AI Native DevCon 2026 London — all conference sessions as interactive skills
70
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Firtman argues that AI agents increasingly need to interact with the web, but today's techniques (HTTP fetch, browser-use plugins, computer use, screenshot inference) are slow, token-hungry, and unreliable. Web MCP is a proposed W3C standard (entering Chrome 149 origin trial) that lets web developers expose typed, named tools from the frontend directly to agents — replacing pixel-guessing inference with an explicit contract that has access to the full browser context (DOM, forms, sensors, session, client APIs).
outline.md to locate the relevant section, then read that section of transcript.md.transcript.md. Never put quotation marks around paraphrased content.transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.When the user asks "how would Firtman tackle ?" or wants the talk's framework applied to their own situation:
outline.md → "Named frameworks / concepts" to find the relevant framework (most likely the adoption recipe: pick one high-value page state → expose a read-only diagnostic tool → evaluate with calls/arguments → automate via Chrome DevTools MCP or Puppeteer).transcript.md for the speaker's exact wording.When the user asks the skill to "draft", "generate", or "show me an example of" a Web MCP tool:
outline.md (Named frameworks / concepts → Tool object shape) and his tool-design guidance (one purpose per tool, state-aware registration, plain language, meaningful errors, small outputs).transcript.md carefully — capture every constraint Firtman mentions.name, description (written for an agent consumer), inputSchema (JSON schema), and execute (async function). For declarative form-based tools, include tool name, tool description, optional tool auto submit, and per-field tool param description where the label is insufficient.[not from talk — added as a starting placeholder]).For any question about what Firtman said, did, or argued:
outline.md first to find the relevant section(s).transcript.md.transcript.md. Do not paraphrase while presenting as a quote.When the user's current work touches on themes Firtman addressed (agents reading/operating web apps, MCP, agent token/context budget, frontend exposure of capabilities to AI):
transcript.md — one quote is usually enough.When the user wants to understand a concept Firtman covered (Web MCP, the agentic web, tool object, imperative vs declarative API, origin trial, MCP-vs-Web-MCP boundary, the Chrome DevTools MCP bridge):
outline.md → "Terminology glossary".transcript.md.quote.md contains pre-extracted safe highlights from this talk, organised by theme. When formulating answers, check quote.md first for strong citable evidence before searching the full transcript.md.
.tessl-plugin
talk-azriel-executable-specs
talk-baker-sadogursky-context-engineering-skills
talk-batey-building-product-teams-age-of-ai
talk-birgitta-closing-keynote
talk-cormack-tests-lie-observability-ai
talk-debois-agent-enablement
talk-douglas-training-ai-on-your-own-code
talk-dubnov-merge-rate-ai-adoption
talk-farley-vibe-coding-best-we-can-do
talk-firtman-web-mcp-agentic-web
talk-foxwell-reinvention-dev-team
talk-groetzinger-skills-everywhere
talk-jones-odevo-ai-native-transformation
talk-jourdan-pipelines-to-prompts
talk-katsioloudes-code-security-ai
talk-kerr-bipolar-disorder-dysregulation-ai
talk-kushwaha-benchmarking-agent-era
talk-lamis-context-engineering-dreaming
talk-lawson-agent-experience
talk-lopopolo-harness-engineering
talk-lubken-embedding-pi-coding-agent
talk-maleix-collective-intelligence
talk-marsden-agent-desktops
talk-martinelli-spec-driven-development
talk-moss-skills-team-workflow
talk-obstbaum-willoughby-vibes-to-metrics
talk-overweg-one-brain-no-filtering
talk-podjarny-skills-are-the-new-code
talk-roberts-ai-native-brownfield
talk-roberts-brownfield-ai-native
talk-ruiz-agents-on-canvas-tldraw
talk-scheire-artificial-intelligence
talk-selajev-docker-sandboxes-agents
talk-sloan-harness-engineering-beyond-code
talk-smith-connecting-context-future-transports
talk-stack-humans-architect-ai-writes-code
talk-syme-agentic-repository-automation
talk-thomas-ai-native-engineering
talk-trieloff-browser-agents
talk-walter-runtime-intelligence-agents
talk-wotherspoon-humans-vs-slop