The AI-Native SDLC: Humans, Agents, CI/CD and Automated Verification
When agents write a large share of code, the question 'how do we know it's right?' moves to the centre of the software development lifecycle…
Category
AI-Assisted Engineering
32 articles tagged AI-Assisted Engineering.
The New Developer Workflow: Humans, Coding Agents and CI/CD
In many teams, a typical day now involves dispatching tasks to coding agents, reviewing their pull requests and tuning the pipeline that che…
Securing AI Coding Agents: Shell Access, Secrets, Git and Production Credentials
Coding agents run shell commands, read files, use Git and sometimes reach cloud consoles, often on developers' own machines with their crede…
Agentic Software Engineering: When AI Agents Become Software Developers
In many engineering organisations, agents now open a steady share of pull requests. That raises management questions nobody had to answer be…
Agentic Software Engineering: Can AI Build and Maintain Software?
Coding agents can now complete many well-defined tasks end to end. The harder question for 2026 is whether they can maintain software over t…
Agentic DevSecOps: When AI Agents Can Write, Test and Deploy Code
Agents now take part in every stage of the delivery pipeline: writing features, fixing findings, triaging failures and preparing releases. T…
AI Agents in CI/CD: Can Agents Test, Debug and Deploy Software?
Coding agents now run inside CI pipelines: triaging failed builds, fixing flaky tests, reviewing pull requests and responding to issues. The…
Building Security Guardrails for AI-Powered Development Teams
This summer delivered a series of warnings for AI-powered development: an agent deleting a production database, a malicious prompt shipped i…
AI-Native Software Development: Designing Applications With Agents From Day One
Increasingly, the users of your application are not only people but AI agents acting for them. Designing for that from day one changes APIs,…
AI-Native Software Engineering: What Actually Changes?
With background coding agents now available from GitHub, OpenAI, Google and Anthropic, some teams have agents opening a meaningful share of…
Coding Agents vs Copilots: The Next Generation of Developer Tools
In the space of two months, every major AI coding tool shipped an 'agent mode'. Instead of suggesting the next line, agents plan changes, ed…
Coding Agents vs Copilots: What's Actually Different?
'Agent' is on every AI coding product this spring. Under the label, the technical differences from a copilot are specific: how context is ga…
AI Coding Assistants and Security: Who Is Responsible for Vulnerable AI-Generated Code?
When an AI assistant writes a vulnerability and a developer merges it, who is responsible: the developer, the reviewer, the organisation or…
How to Review AI-Generated Code Like a Senior Engineer
Google has said more than a quarter of its new code is now AI-generated, then reviewed and accepted by engineers. As AI writes more code eve…
From DevOps to AI-Augmented DevOps
LLMs are finding their way into every stage of the DevOps loop: explaining failed builds, drafting infrastructure code, summarising incident…
LLMs in the SDLC: Requirements, Coding, Testing and Documentation
Most discussion of AI in software development focuses on writing code, which is only one part of the software development lifecycle. We walk…
AI-Assisted Security Testing: Finding Vulnerabilities During Development
AI is arriving in application security tooling: automatic fix suggestions for scanner findings, LLM-assisted code review, AI-generated secur…
AI-Assisted Software Engineering: Beyond Code Completion
Code completion was the first act. In 2024, AI tools are taking on larger units of software engineering work: understanding whole codebases,…
AI Coding Assistants: How LLMs Are Changing Software Development
AI coding tools have moved beyond autocomplete to chat, codebase-aware answers and, as of last week's Devin announcement, claims of autonomo…
The Hidden Problems With AI-Generated Code: Security, Bugs and Technical Debt
AI assistants make developers faster, and they also introduce problems that do not show up immediately: insecure patterns delivered with con…
AI Coding Assistants: How Developers Actually Use LLMs
Developer surveys this summer show AI tools have gone mainstream: most developers use them or plan to. But usage looks different from the ma…
The Rise of AI-Assisted Software Development
In twelve months, AI assistants have gone from a novelty to a daily tool for a large share of developers. Copilot is generally available, Ch…
Building Software With GPT-4: From Prompt to Production
GPT-4 and the ChatGPT API have made it easy to build an impressive LLM prototype in a day. Getting it to production is another matter. This…
Prompt Engineering for Developers: Programming With Natural Language
A week after ChatGPT's launch, developers are using it to explain code, write functions, draft tests and debug errors. Getting good results…
The Rise of AI Pair Programming
GitHub Copilot became generally available three weeks ago and Amazon has announced CodeWhisperer. AI pair programming has moved from preview…
From Code Completion to Code Generation: How LLMs Changed Development
DeepMind's AlphaCode, announced this month, reached roughly median human performance in competitive programming. Six months after Copilot's…
AI-Assisted Testing: Automatically Finding Bugs in Software
Writing tests is the part of software engineering that developers most often skip. Search-based tools, reinforcement learning and now large…
Can AI Really Understand Code? Exploring Code Intelligence
OpenAI's Codex paper reports that its model solves a meaningful share of hand-written programming problems from their descriptions, and far…
GitHub Copilot and the Beginning of AI-Assisted Software Development
Last week GitHub launched a technical preview of Copilot, an 'AI pair programmer' that suggests whole functions inside the editor. It is the…
Machine Learning for Software Testing and Bug Detection
Testing and bug-finding consume a large share of engineering time, and machine learning is starting to help: predicting which tests to run,…
Code Completion Before Copilot: The Early Evolution of AI Coding Tools
Autocomplete has been part of IDEs for decades. In the last two years, machine learning has pushed it from completing identifiers to suggest…
AI-Assisted Programming: Can Machine Learning Help Developers Write Code?
Machine learning has transformed image recognition and translation. Can it do the same for programming? Research models like CodeBERT and pr…