Todd Schiller

This Week in Extensibility: Edge commits to removing Manifest V2, WebMCP adds Edge and Brave, Cloudflare previews a code-sandbox SDK

Todd Schiller — Fri, 14 Aug 2026 00:00:00 -0400

Week of August 7–14, 2026: Microsoft Edge commits to removing Manifest V2, WebMCP origin trials reach Microsoft Edge and Brave, and Cloudflare ships a 1.0 preview of the SDK for running customer and agent code in isolated sandboxes.

Agentic Software Factories: Parallel agents diverge. Plan to converge.

Todd Schiller — Wed, 12 Aug 2026 00:00:00 -0400

Running coding agents in parallel is closer to a team of different developers than one developer multitasking, so plan a deliberate converge phase after the diverge phase.

This Week in Extensibility: six vendors standardize agent-plugin bundles, Mozilla stays neutral on WebMCP, Atlassian opens Rovo to Forge apps

Todd Schiller — Fri, 07 Aug 2026 00:00:00 -0400

Week of July 31 – August 7, 2026: six agent vendors publish a shared plugin-packaging standard, Mozilla files a neutral position on WebMCP that leaves the browser engines split, and Atlassian opens its Rovo agent framework to Forge apps.

This Week in Extensibility: MCP ships its stateless spec with sandboxed app UIs, WebMCP starts tracking cross-engine support, WebExtensions weighs OAuth for MCP servers

Todd Schiller — Fri, 31 Jul 2026 00:00:00 -0400

Week of July 24–31, 2026: MCP ships its 2026-07-28 specification with a stateless core and first-class extensions for sandboxed app UIs and async tasks, WebMCP stands up a cross-engine implementation tracker, and the WebExtensions group weighs letting extensions authenticate to MCP servers.

This Week in Extensibility: Wasmtime enables GC and exceptions by default, WebMCP specs in-page agent APIs, the WebExtensions group commits to shipping spec text

Todd Schiller — Fri, 24 Jul 2026 00:00:00 -0400

Week of July 17–24, 2026: Wasmtime turns on WebAssembly GC and exceptions by default, WebMCP specifies how a user's in-page agent discovers and invokes a site's tools, and the W3C WebExtensions group commits to writing normative spec text.

This Week in Extensibility: the Chrome Web Store bans two extension categories, Mozilla proposes a permission model for AI agents, Cloudflare runs customer code before signup

Todd Schiller — Fri, 17 Jul 2026 00:00:00 -0400

Week of July 10–17, 2026: the Chrome Web Store bans prediction-market and AI-guardrail-circumvention extensions and narrows what any extension may collect, Mozilla proposes a browser-mediated permission model for AI agents at the WebExtensions group, and Cloudflare ships a way to run a customer's code before they sign up.

This Week in Extensibility: MCP's spec locks down its auth and skills, WebMCP gets conformance tests, WebAssembly components bind to real-world interfaces

Todd Schiller — Fri, 10 Jul 2026 00:00:00 -0400

Week of July 3–10, 2026: MCP's next spec locks down its client-auth and skill-distribution pieces before a July 28 launch, WebMCP gains a cross-vendor conformance suite, the WebAssembly Component Model moves to bind components to real-world interfaces, and Apple ships a first-party Safari MCP server in preview.

Loop Engineering: always be compounding

Todd Schiller — Tue, 07 Jul 2026 00:00:00 -0400

Loop engineering for AI agents should raise the floor on each iteration by creating tools and correcting instructions.

This Week in Extensibility: MCP trims to a stateless core, extensions weigh softer permission prompts, ChatGPT adds plugin governance

Todd Schiller — Fri, 03 Jul 2026 00:00:00 -0400

Week of June 26 – July 3, 2026: MCP ships beta SDKs for a leaner stateless spec, the WebExtensions group takes up softer permission prompts, and ChatGPT Business adds a plugin control plane for admins.

This Week in Extensibility: hyperscale sandboxes, extensions get a standards track, and prompt-to-plugin

Todd Schiller — Fri, 26 Jun 2026 00:00:00 -0400

Week of June 19–26, 2026: AWS makes per-user code isolation a managed product, the WebExtensions API gets a chartered W3C Working Group, and Figma turns plugin authoring into a writing task.

Beliefs hitchhike like genes

Todd Schiller — Tue, 09 Jun 2026 00:00:00 -0400

A new explorer that clusters public thinkers by the genome of their beliefs, inspired by genetic hitchhiking.

agent-browser-shield is live on Product Hunt

Todd Schiller — Fri, 05 Jun 2026 00:00:00 -0400

agent-browser-shield, a source-available defense layer for AI agents in the browser, is on Product Hunt today.

agent-browser-shield June 3 update: 14 new rules and the Chrome Web Store listing

Todd Schiller — Wed, 03 Jun 2026 00:00:00 -0400

14 new rules shipped in agent-browser-shield, now installable from the Chrome Web Store, and using it for daily driving.

Introducing agent-browser-shield (alpha): keeping AI agents safe in the browser

Todd Schiller — Mon, 01 Jun 2026 00:00:00 -0400

Announcing the alpha of agent-browser-shield — a source-available defense layer (also available as an OpenClaw skill) that blocks prompt injection and dark patterns before they reach your agent.

Letting OpenClaw loose on Boston's open data

Todd Schiller — Sat, 30 May 2026 00:00:00 -0400

At the Boston OpenClaw 2026 hackathon, I let an agent autonomously connect to the city's open-data MCP server, devise its own corruption-signal queries on contract data, and package the workflow as a reusable Claude skill.

Did Google sneak a local LLM model into Chrome?

Todd Schiller — Tue, 26 May 2026 00:00:00 -0400

A response to FUD around Chrome's new Local AI models, plus a demo using PixieBrix + Local AI to filter my LinkedIn feed.

ACH as Bayesian reasoning in disguise

Todd Schiller — Sun, 24 May 2026 00:00:00 -0400

The Analysis of Competing Hypotheses worksheet is naive Bayes with a friendlier UI. An interactive artifact to explore.

Making AI coding work for enterprise-grade browser extensions

Todd Schiller — Fri, 27 Feb 2026 00:00:00 -0500

Lessons learned using AI coding tools to build PixieBrix, an enterprise-grade browser extension with a complex architecture spanning content scripts, background workers, and React UI.

Speaking at AI Coding Summit 2026: making AI coding work for enterprise-grade browser extensions

Todd Schiller — Wed, 25 Feb 2026 00:00:00 -0500

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

My talk, Making AI Coding Work for Enterprise-Grade Browser Extensions, covers the unique challenges of applying AI coding workflows to browser extension development.

Mainstream "vibe coding" workflows weren't designed for browser extensions. Extensions have distributed architectures spanning tabs …

The agentic opportunity: value, not hours

Todd Schiller — Sun, 26 Oct 2025 00:00:00 -0400

Focusing on hours (or FTEs) misses the point of the agentic opportunity.

Co-pilots, not chatbots: highlights from a TaskUs Forward webinar

Todd Schiller — Mon, 02 Sep 2024 00:00:00 -0400

Highlights from the September 2024 TaskUs Forward webinar with Manish Pandya and host Alp Uguray on what it takes to operationalize generative AI in CX.

AI frees humans to be more human: highlights from Success League Radio

Todd Schiller — Tue, 19 Sep 2023 00:00:00 -0400

A few moments from my conversation with Kristen Hayer on Success League Radio about where generative AI fits in customer success.

Compliance, low-code, and the user as hero: highlights from Drata's podcast

Todd Schiller — Thu, 09 Mar 2023 00:00:00 -0500

Highlights from my conversation with Drata's Helina Medhin and Arlo Guthrie on Compliance Uncomplicated about low-code, AI, user experience, and SOC 2.

Everything is UI/UX: highlights from Masters of Automation

Todd Schiller — Tue, 09 Aug 2022 00:00:00 -0400

A few moments from my August 2022 conversation with Alp Uguray on Masters of Automation about PixieBrix, low-code, and putting humans at the center of the future of work.

A brief history of browser extensibility

Todd Schiller — Thu, 04 Mar 2021 00:00:00 -0500

Web browsers are the modern operating system. Google's Chrome OS, an operating system that runs the Chrome Browser exclusively, is now the second most popular desktop operating system. Additionally, the rise of Electron and similar cross-platform frameworks means that many of the applications we use every day (e.g., Slack …

7 bite-sized tips for reliable web automation and scraping selectors

Todd Schiller — Thu, 03 Dec 2020 00:00:00 -0500

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

For example, the following CSS rule combines a paragraph element selector p with a class name selector .lead to set the font size:

p.lead {
    font-size: 32px;
}

We can mix-and-match CSS selectors to …

The PixieBrix manifesto: web customization for the masses

Todd Schiller — Wed, 02 Sep 2020 00:00:00 -0400

My freshman year of college, I interned as an "equities analyst". What this meant in practice was that I was supposed to look up numbers in a terminal, and then type them into an Excel spreadsheet. The software provider hadn't gotten around to implementing export for the data yet.

Not …

Three interviewing mistakes that sabotage your diversity and inclusion initiatives

Todd Schiller — Thu, 25 Jun 2020 00:00:00 -0400

Learn the three interviewing mistakes that sabotage your diversity and inclusion initiatives and how to prevent them

Effective debugging: the observe-hypothesize-test cycle

Todd Schiller — Wed, 02 Jan 2019 00:00:00 -0500

Have you ever been stumped by a bug? Overwhelmed? Did it take hours, days, or weeks to solve? How did you finally manage to get yourself unstuck? Did you just get lucky, or was it skill?

I certainly didn’t always follow a formal debugging process. My first programming gig …

The MBA guide to software development

Todd Schiller — Wed, 04 May 2016 00:00:00 -0400

This guide is for executives, managers, and entrepreneurs who want to make better strategic decisions about software. It’s designed to give you a baseline conceptual understanding of the software development process to help you buy software, build software, and interact with software development teams.

Markov logic networks for fun and profit: NBA playoffs edition

Todd Schiller — Tue, 19 Apr 2016 00:00:00 -0400

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. Since it's the NBA playoffs, let's use MLNs and our beliefs about the NBA to predict the 2016 NBA championship.

Specific Beliefs (Predicates)

To get …

Combating information failure during software development

Todd Schiller — Mon, 16 Feb 2015 00:00:00 -0500

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

Former Defense Secretary Donald Rumsfeld's famous intuition is actually roughly correct for understanding program understanding:

There are known knowns. These are things we know that we know. There …

4 steps to effective development questions and bug reports

Todd Schiller — Tue, 23 Dec 2014 00:00:00 -0500

Library use is common but documentation is scarce. Your ability to ascertain information quickly about a library can mean the difference between success and failure in time-sensitive projects.

There are two cases where interaction with developers is the bottleneck: (1) reporting a bug, and (2) learning to use a feature …

Making Wrong Code... Wrong

Todd Schiller — Mon, 08 Dec 2014 00:00:00 -0500

Joel Spolsky has a popular post from 2005 on "Making Wrong Code Look Wrong". In this post, I'll address his suggestion to use Hungarian Notation. It turns out we can now do better: we can make wrong code... wrong!

Hungarian Notation is a naming scheme that conveys information about methods …

Enforcing memory allocation patterns with an effect system

Todd Schiller — Sun, 23 Nov 2014 00:00:00 -0500

Writing performant Java software often means controlling allocation patterns to prevent garbage collection. For example, a program for processing financial FIX messages in real-time might use a fixed buffer to avoid allocations altogether.

In many cases, it's easy to determine whether code allocates memory. However, manually verifying allocation patterns becomes …

Improving unit testing with data provenance

Todd Schiller — Sun, 29 Dec 2013 00:00:00 -0500

In an ideal world, each unit test would run in isolation. In practice, environment setup (e.g., database schema setup) is expensive, so it's common to share resources between tests.

In the worst case, interference between tests can actually mask bugs that the test suite would otherwise catch [1]. In …

Financial DSL resources

Todd Schiller — Mon, 10 Jun 2013 00:00:00 -0400

I've been creating an annotated collection of financial domain-specific language papers, talks, and webpages on the DSLFIN workshop resources page. Since it's become a bit unwieldy, I'll be imposing some order on the listing by host language and target application. If you have any suggestions for resources, or would like …

Financial DSL workshop at MODELS 2013

Todd Schiller — Tue, 21 May 2013 00:00:00 -0400

Information about the Workshop on Domain-Specific Languages for Financial Systems (DSLFIN).