Unlocking the Power of Intelligent Engineering: AI Foundations for Software Development Teams

Foundations

Intelligent Engineering

Applying AI across the software development lifecycle to accelerate and improve how teams build software.

Generative AI for Developers

AI that helps generate code, tests, and documentation from natural-language prompts and context.

Augmenting Developers

AI assists with routine and boilerplate work so developers focus on design and problem-solving.

Human Accountability

Developers remain responsible for correctness, quality, and security; AI output must be reviewed.

Coding

AI-Assisted Coding

Using AI to draft code, suggest completions, and explain unfamiliar code.

Code Explanation

Using AI to understand and summarize existing or legacy code quickly.

Refactoring Support

Using AI to suggest refactorings, reviewed by the developer for correctness.

Boilerplate Generation

Using AI to generate repetitive scaffolding, freeing time for design work.

Testing

AI-Assisted Testing

Using AI to draft unit and integration tests and suggest edge cases.

Test Data Generation

Using AI to create realistic test data for thorough testing.

Reviewing Coverage

Using AI to identify gaps in test coverage for the developer to address.

Docs

Documentation Generation

Using AI to draft code comments, API docs, and READMEs that developers verify.

Summarizing Changes

Using AI to summarize commits and pull requests for reviewers.

Prompting

Effective Prompts

Writing clear, specific prompts with context to get useful engineering output.

Providing Code Context

Giving AI the relevant code and constraints so its suggestions fit the codebase.

Iterating on Output

Refining prompts and reviewing results until the code or tests meet the need.

Pipeline

AI in the Delivery Pipeline

Integrating AI tools into development and CI/CD to accelerate flow with fast feedback.

Code Review with AI

Using AI to assist reviews by flagging issues, with humans making decisions.

Quality & Security

Verifying AI Output

Always testing and reviewing AI-generated code for correctness, quality, and security.

Security Risks

Being aware that AI can suggest insecure code or leak data; applying safeguards.

Responsible AI

Protecting Source and Data

Avoiding exposing proprietary code or sensitive data to public AI tools.

Guardrails and Policy

Following organizational rules on approved AI tools and acceptable use in engineering.