AI Agents - The Geeky Bee Blog Page

Sign in Subscribe

AI Agents

A collection of 3 posts

I started with Turbo Prolog in 1986. AI has reinvented itself four times since.

History of Artificial Intelligence

I started with Turbo Prolog in 1986. AI has reinvented itself four times since.

From Turbo Prolog in 1986 to autonomous AI agents in 2026, I've watched artificial intelligence reinvent itself for forty years. Through breakthroughs, false dawns and spectacular failures, this is the story of how AI finally became useful, accessible and capable of helping us build software.

Dots and Muse: useful AI assistants, or just token furnaces?

Dots and Muse: useful AI assistants, or just token furnaces?

AI agents such as Dots and Muse promise to keep working when we're not there. But when does useful persistence become a token furnace? We look at the benefits, costs and security risks of giving AI more autonomy - and knowing when it should stop.

When Your AI Agent Takes Instructions From Strangers: What SalesBleed Teaches Every Business Using AI

When Your AI Agent Takes Instructions From Strangers: What SalesBleed Teaches Every Business Using AI

Salesforce’s recent SalesBleed vulnerabilities highlight a wider AI security issue: what happens when an AI mistakes information for an instruction? We look at prompt injection, public-facing AI agents, and how authentication, restricted permissions and human approval can make them safer.