Mid-Journey

How to use Roles (and Roleplay) with AI

Learn how to improve your prompts by introducing Roles or Roleplaying to AI, wit...

What it means to give a "Role"

Each person has a role to play. Whether it’s a parent, sibling, child, or a lawy...

AI Agents vs MCP vs Automation

Automation executes, agents decide, MCP connects, and you need to choose what's ...

How to balance Input with Automation

Balance AI by automating the routine while people scope and make the final call ...

When you do a SWOT analysis instead of Googling your name

AI is great when it comes to doing traditional analysis on non-traditional things.

The assistant, not the author.

How AI is engraining in New England schools: From the tools to PD to the pilots.

High-Confidence Wrong: AI and Insecure Code

Studies show ~45% of AI-generated code carries OWASP-class flaws. The threat isn...

AI generated Review Floods

Review floods are a reputational DoS. How AI-made fakes, extortion, and pile-ons...

RAG Poisoning and the Drift You Don’t See

Change the retrieval, change the answer. RAG turns inputs into control channels....

That Trust Stack is Under Attack

AI scaled social engineering. Deepfakes, spoofs, and fake AI tools exploit meeti...

The Trojan Stack: Fake AI APIs and SDKs

Malicious AI-branded SDKs, fake APIs, and extensions are the new supply chain. H...

Industrialized AI Intimacy Scams

Inside shift-based, AI-oiled chat factories that scale intimacy across apps and ...

When a Meeting Isn’t a Meeting

Live deepfake calls blend faces, voices, and authority to move money. Arup's los...

Why AI Just Can't Fix that Bug

The steps between feeling like a Prompting God to feeling like you are being gas...

When the model hallucinates, and you didn't know

Models will hallucinate. Sometimes when you are demoing the model like what happ...

Fake Chatbots, Extensions, and Apps

How fake ChatGPT apps and extensions exploit speed, trust, and convenience to hi...