What Is Progressive Disclosure in AI Agents
Progressive disclosure is a three-level loading strategy that feeds AI agents only the context they need at the moment, keeping sessions fast and token costs low.
AI-Assisted
Posts tagged AI-Assisted are created with support from artificial intelligence. I use AI tools to research, draft, and refine ideas—combining human insight with machine precision to deliver clear, informed, and creative content.
What Are Agent Skills in AI Coding Tools
Agent skills are reusable markdown files that teach AI coding tools how to perform repeated tasks consistently, replacing ad-hoc prompts with version-controlled procedures.
What Is Blast Radius in AI Agent Security
Blast radius is the total scope of damage a compromised or malfunctioning AI agent can cause before anything stops it, and limiting it is the most practical security strategy you have.
What Is Tool Poisoning in MCP Servers
Tool poisoning is a stealth attack that embeds malicious instructions inside MCP tool descriptions, corrupting your AI agent before a single user command is typed.
What Is Slopsquatting in AI Generated Code
Slopsquatting is a supply chain attack where adversaries register package names that AI coding tools hallucinate, turning a simple install command into a security breach.
What Is the Lethal Trifecta in AI Agent Security
The lethal trifecta describes the dangerous combination of private data access, untrusted content exposure, and outbound action capability that makes AI agents exploitable.
What Is Workslop in AI Assisted Development
Workslop is AI-generated output that appears complete and professional but quietly transfers the real work to whoever reviews, maintains, or builds on top of it.
What Is Verification Debt in AI Assisted Development
Verification debt builds when AI agents write code faster than your team can review it. Learn what it costs and how to keep it under control.
What Is Context Compaction in AI
You have been working with an AI coding agent for about an hour. The session started great. But now the agent is re-reading files it already modified, asking questions you already answered, and generating code that contradicts its own earlier…
What Is Agent Drift in AI Coding
You asked an AI coding agent to add a user profile feature. It came back with clean code, passing tests, and a working UI. Everything looks great until you realize it created a brand new users table instead of using…
The Complete Guide to APEXlang in Oracle APEX 26.1
For over two decades, an Oracle APEX application has lived inside the database as metadata you could only realistically touch through the App Builder. The export was a giant f100.sql file — fine for deployment, nearly useless for code review, diffing, or…
How ATS Works for Resumes: What Really Happens After You Apply
You polish your resume, click "Submit," and then… silence. No rejection, no interview, nothing. Before you blame your experience, understand the software sitting between you and the recruiter: the Applicant Tracking System (ATS). More than 97% of Fortune 500 companies and…
Resume vs CV: What's the Difference and Which One You Need
You're about to apply for a job, and the posting asks for a "CV" but everything you've ever written is a resume. Or you're applying abroad, and suddenly the rules feel different. The resume vs CV confusion trips up job seekers constantly,…
How to Write a Software Engineer Resume That Gets Interviews
You can be a brilliant engineer and still get rejected before a human ever reads your application. The reason is almost never your code — it's your resume. A great software engineer resume does one job: it convinces a recruiter and an…
Model Collapse: What Happens When AI Trains on AI-Generated Data
Imagine photocopying a photocopy. The first copy looks fine. The tenth is blurry. The hundredth is an unreadable smudge. Model collapse — sometimes called recursive contamination — is the AI equivalent of that decay. When models are trained on data produced by other models,…
Context Decay: Why LLMs Forget Your Instructions in Long Conversations
You give a large language model a clear instruction at the start of a long document — "Respond only in JSON" or "Never reveal the customer's account number" — and 20,000 tokens later, it quietly ignores you. The rules you…
Prompt Injection Chain: How One Attack Cascades Through AI
A single prompt injection is dangerous. A prompt injection chain is worse — it's what happens when one malicious instruction doesn't just hijack a single AI response, but cascades from one component to the next, compromising an entire pipeline of agents, tools,…
What Is Vector Poisoning? The AI Attack Explained
Modern AI assistants feel trustworthy because they cite "their knowledge base." But what if an attacker could secretly slip false information into that knowledge base — so the AI confidently serves up lies, leaks data, or pushes malicious instructions to every user…