Todd Schiller

This week's changes give a user's agent more structured and safer control over the software it touches.

The week's activity clustered on the agentic web.

This week, Google made a move to curb AI slop by capping how many extensions a single publisher can list.

I joined David Dean Mauro on the Cyber Crime Junkies podcast to talk about how fraud works inside contact centers, and how AI is reshaping both sides of that fight.

The Chromium browsers moved in two directions at once this week.

Running coding agents in parallel is less like one developer juggling features and more like a team of different developers building at the same time independently.

The theme this week was a split between packaging and trust.

The agentic-web plumbing consolidated around MCP this week.

The week moved extensibility work from proposal to committed output.

The week was about boundaries, not new capabilities.

The connective layer for agent-driven software kept maturing this week.

Loop engineering for AI agents should be about compounding, not repetition.

Welcome to This Week in Extensibility, a weekly read on the meta layer of software extensibility: the infrastructure that decides what end users and customers can customize, automate, and modify in the software they already use.

Welcome to This Week in Extensibility, a weekly read on the meta layer of software extensibility: the infrastructure that decides what end users and customers can customize, automate, and modify in the software they already use.

In high school, I spent a summer in a computational biology lab measuring genetic hitchhiking in S. cerevisiae (brewer's yeast).

agent-browser-shield is live on Product Hunt today.

Two days after the alpha announcement, agent-browser-shield has a Chrome Web Store listing and 14 new protection rules.

There are 6 billion internet users.

Today was the Boston OpenClaw Hackathon, which had a theme of using the Boston open data hub.

There's a lot of FUD around Chrome's new Local AI models.

A note on format.

This is a transcript of my talk at the AI Coding Summit on February 26, 2026.

I'll be speaking at the AI Coding Summit on February 26, 2026.

A fundamental mistake people make when assessing the agentic opportunity is a focus on hours (or FTEs) instead of value.

I joined Manish Pandya (SVP of Digital at TaskUs) and host Alp Uguray (Masters of Automation) for a TaskUs Forward webinar on operationalizing generative AI in customer experience.

I joined Kristen Hayer on Innovations in Leadership, the Success League Radio podcast, to talk through where generative AI fits in customer success.

I joined Helina Medhin and Arlo Guthrie (Drata's Director of Design) on Compliance Uncomplicated to talk about PixieBrix — how low-code can democratize software customization, where humans still beat computers, and why we went after SOC 2 early.

I joined Alp Uguray on the Masters of Automation podcast to talk about why we started PixieBrix — what low-code/no-code really means, why the future of work has to be human-first, and what we'd been hearing from the community.

Web browsers are the modern operating system.

If you're like most developers, you've probably encountered Cascading Style Sheet (CSS) selectors for styling webpages.

My freshman year of college, I interned as an "equities analyst".

If you're like most business leaders, George Floyd's death and the resulting push for reform have led you to reflect on your own company's approach to diversity and inclusion (D&I).

Have you ever been stumped by a bug?

Who This Guide is For This guide is for executives, managers, and entrepreneurs who want to make better strategic decisions about software.

Markov Logic Networks (MLNs) are a tool for capturing your beliefs about the world and then calculating the likelihood of outcomes based on those beliefs.

Developer productivity is a product of program understanding, a developer's (1) mental model, and (2) access to information for refining that model.

Library use is common but documentation is scarce.

Joel Spolsky has a popular post from 2005 on "Making Wrong Code Look Wrong".

Writing performant Java software often means controlling allocation patterns to prevent garbage collection.

In an ideal world, each unit test would run in isolation.

I've been creating an annotated collection of financial domain-specific language papers, talks, and webpages on the DSLFIN workshop resources page.

I'm co-organizing the Workshop on Domain-Specific Languages for Financial Systems (DSLFIN) taking place in Miami on October 1, 2013.