combined into a single model to decrease the error rate of separate models. The final ML model is validated against a test dataset in the pre-production environment.

AI deployment

Duration: 2-4 weeks

The configuration of the AI deployment infrastructure and approach to integrating AI into software depends on how AI should output results:

In batches: AI outputs are cached according to pre-scheduled time intervals. Targeted software retrieves AI outputs from the data storage it is connected with. Higher latency is acceptable.
As a web service: near-real-time outputs triggered by a user or a system request via API. Low latency is required.

Pilot deployment to a limited number of software users is recommended to verify the smoothness of AI integration with target software and compatibility with the infrastructure (latency, CPU and RAM usage) and run user acceptance tests to handle possible issues before a full-scale rollout.

Vertscend best practice: To accelerate the AI deployment, in our projects we leverage leading AI cloud platforms – Amazon SageMaker, Azure Machine Learning, Google AI Platform.

Maintenance and evolution of AI-powered software

Tracking and fixing software bugs and issues of integration with AI, optimizing software performance and enhancing UI based on user feedback, developing new features or extending AI-enabled functionality drawing on evolving business or user needs.

Maintenance of AI is a separately controlled process. It includes monitoring of ML model performance to detect a ‘drift’ (decreasing accuracy and increasing bias when the data that AI processes grows and starts deviating from the initial training data).

In case of the drift, models should be retrained with new hyperparameters or newly engineered features reflecting shifts in data patterns. They can also be replaced by challenger models with higher performance (identified during A/B testing).

Consider Professional Services for Development of AI-Powered Software

Vertscend applies 32-year experience in software development and data science to create solid software with AI capabilities.

Consulting: software development with AI capabilities

Our consultants help:

Conduct a feasibility study on integrating AI into your software (potential benefits, risks, and costs).
Outline a risk management strategy to mitigate AI-related risks.
Outline a development, deployment and integration plan for building software with AI capabilities.
Choose an optimal sourcing model.
Select a fitting technology stack for software and its AI part prioritizing open-source frameworks to optimize development time and costs.

Outsourced development of software with AI capabilities

We cover all the stages of development:

Feasibility study (including PoC).
Business analysis: eliciting requirements for software and AI.
Software development: UX and design, front-end and back-end development, QA.
AI development: data preparation, ML model building, training and tuning.
AI integration with software, deployment (MVP and full-scale rollout) and testing.
User training.
Software maintenance and evolution.

Talents Required for Developing Software with AI Capabilities

The roles required in a software development project with an AI part vary according to the project’s goals and scope. The key roles include:

Project manager

To outline a project roadmap, manage the software & AI development life cycle, and foster collaboration between business and tech stakeholders.

Business analysts

To analyze business and user needs and translate them into technical requirements for software, AI, and integration between them.

Data scientists

To cleanse data for AI and engineer features; to build, train, test, and validate ML models. Domain experience is preferred.

Data engineer

To deploy AI and monitor it in production.

UX and UI designers

To design wireframes, create user stories and UI prototypes for AI-driven software, following the principles of user-centricity.

Software developers

To build the software back end and front end and build and implement APIs necessary for integration with AI, and further evolve software

QA specialists

To design and implement a test strategy to validate software quality.

Sourcing Models of Developing Software with AI capabilities

All resources are in-house

Full control over the project, however, the lack of the required skills in AI is likely. Growing in-house AI capabilities can be a strategic decision if the development of software with AI functionality is a part of company-wide adoption of AI technologies.

All resources are in-house, except for data scientists

High control over the project and access to competencies unavailable in-house. If you’re looking to grow an end-to-end in-house team in the future, look for a resource vendor who provides knowledge sharing.

Confirm Project Viability, Then Invest

A feasibility study conducted by Vertscend will help you see the strengths of your large-scale project and potential threats to its success.

Our High-Tech Expertise

Advanced data analytics techniques and solutions

Big data solutions
Data science
Machine learning
Artificial intelligence (AI)

Innovative technologies

Internet of Things (IoT)
Blockchain
Computer vision
Augmented reality (AR)
Virtual reality (VR)

Software architectural patterns

Microservices architecture
Cloud-native architecture
Tiered architecture
Reactive architecture

Prominent Projects by Vertscend

The World's Largest PLM Software Development

Vertscend developed a product lifecycle management application powering 20,000 retailers, manufacturers, and suppliers in 110 countries.

Our Customers Talk

Vertscend Services for Large-Scale Projects

Project management consulting

Reviewing your current project management process.
Planning and implementing new project management practices and instruments that address management gaps.
Documenting project requirements and scope.
Planning resources needed to achieve project goals.
Estimating the budget based on the project scope.
Setting up a project schedule, planning iterative releases if needed.

Software consulting

Investigating all business workflows that must be covered by software.
Scoping software requirements, addressing conflicting requirements.
Helping choose between custom and platform-based software development.
Creating functional and architecture specifications.
Planning software integrations (10+ integrations may be required for business-critical systems).
Planning the infrastructure capable of supporting the required workload.

Dedicated team for large-scale software development

Providing all resources needed for project completion (a pool of 370+ software developers and 240+ other project roles).
An in-house Project Management Office.
Fully self-organized teams with no need for your interference in daily activities.
Transparent reporting according to the agreed schedule.

Staff augmentation

We can complement your project team with the following competencies:

Project management
Back-end and front-end programming
Software architecture
Testing and QA
DevOps
UX and UI design
Cybersecurity
Help desk

Get Expert Help for Large-Scale Software Development

With Vertscend, you get knowledgeable project management and skilled software engineering that positively impact the course and results of large-scale projects.

Project costs are reduced due to the fast development pace.
Project flow is coordinated and clear to all the involved participants.
The time-to-value is short, with the first release generally available in 4-6 months and further releases each 2-3 months.
Software under iterative development is available 99.99% of the time due to the well-established CI/CD process.
Risks of budget overruns and vague deadlines are minimized.

Have any questions?