Tag: AI code review
The Open Source Trap: Why Trust Isn’t a Security Strategy
The XZ Utils backdoor was a wake-up call, but the underlying problem it exposed has not gone away. Sophisticated adversaries are playing the long game, spending months or years earning trust within ...
GitHub Copilot CLI Gets a Second Opinion — and It’s From a Different AI Family
Tom Smith | | AI agents, AI code review, Claude Sonnet 4.6, cross-family collaboration, developer tools, GitHub Copilot, GPT-5.4, Rubber Duck, SWE-Bench ProGitHub Copilot CLI’s "Rubber Duck" experimental feature uses cross-family model collaboration (Claude + GPT-5.4) to catch architectural flaws and reduce logic errors ...
Why Code Validation is the Next Frontier
Shared staging environments were never designed for a world where dozens of changes land in a codebase every hour. Yet most engineering teams still depend on them as the primary checkpoint before ...
Why Governance Determines Whether Agentic AI Accelerates or Stalls Engineering
Eric Paulsen | | agentic AI, Agentic Workflows, AI code review, auditability, Automated Refactoring, Code Completion, Developer Velocity, Engineering Governance, Governance Debt, Parallel Engineering, Risk-based Governance, software development lifecycle SDLCAI coding tools offer rapid productivity gains, but "governance debt" often slows delivery. Learn how to embed risk-based controls and auditability into agentic AI workflows to scale engineering capacity ...
Anthropic Code Review Dispatches Agent Teams to Catch the Bugs That Skim Reads Miss
Tom Smith | | AI code review, AI coding agents, Anthropic Code Review, Claude Code, Code Review Automation, developer productivity, devops, Engineering Velocity, GitHub integration, Logical Bug Detection, multi-agent systems, Pull Request Automation, secure software development, software quality, software reliabilityAnthropic Code Review dispatches agent teams to find bugs in PRs. Multi-agent analysis, severity ranking, and inline fixes for Teams and Enterprise ...
Cursor Cloud Agents Get Their Own Computers — and 35% of Internal PRs to Prove It
Tom Smith | | agent-driven development, AI code review, AI coding agents, autonomous software development, CI/CD and AI agents, cloud-based AI development, Cursor cloud agents, devops automation, self-verifying AI code, software engineering automationCursor’s new cloud AI coding agents can build, test, and verify software autonomously using real UI interaction. With 35% of production PRs generated by agents, software delivery is shifting from code authoring ...
Qodo Adds Multiple AI Agents to Code Review Platform
Mike Vizard | | AI code review, ai copilot, AI-assisted testing, AI-generated code, automated code review, Bitbucket, code review, code review benchmark, defect detection, devops, F1 score, github, gitlab, LLM, memory-enabled agents, multi-agent AI, pull requests, Qodo, software qualityQodo 2.0 adds memory-enabled, task-specific AI agents to its LLM-based code-review platform, improving defect recall and F1 performance to help DevOps scale code quality as AI-generated code rises ...
The Deterministic Future of AI-Generated Code
Yechezkel Rabinovich | | AI code generation, AI code review, AI development workflows, automated pull requests, behavioral verification, CI pipeline, code validation, deterministic guardrails, DevOps AI, ebpf, generated code risks, observability, smarter linters, software reliabilityAI has eliminated the bottleneck of writing code—but introduced massive uncertainty in verifying it. This piece explores why deterministic guardrails, smarter linters, and eBPF-driven observability are becoming essential to code review and ...
Vibe Coding Can Create Unseen Vulnerabilities
Jeff Kuo | | AI and cybersecurity, AI automation, AI code review, AI code validation, AI coding ethics, AI development oversight, AI hallucination, AI in app development, AI programming, AI software reliability, AI software security, black-box coding, developer in the loop, Firebase breach, GenAI, low-code platforms, no-code tools, secure coding practices, software quality assurance, technical debtVibe coding uses AI to write software fast — but without developer oversight, it can introduce security flaws, technical debt and compliance risks ...
Sonar Previews Service to Improve Quality of AI Generated Code
Mike Vizard | | AI code quality, AI code review, AI code security, AI model training, AI-generated code, bug reduction, code vulnerabilities, cybersecurity in AI, devsecops, Large Language Models, reinforcement learning, secure coding, software development, Sonar platform, SonarSweepSonar’s SonarSweep improves AI-generated code by reducing bugs and vulnerabilities, helping organizations train more reliable AI models ...
Atlassian Makes AI Coding Agent Generally Available
Mike Vizard | | AI code review, AI coding agent, AI DevOps tools, AI for software development, AI in CI/CD, AI project planning, AI software orchestration, Anthropic MCP, Atlassian AI, Atlassian Compass, Atlassian Team 25, devops automation, DX engineering metrics, Jira integration, Model Context ProtocolAtlassian launches Rovo Dev, an AI coding agent for writing, reviewing, and planning code, bundled with Bitbucket, Compass, and DX in the new Software Collection ...
OpenAI’s GPT-5-Codex: A Smarter Approach to Enterprise Development
Tom Smith | | AI code review, AI in DevOps, complex debugging AI, enterprise AI coding, enterprise software development, GPT-5 for developers, GPT-5-Codex, IDE Integration, long-running tasks AI, OpenAI CodexOpenAI’s GPT-5-Codex is built for real-world enterprise software engineering, handling long-running tasks, complex refactoring, and intelligent code reviews with strong security and IDE integration ...
