There’s a friendly debate among developers about how to give AI agents reliable ways to use external tools, data, and services so they can do useful work beyond generating text. One side favors CLIs, or Command-Line Interfaces, where agents run text commands against tools like git, aws, jq, duckdb and internal scripts. The other sideContinue reading “Your CLI Was Built for Humans, Not Agents”
Author Archives: Ben Lorica
What happens when your agent can touch money
Subscribe • Previous Issues Your CLI Was Built for Humans, Not Agents There’s a friendly debate among developers about how to give AI agents reliable ways to use external tools, data, and services so they can do useful work beyond generating text. One side favors CLIs, or Command-Line Interfaces, where agents run text commands against tools likeContinue reading “What happens when your agent can touch money”
Does AI Actually Make Developers More Productive? The Evidence, For and Against
This guide is built from studies and reports published in recent months. Sources include a large matched study tracking more than 100,000 real GitHub developers, a meta-analysis pooling 23 separate productivity studies, telemetry-based reports from engineering-analytics vendors covering thousands of teams and tens of thousands of developers, large multi-country surveys of developers and technology buyers,Continue reading “Does AI Actually Make Developers More Productive? The Evidence, For and Against”
Agents Need Maps, Not Bigger Context Windows
Like everyone else, I’ve been enjoying the steady improvement in coding agents and the tooling around them, from frameworks and harnesses to evaluation suites. But the more I talk with teams actually deploying agents in enterprises, the more I circle back to plumbing. Agents need data integrations and infrastructure built for them, a theme IContinue reading “Agents Need Maps, Not Bigger Context Windows”
I talked to Google’s former AI head about messy data
Subscribe • Previous Issues Agents Need Maps, Not Bigger Context Windows Like everyone else, I’ve been enjoying the steady improvement in coding agents and the tooling around them, from frameworks and harnesses to evaluation suites. But the more I talk with teams actually deploying agents in enterprises, the more I circle back to plumbing. Agents need dataContinue reading “I talked to Google’s former AI head about messy data”
The Data Compliance Problem AI Teams Keep Ignoring
I’ve avoided writing about copyright and AI. Not because it isn’t important, but because it felt like a legal sideshow compared to the engineering and business questions I find more interesting. That’s gotten harder to justify. There is also something mildly funny about naming my podcast The Data Exchange years ago, because I believed dataContinue reading “The Data Compliance Problem AI Teams Keep Ignoring”
What your base model doesn’t protect you from
Subscribe • Previous Issues The Data Compliance Problem AI Teams Keep Ignoring I’ve avoided writing about copyright and AI. Not because it isn’t important, but because it felt like a legal sideshow compared to the engineering and business questions I find more interesting. That’s gotten harder to justify. There is also something mildly funny about naming myContinue reading “What your base model doesn’t protect you from”
The Bear Case for AI Data Centers
The more I dig into the economics, the harder it is to see AI data centers as a good business, and they’re now my leading candidate for what pops the AI bubble in the next 6 to 12 months. The concern isn’t that AI stops improving or that demand vanishes. It’s that spending has racedContinue reading “The Bear Case for AI Data Centers”
The Hybrid AI Stack Is Coming for the Pricing Power of OpenAI and Anthropic
OpenAI and Anthropic are going public while still capturing much of the money spent on foundation-model usage. But deployment patterns are starting to tell a more complicated story. Companies are building hybrid model portfolios, using proprietary models where convenience, support, and frontier capability matter, while turning to open-weights models where cost, privacy, customization, and deploymentContinue reading “The Hybrid AI Stack Is Coming for the Pricing Power of OpenAI and Anthropic”
Your AI bill is a tax on scale
Subscribe • Previous Issues The Hybrid AI Stack Is Coming for the Pricing Power of OpenAI and Anthropic OpenAI and Anthropic are going public while still capturing much of the money spent on foundation-model usage. But deployment patterns are starting to tell a more complicated story. Companies are building hybrid model portfolios, using proprietary models where convenience,Continue reading “Your AI bill is a tax on scale”