Source: https://toddschiller.com/categories.html

# Categories

## [Ai](https://toddschiller.com/category/ai.html) (9)

- Note [What size model does real-time on-device protection need?](https://toddschiller.com/blog/on-device-slm-behavior-detection.html)

  Oct 14, 2026 System One decision models fit on-device behavior detection, and Chrome is building one into the browser. For real-time protection, small models trained for the task still win...
- Note [Agentic Software Factories: Parallel agents diverge. Plan to converge.](https://toddschiller.com/blog/parallel-agents-diverge-converge.html)

  Aug 12, 2026 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.
- Note [Loop Engineering: always be compounding](https://toddschiller.com/blog/loop-engineering-compounding.html)

  Jul 07, 2026 Loop engineering for AI agents should raise the floor on each iteration by creating tools and correcting instructions.
- Note [Beliefs hitchhike like genes](https://toddschiller.com/blog/belief-phylogenetics-artifact.html)

  Jun 09, 2026 A new explorer that clusters public thinkers by the genome of their beliefs, inspired by genetic hitchhiking.
- Note [agent-browser-shield is live on Product Hunt](https://toddschiller.com/blog/agent-browser-shield-product-hunt.html)

  Jun 05, 2026 agent-browser-shield, a source-available defense layer for AI agents in the browser, is on Product Hunt today.
- Note [agent-browser-shield June 3 update: 14 new rules and the Chrome Web Store listing](https://toddschiller.com/blog/agent-browser-shield-june-03-update.html)

  Jun 03, 2026 14 new rules shipped in agent-browser-shield, now installable from the Chrome Web Store, and using it for daily driving.
- Note [Introducing agent-browser-shield (alpha): keeping AI agents safe in the browser](https://toddschiller.com/blog/agent-browser-shield-alpha.html)

  Jun 01, 2026 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...
- Note [Letting OpenClaw loose on Boston's open data](https://toddschiller.com/blog/openclaw-boston-open-data.html)

  May 30, 2026 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...
- Note [The agentic opportunity: value, not hours](https://toddschiller.com/blog/agentic-value-not-hours.html)

  Oct 26, 2025 Focusing on hours (or FTEs) misses the point of the agentic opportunity.

## [Browser extensions](https://toddschiller.com/category/browser-extensions.html) (8)

- Note [Did Google sneak a local LLM model into Chrome?](https://toddschiller.com/blog/chrome-local-ai-linkedin-filter.html)

  May 26, 2026 A response to FUD around Chrome's new Local AI models, plus a demo using PixieBrix + Local AI to filter my LinkedIn feed.
- [Making AI coding work for enterprise-grade browser extensions](https://toddschiller.com/blog/ai-coding-browser-extensions.html)

  Feb 27, 2026 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.
- Note [Speaking at AI Coding Summit 2026: making AI coding work for enterprise-grade browser extensions](https://toddschiller.com/blog/ai-coding-summit-2026.html)

  Feb 25, 2026 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...
- [Compliance, low-code, and the user as hero: highlights from Drata's podcast](https://toddschiller.com/blog/compliance-uncomplicated-highlights.html)

  Mar 09, 2023 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](https://toddschiller.com/blog/masters-of-automation-2022-highlights.html)

  Aug 09, 2022 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](https://toddschiller.com/blog/history-browser-extensibility.html)

  Mar 04, 2021 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...
- [7 bite-sized tips for reliable web automation and scraping selectors](https://toddschiller.com/blog/reliable-web-scrapers.html)

  Dec 03, 2020 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...
- [The PixieBrix manifesto: web customization for the masses](https://toddschiller.com/blog/pixiebrix-manifesto.html)

  Sep 02, 2020 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...

## [Domain specific languages](https://toddschiller.com/category/domain-specific-languages.html) (2)

- Note [Financial DSL resources](https://toddschiller.com/blog/financial-dsl-resources.html)

  Jun 10, 2013 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...
- Note [Financial DSL workshop at MODELS 2013](https://toddschiller.com/blog/financial-dsl-workshop-announce.html)

  May 21, 2013 Information about the Workshop on Domain-Specific Languages for Financial Systems (DSLFIN).

## [Extensibility](https://toddschiller.com/category/extensibility.html) (18)

- Note [This Week in Extensibility: Shopify asks app developers to run its new AI security scanner, the Model Context Protocol charters a Tasks and Events group to standardize how servers notify a user's agent, and Trigger.dev makes inbound webhooks a hosted service](https://toddschiller.com/blog/this-week-in-extensibility-2026-10-23.html)

  Oct 23, 2026 Week of October 17 – October 23, 2026: Shopify asked every app developer to run its new AI security scanner and previewed tougher App Store requirements, the Model Context...
- Note [This Week in Extensibility: The Bytecode Alliance patches a sandbox escape in Wasmtime, Cloudflare acquires Deno to make self-hosted Workers a first-class path, and Shopify opens agent checkout across its catalog](https://toddschiller.com/blog/this-week-in-extensibility-2026-10-16.html)

  Oct 16, 2026 Week of October 10 – October 16, 2026: the Bytecode Alliance patched a high-severity filesystem sandbox escape in Wasmtime, the engine many products use to run customer...
- Note [This Week in Extensibility: Meta open-sources the Muse Gadgets SDK for building hardware its agent controls, Microsoft ships MXC, a stable cross-platform sandbox for untrusted code, and the Model Context Protocol adds Server Cards for sizing up a server before connecting](https://toddschiller.com/blog/this-week-in-extensibility-2026-10-09.html)

  Oct 09, 2026 Week of October 3 – October 9, 2026: Meta open-sources the Muse Gadgets SDK for building hardware its personal agent controls, Microsoft ships the first stable release of MXC,...
- Note [This Week in Extensibility: Claude Code launches mods that let users reshape the tool, Atlassian opens Forge app tools to outside AI agents, and Shopify closes off the old script-injection path for apps](https://toddschiller.com/blog/extensibility-radar-2026-10-02.html)

  Oct 02, 2026 Week of September 26 – October 2, 2026: Anthropic launches mods for Claude Code, opening the coding tool to small programs that reshape how it works, Atlassian widens its Rovo...
- Note [This Week in Extensibility: Meta opens its personal agent to third-party developers, Google turns on end-user automation building in Workspace, and Adobe sets a deadline to retire its old Creative Cloud plugin system](https://toddschiller.com/blog/extensibility-radar-2026-09-25.html)

  Sep 25, 2026 Week of September 19–25, 2026: Meta opens its Muse personal agent to a third-party connector platform that outside developers plug their services into, Google switches on...
- Note [This Week in Extensibility: Apple ships end-user extension authoring in Safari, Anthropic names 'Claude Mods' for Claude Code, and HubSpot and Salesforce let installed apps add tools straight to a customer's AI agent](https://toddschiller.com/blog/extensibility-radar-2026-09-18.html)

  Sep 18, 2026 Week of September 12–18, 2026: Apple ships a Safari feature that turns a plain-language description into a working browser extension, Anthropic names 'Claude Mods' for its...
- Note [This Week in Extensibility: Atlassian's agent server reaches general availability, CopilotKit pipes MCP tools into AG-UI apps, and Apple widens the in-app actions its assistant can drive](https://toddschiller.com/blog/extensibility-radar-2026-09-11.html)

  Sep 11, 2026 Week of September 5–11, 2026: Atlassian's Rovo agent server reaches general availability across its suite, CopilotKit ships a first adapter that pipes an MCP server's tools...
- Note [This Week in Extensibility: portable skills for MCP, a confirm-before-acting flag for web agents, and rules for which sites can message a browser extension](https://toddschiller.com/blog/extensibility-radar-2026-09-04.html)

  Sep 04, 2026 Week of August 29 – September 4, 2026: the Model Context Protocol accepts a format for packaging reusable agent skills that move between apps, WebMCP adds a way for sites to...
- Note [This Week in Extensibility: OpenAI rallies vendors behind WebMCP, MCP maps its next spec cycle, and an argument for governing agents over sandboxing them](https://toddschiller.com/blog/extensibility-radar-2026-08-28.html)

  Aug 28, 2026 Week of August 21–28, 2026: OpenAI and six web-platform companies launch a WebMCP hackathon, the Model Context Protocol publishes a roadmap for its next cycle, and Steve Yegge...
- Note [This Week in Extensibility: Chrome Web Store caps extensions per publisher, the blogosphere discusses LLM-generated user extensions, and YC startup Vendo launches on HN](https://toddschiller.com/blog/extensibility-radar-2026-08-21.html)

  Aug 21, 2026 Week of August 14–21, 2026: Google caps how many extensions one publisher can list in the Chrome Web Store, an essay argues web apps should let users generate their own...
- Note [This Week in Extensibility: Edge commits to removing Manifest V2, WebMCP adds Edge and Brave, Cloudflare previews a code-sandbox SDK](https://toddschiller.com/blog/extensibility-radar-2026-08-14.html)

  Aug 14, 2026 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...
- Note [This Week in Extensibility: six vendors standardize agent-plugin bundles, Mozilla stays neutral on WebMCP, Atlassian opens Rovo to Forge apps](https://toddschiller.com/blog/extensibility-radar-2026-08-07.html)

  Aug 07, 2026 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...
- Note [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](https://toddschiller.com/blog/extensibility-radar-2026-07-31.html)

  Jul 31, 2026 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...
- Note [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](https://toddschiller.com/blog/extensibility-radar-2026-07-24.html)

  Jul 24, 2026 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...
- Note [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](https://toddschiller.com/blog/extensibility-radar-2026-07-17.html)

  Jul 17, 2026 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...
- Note [This Week in Extensibility: MCP's spec locks down its auth and skills, WebMCP gets conformance tests, WebAssembly components bind to real-world interfaces](https://toddschiller.com/blog/extensibility-radar-2026-07-10.html)

  Jul 10, 2026 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...
- Note [This Week in Extensibility: MCP trims to a stateless core, extensions weigh softer permission prompts, ChatGPT adds plugin governance](https://toddschiller.com/blog/extensibility-radar-2026-07-03.html)

  Jul 03, 2026 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...
- Note [This Week in Extensibility: hyperscale sandboxes, extensions get a standards track, and prompt-to-plugin](https://toddschiller.com/blog/extensibility-radar-2026-06-26.html)

  Jun 26, 2026 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...

## [Machine learning](https://toddschiller.com/category/machine-learning.html) (4)

- [Contact Center Fraud: highlights from my Cyber Crime Junkies episode](https://toddschiller.com/blog/cyber-crime-junkies-highlights.html)

  Aug 20, 2026 Highlights from my conversation with David Dean Mauro on Cyber Crime Junkies about contact center fraud, insider risk, AI agents, and locking down shadow AI.
- [Co-pilots, not chatbots: highlights from a TaskUs Forward webinar](https://toddschiller.com/blog/operationalizing-ai-at-scale-highlights.html)

  Sep 02, 2024 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](https://toddschiller.com/blog/generative-ai-customer-success-highlights.html)

  Sep 19, 2023 A few moments from my conversation with Kristen Hayer on Success League Radio about where generative AI fits in customer success.
- [Markov logic networks for fun and profit: NBA playoffs edition](https://toddschiller.com/blog/markov-logic-network-nba-playoffs.html)

  Apr 19, 2016 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...

## [Reasoning](https://toddschiller.com/category/reasoning.html) (1)

- [ACH as Bayesian reasoning in disguise](https://toddschiller.com/blog/ach-bayesian-reasoning.html)

  May 24, 2026 The Analysis of Competing Hypotheses worksheet is naive Bayes with a friendlier UI. An interactive artifact to explore.

## [Software engineering](https://toddschiller.com/category/software-engineering.html) (4)

- [Effective debugging: the observe-hypothesize-test cycle](https://toddschiller.com/blog/debugging-steps.html)

  Jan 02, 2019 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...
- [The MBA guide to software development](https://toddschiller.com/blog/the-mba-guide-to-software-development.html)

  May 04, 2016 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...
- [Combating information failure during software development](https://toddschiller.com/blog/information-failure-software-development.html)

  Feb 16, 2015 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...
- [4 steps to effective development questions and bug reports](https://toddschiller.com/blog/bug-reports-development-questions.html)

  Dec 23, 2014 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...

## [Talent acquisition](https://toddschiller.com/category/talent-acquisition.html) (1)

- [Three interviewing mistakes that sabotage your diversity and inclusion initiatives](https://toddschiller.com/blog/diversity-inclusion-mistakes.html)

  Jun 25, 2020 Learn the three interviewing mistakes that sabotage your diversity and inclusion initiatives and how to prevent them

## [Testing](https://toddschiller.com/category/testing.html) (1)

- [Improving unit testing with data provenance](https://toddschiller.com/blog/improving-unit-testing-with-data-provenance.html)

  Dec 29, 2013 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...

## [Verification](https://toddschiller.com/category/verification.html) (2)

- [Making Wrong Code... Wrong](https://toddschiller.com/blog/java-hungarian-notation-checker.html)

  Dec 08, 2014 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...
- [Enforcing memory allocation patterns with an effect system](https://toddschiller.com/blog/java-allocation-effect-system.html)

  Nov 23, 2014 Writing performant Java software often means controlling allocation patterns to prevent garbage collection. For example, a program for processing financial FIX messages in...