The Workshop.
Notes on browser automation, local AI and building in public.
FeaturedTutorials
Use Your Web Browser to Feed a RAG Pipeline
Build a RAG knowledge base from web pages without a crawler or a vector server: save pages and tabs from your browser, index them on your device, then ask questions.
Latest articles
Showing all categories
TutorialsBrowser Automation Without Selenium, Playwright or Puppeteer
Map each Selenium, Playwright or Puppeteer step (open, click, type, wait, extract, schedule) to a no-driver workflow in your own Chrome, and when to keep the script.
TutorialsNo-Code Browser Automation: Record Once, Replay Forever
Record your clicks and typing once in Chrome, then replay them for every row of a sheet, from a shortcut or on a schedule. No code, no server.
ComparisonsCloud Browser or Your Own Browser for AI Agents?
How should an AI agent reach the web? Compare search APIs, cloud browsers and your own logged-in browser: where each wins, where each breaks, and what to pick.
ProductFrom an OpenAPI spec to a typed workflow node at runtime, with no codegen and no backend
Paste the URL of an OpenAPI spec, pick an operation, and the node renders its fields and calls it. How AWFlow's Custom API node works, step by step, and what I deliberately left out.
ProductHow we built teams of AI agents that don't loop
Handoff maps, three ways of working and hard budgets: the coordination runtime that makes a team of AI agents usable in a product, not just in a demo.
ProductOur AI agents run on workflows, and that's deliberate
Pure agents decide every step at run time, which makes them flexible and hard to trust unattended. AWFlow's agents run on ordinary workflows instead: a deterministic skeleton with AI in the slots. Why we chose it and how it shows up in the code.
ProductRecording clicks into replayable browser workflows: selectors, event mapping and MV3 gotchas
How a browser recorder turns clicks and typing into steps you can replay: capture-phase listeners, mapping raw events to intent, selectors that survive the next deploy, and a port that reconnects when the service worker sleeps.
Local AIRunning LLMs inside a Chrome extension: WebLLM, transformers.js and the MV3 traps
What it took to run AI models inside a Manifest V3 extension: three runtimes, two Web Workers, a WebGPU probe with a WASM fallback, and the CSP rule that silently blocks your runtime.
ProductSharing an AI agent: what to keep, what to strip, and what never to trust
An agent is more than a prompt: it has memory, skills, rules and connections. Here is where we drew the line between the reusable setup and the personal state, and the rules we follow when someone installs a template.
Local AITool calling for small on-device LLMs that don't support tool calling
Models running in the browser give you text in and text out, so agent frameworks refuse them. How we added prompt-based tool calling with a model-agnostic parser: one format asked for, many accepted, and three rules that keep it safe.
ProductWe audited our own AI agent harness: 9 failure modes and the fixes
We audited the loop, context, tools, cancellation and failover around our in-browser AI assistant and found 21 gaps. Almost none were about the model. Here are the failure modes, the fixes, and a checklist for your own agent.
Local AIWe rebuilt RAG in a browser tab. Our first bug: every vector was empty.
Our knowledge bases embed, store and search your documents inside the browser. Before rebuilding them, an audit found that no knowledge base had ever had a single searchable chunk. Ten RAG lessons from that rebuild, written so you can check your own pipeline.
No article matches that search.
One letter a month. No noise.
New articles, templates worth stealing and what shipped. Unsubscribe in one click.