How to Scan AI-Generated Code for Vulnerabilities Before Merge
Set up a CI gate with secrets scanning, dependency checks for hallucinated packages, and blocking SAST, enforced by branch protection on every pull request.
AI News & Models
AI Coding Tools
Claude Code, Codex, Cursor and other coding agents: how to use them, which to pick, and how to trust the code they write.
83 articles · Updated Nov 12, 2026
Most read by people in Engineering, IT and Product Management.
What Is AI Code Bloat? How to Measure and Manage It
AI code bloat explained: how duplication, falling code reuse, and error-masking show up in GitClear, DORA, and CodeRabbit data, plus metrics to track.
What Is Explainable AI for Code? How to Audit AI-Written Code
Learn how explainable AI and reverse engineering help you audit AI-generated code, reduce cognitive debt, and meet compliance needs, with data from recent studies.
explainable AIaudit AI-generated codereverse engineering code
How to Tell If AI Is Actually Making Developers More Productive
METR, DORA, and Faros data show AI can slow developers and hurt delivery stability. Learn five signs your AI coding stack adds output but not value.
AI developer productivitydoes AI make developers fasterAI coding productivity study
What Is an AI Skill File? SKILL.md vs MCP Servers Explained
An AI skill file (SKILL.md) is a markdown folder of instructions an agent loads on demand. Learn the format, token costs, and how it compares to MCP servers.
AI skill fileSKILL.mdagent skills vs MCP server
Can You Run a Dev Environment in the Browser? WebContainers and More
Can you build a full-stack app with no cloud compute? We tested WebContainers, WebVM, Pyodide, HiGHS-js, and WebLLM to find what works and where it breaks.
browser-based development environmentWebContainersrun Node.js in browser
Is AI-Generated Code Secure? 2025 Data on Copilot Leaks and Agent Risks
AI-generated code fails security checks 45% of the time, Copilot repos leak secrets 40% more often, and shadow AI adds $670,000 to breach costs, per 2025 data.
How to Review AI-Generated Code: A Checklist for Developers
Learn how to review AI-generated code: verify behavior, check dependencies, scan for security flaws, and add monitoring. Includes data on why standard PR review fails.
The Verification Bottleneck: When Your AI Writes Logic You Can't Audit
Human review can't keep up with AI-generated code and math. Here's why formal, machine-checkable verification is becoming the real governance control.
AI Agents That Write Code From Diagrams: What's Actually Shipping
Diagrams and canvases now generate working code. See how tldraw, Figma, and Coinbase's own agent turn sketches into shipped internal tools.
AI agents write code from diagramstldraw Make RealFigma use_figma MCP
How to Enjoy Programming With AI (Without Losing the Craft)
Developers are burned out by shallow AI prompting. The fix: redirect AI toward boilerplate and owned internal tools, not another rented SaaS subscription.
how to enjoy programming with AIAI developer burnoutAI coding boilerplate
AI Query Optimization vs. Postgres: An Experiment in Owning the Planner
Bao and LLM-QO beat Postgres's planner by 20-70%. Here's whether a cheap, fine-tuned 4B model can be owned outright instead of rented from a vendor.
AI query optimizationPostgres query plannerlearned query optimizer
Open Source AI IDEs for Agents: Inside the Workspace Replacing Solo Coding
Cline Desktop and Whiteboard show what an open-source, agent-native IDE requires: model flexibility, self-hosting, and real governance controls.
Securing AI-Generated Code: How Slopsquatting Exploits Hallucinated Packages
AI coding tools hallucinate open-source packages, and attackers register them with malware. Here's how to secure AI-generated code before slopsquatting reaches production.
We Analyzed 10,000 Lines of AI-Generated Code. Here's How to Measure the Sloppiness.
The research is consistent: AI code ships faster and breaks more. Here's the churn, duplication, and complexity toolkit that quantifies it.
How AI's Math Breakthroughs Are Changing Software Engineering
AI hit IMO gold medal reasoning in 2025. That same machinery now verifies code correctness, changing the risk math behind build vs. buy decisions.
AI math breakthroughs software engineeringformal verification AI codeLean proof assistant software
AI Coding Agents Broke CI/CD. Here's How Teams Are Fixing the Bottleneck
AI agents now outpace CI/CD, review, and staging. The data on the bottleneck, what an intent conflict is, and the five fixes teams are building.
AI coding agents CI/CD bottleneckintent conflict AI codeCI/CD pipeline AI agents
How to Write Specs for AI Coding Agents
AI made writing code cheap. Correctness is the expensive part now. Here's how to write specs that actually guide coding agents to build it right.
AI Agent Chat Portability for Code: How to Avoid Vendor Lock-in
Losing an AI coding vendor means losing sealed chat history and reasoning, not just code. Here's how to keep that context portable and owned.
ai agent chat portability for codevendor lock-in AI agentsAI coding agent audit trail
The Best AI Coding Agents in 2026: Claude Code, Cursor, Devin, and What Replaced Autocomplete
The best AI coding agents in 2026 don't autocomplete, they ship. A practitioner's guide to Claude Code, Cursor, Devin, and the local tools replacing SaaS.
best AI coding agents 2026Claude CodeCursor AI
The AI Agent Code Security Workflow You Need Before You Ship
How to build a mandatory security scanning gate into AI coding agent workflows, with SAST, SCA, human review, and logging for agents like GPT-6 Astra.
AI agent code security workflowsecuring AI generated codeagentic coding security
What Are AI Agent Skills Files (SKILL.md)?
SKILL.md skills files are plain-text onboarding guides for AI agents. Here's how progressive disclosure works, why sprawl and security risks are real, and how skills pair with MCP.
AI agent skills filesSKILL.mdagent skills standard
How to Test AI-Generated Code Before It Breaks Production
Human review can't catch vibe-coded PRs anymore. Here's the mechanical pipeline, from mutation testing to canary releases, that tests AI code before it merges.
Can AI Write Code for Microcontrollers? Yes, But That's Not the Interesting Part
AI writes microcontroller firmware, decodes undocumented chips, and now designs PCBs from prompts. What it can and can't do, with real numbers.
can ai write code for microcontrollersAI firmware generationAI reverse engineering