AI
Building with AI — agents, LLMs, RAG, prompting, and the engineering behind shipping AI features that hold up.
- A session should survive a node change
- The SQLite CVE mess shows where your vulnerability automation needs a gate
- Coding agents make senior engineers more valuable, if the rulebook leaves their head
- Open weights are now part of your AI disaster-recovery plan
- Open-weight access now belongs in your AI supply chain
- The SOC 2 deadline that matters is the start of your observation window
- PGSimCity is the Postgres refresher you need before parallel agents melt your pool
- Dependabot's cooldown is the policy your Node repo needed once agents sped up dependency churn
- Take-home projects are untrusted code, so give them a sandbox
- Your eval harness needs its own threat model
- Model portability is now a governance feature for AI agents
- Your real moat after GPT-5.6 and Kimi K3 is a private eval harness
- Trust Boundaries for AI Agents: Securing Automated Workflows
- Arm-Based Cloud Compute for Agentic AI: A Look at Azure Cobalt 200
- Build Your Own Code Agent: Tool Calling, Memory, and MCP from Scratch
- Ensemble LLMs: How Multi-Model Fusion Picks the Best Answer
- Parallel Agent Orchestration: Building Multi-Agent Pipelines
- How Reinforcement-Learning Environments Train Better Coding Models
- When AI Agents Drift: Preference Shift Under Load
- Supervising Long-Running AI Agents: Outcome Grading and Webhooks
- Cutting LLM Costs by Nearly Half: A Practical Pre-Scale Playbook
- Scheduling Unattended Coding Workflows with Agent Routines
- Recurrent-Depth Transformers Explained: Looped Reasoning and MoE Routing
- From AI Editor to Agent Orchestrator: Managing Parallel Coding Agents
- Model-Agnostic Coding Agents: One CLI Across Many LLMs
- Giving AI Agents Persistent Memory: Lessons from LongMemEval
- Automating Security Reviews in Your PR Pipeline
- Beyond Bypass Permissions: Risk-Aware Autonomy for Coding Agents
- A Stack Overflow for AI Agents: Shared Knowledge Bases That Cut Wasted Work
- Harness Design: Structuring AI Agents for Long-Running Builds
- How AI Finds Vulnerabilities Traditional Scanners Miss
- From Writing Code to Directing It: How the Developer Role Is Shifting
- Making the Most of Million-Token Context Windows
- Writing Effective Specs for AI Agents
- Inside Agentic Coding Models: Long-Context Self-Summarization and RL
- Breaking the Stack: How Adversarial Attacks Bypass Layered LLM Safeguards
- Building Cosmos DB Infrastructure with an AI Agent Kit
- Coordinating Parallel AI Agents on Long-Running Engineering Tasks
- Why Agent Evaluations Matter: What a Vending-Machine Sim Reveals
- Building a Better AI Code Reviewer: What Makes Review Trustworthy
- Parallel AI Coding: Subagents and Agent Skills in a Modern Editor
- MCP Apps Explained: Interactive Tool UIs Inside the Chat
- When Your AI Assistant Gets Hacked: Prompt Injection and Exposed Gateways
- One Language for AI Commerce: Inside the Universal Commerce Protocol
- An Agentic Coding Workflow That Scales: Hooks, Sub-Agents, and Feedback Loops
- Context on Demand: How Dynamic Context Discovery Cuts Agent Token Use
- The Free Prompt Hack: Why Repeating Your Prompt Helps Non-Reasoning LLMs
- Can an AI Agent Run a Business? Lessons from an Autonomy Experiment
- The 2025 LLM Year in Review: RLVR, Test-Time Compute, and Jagged Intelligence
- Learning Machine Learning in a Spreadsheet
- AI in the Inspector: Debugging Faster with Chrome DevTools Assistance
- Dialing Reasoning Depth: A Developer's Guide to Gemini 3's thinking_level
- AGENTS.md Explained: A README for Your AI Coding Agents
- Building MCP Servers by Dragging Blocks: Visual MCP Explained
- Guarding Agentic Browsers: How Chrome Fights AI Prompt Injection
- Does AI Really Make You 80% Faster? Reading a Productivity Study
- Editing SQL Data with AI: Copilot in the VS Code MSSQL Extension
- A 7B Model That Drives Your Computer: Efficient Agentic Models Explained
- Semantic Code Search: How Embeddings Speed Up AI Coding Assistants
- Building Generative AI Apps in .NET: A Hands-On Course Breakdown
- A First Look at Agent-First AI IDEs
- Meet Seer: How an AI Debugger Diagnoses Production Errors
- Anatomy of the First Reported AI-Orchestrated Cyber Espionage Campaign
- An Autonomous Security Researcher for Finding Bugs
- Why Small Language Models Are the Future of Local Setups
- Cutting Token Bills: Converting JSON to TOON for Leaner LLM Prompts
- Cursor 2.0: Multi-Agent Coding and What Actually Changed
- Plan Before You Prompt: Copilot's New Planning Mode in Visual Studio
- AI That Patches Your Code: Inside an Autonomous Vulnerability Agent
- Context Rot: The Research on Why LLM Quality Degrades
- Fine-Tuning for the Edge: A Gemma 3 270M On-Device Walkthrough
- Claude Skills: Packaging Instructions and Scripts Your AI Loads on Demand
- Apps Inside ChatGPT: Building on the MCP App Platform
- Big Models, Local Tools: Ollama's Cloud Models Explained
- Codex Goes Agentic: Running a Coding Model Autonomously for Hours
- Autonomous Pentesting: AI Agents That Exploit Bugs Instead of Just Flagging Them
- How AI Agents Pay: A Practical Guide to the Agent Payments Protocol
- Profiling by Prompt: Copilot's New Performance Agent in Visual Studio
- Testing Your AI's Defenses: Prompt Injection Lessons from Gandalf
- Prompt Engineering for a Fast, Cheap Coding Model
- Agentic Design Patterns: A Field Guide to Building AI Agents
- Building Production Voice Agents with the gpt-realtime API
- The Hidden Limit of RAG: Why Vector Dimensions Cap Your Dataset
- Visualizing Embeddings at Scale with Apple's Embedding Atlas
- The Lethal Trifecta: Understanding Prompt Injection in AI Agents
- Generating UI Components from Figma with the Dev Mode MCP Server
- Hosting MCP Servers in Production with FastMCP Cloud
- Building AI Agents in .NET with the A2A SDK
- No-Code AI App Builders: A First Look at Google Opal
- AI in Your Git Workflow: Copilot Commit Messages and Code Review
- Building AI Agent Teams with Claude Code Sub-Agents
- Running LLMs Locally: Ollama vs LM Studio
- Prompting GPT-5: A Practical Guide for Developers
- Building a RAG System with Local Vector Search
- Ask Mode vs Agent Mode: Getting the Most Out of GitHub Copilot
- Verification-and-Refinement: How Standard LLMs Reached IMO 2025 Gold
- Genspark AI: New Super Agent
- Claude Code: Anthropic's AI Coding Assistant
- Get started with the official Microsoft's Azure MCP Server
- Agentic AI implementation guidance
- Microsoft Copilot Studio: a Low‑Code AI Assistant Builder
- MCP Explained: Empower your AI
- Vector Databases in AI/ML: the next-gen infrastructure for intelligent search
- Agentic AI: the rise of autonomous agents