Posts Tagged: agentic AI

The silhouette of a person walking down a long, brightly lit aisle between rows of tall server cabinets in a data centre.

Your AI Agents Now Run on a Grid With a Dimmer Switch

Posted by & filed under , , .

Voters turned down data centres in all but one of 41 ballot measures, and OpenAI answered with cheaper power promises, a grid dimmer switch and a new name. The name is the least interesting bit: the compute your AI agents run on is now interruptible, and engineering teams should plan for it.

Five colleagues work together around one long desk with computers, a laptop and a printed blueprint, seen from above.

Five Engineers Rebuilt X.com With AI Agents. Should You Rewrite Too?

Posted by & filed under , , .

Five engineers and their AI coding agents rebuilt the x.com web app in under six months. “Never rewrite from scratch” used to be gospel, but when writing code gets cheap, the hard part moves to the plan and the rollout. Here’s how that played out when I chose to build the Calendrz mobile apps natively, twice.

A person's hands typing on a laptop keyboard, with lines of code on the screen, on a rustic wooden table.

Of AI Agents, Code Mode and the One Tool to Rule Them All

Posted by & filed under , .

Agents are collapsing their tool catalogues into a single exec tool and writing code against your APIs. Having built an MCP server with 30+ tools for Calendrz, I think that makes your tool design more important, not less, and privacy has to live in the tools.

An old brick building with a red tiled roof, wrapped in scaffolding and safety netting during renovation, against a blue sky.

Of Legacy Code and Unlimited AI Tokens

Posted by & filed under , , .

Cisco has given one engineer unlimited AI tokens to rewrite 98% of its legacy code. I did a (much smaller) version of that on the Calendrz codebase this year, and the tokens were the easy part: the tests and the deleting came first.

A startled man in glasses and a green jumper sitting at a desk while hands around him push a phone, a tablet, an alarm clock, a notebook and documents at him.

Of Leaders, Workers and Too Many AI Agents

Posted by & filed under , .

A new Asana report finds leaders use far more AI agents than their teams, while workers lose time juggling them. My take on why the two sides see agents so differently, and why leaders should measure finished work rather than agent activity.