talk-maple-ai-native-devcon-welcome-slick

name	talk-maple-ai-native-devcon-welcome-slick
description	Use when the user asks about the "Welcome to AI Native DevCon" talk introducing Slick (slick.com) — a browser-native agent that controls the browser it runs in. Covers Slick's architecture (sprinkles, scoops, licks, the cone), how it uses HTTP / Chrome Debug Protocol / WebRTC, pyagent as the agentic loop, skills as "step zero of agent enablement", MCP and webMCP support, remote-controlling Electron apps (Slack, Teams, Claude desktop) via Slick Star, ad hoc generative UI, OAuth token handling, and verbatim quotes from the talk. Also use when the user wants to apply this browser-native agent approach to their own work.
metadata	{"generated-by":"talk-to-skill","source":"user-provided-transcript","generated-at":"2026-06-01T00:00:00.000Z"}

Welcome to AI Native DevCon — Slick: A Browser-Native Agent

The talk introduces Slick (slick.com), an agent that runs inside the browser and controls the very browser it runs in — a "self-licking ice cream cone." The presenter argues that skills are "the step zero of agent enablement" and demonstrates Slick's architecture: sprinkles (HTML iframes in the sidebar), scoops (sub-agents), licks (events), and the cone (the main UI agent), built on pyagent and leveraging HTTP, the Chrome Debug Protocol, and WebRTC to remote-control web apps and Electron apps including Slack, Teams, and Claude desktop.

Note: the talk is delivered as a live Slick demo — the slides themselves are sprinkles rendered by the agent. Attribution in this transcript is ambiguous: the speaker metadata lists Simon Maple, but the transcript closes with "Lars, the cone really does follow you everywhere, even on stage," suggesting Lars may be the on-stage presenter and Simon Maple may be the host/introducer. Treat speaker attribution with care.

Grounding rules — MUST follow when answering

1. Before answering any specific question, read outline.md to locate the relevant section, then read that section of transcript.md.
2. When attributing words, quote verbatim from transcript.md. Never put quotation marks around paraphrased content.
3. If a claim isn't in transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.
4. Cite by transcript line range or section whenever possible.
5. Speaker attribution is unreliable for this transcript — the source has no per-speaker labels, and there is ambiguity about whether the on-stage presenter is Simon Maple (listed in metadata) or Lars (named at the close of the talk). Prefer phrasing like "the presenter said..." or "Slick's author said..." unless context clearly disambiguates.
6. Cross-reference any named addressee with the participants noted in the transcript header before attributing.

How to help with this talk

Factual Q&A about the talk

For any question about what the speaker said, did, or argued:

1. Read outline.md first to find the relevant section(s).
2. Read the matching range of transcript.md.
3. Answer using verbatim quotes from transcript.md. Do not paraphrase the speaker's words while presenting them as a quote.
4. Cite line numbers or section headings so the user can verify.
5. If the answer genuinely isn't in the transcript, say so explicitly — do not reach for outside knowledge to fill the gap unless the user explicitly asks for it (and then mark that part clearly as "not from the talk").

Apply the speaker's approach to current work

When the user asks "how would the Slick approach apply to ?" or wants the talk's architecture applied to their own situation:

1. Use outline.md → "Named frameworks / concepts" to find the relevant idea (sprinkles, scoops, licks, the cone, Slick Star, etc.).
2. Read the corresponding range of transcript.md for the speaker's exact wording.
3. Anchor your suggestion in a verbatim quote of how the speaker articulates the idea. Then walk through applying it step-by-step to the user's case.
4. If the idea genuinely doesn't fit the user's situation, say so. Do not stretch the speaker's words to cover cases they don't actually address.

Surface this talk proactively when relevant

When the user's current work touches on themes the speaker addressed (browser-based agents, agent harnesses, skills as enablement, MCP / webMCP, remote-controlling Electron apps, ad hoc generative UI):

1. Briefly note: "The Slick talk at AI Native DevCon made a related point..."
2. Quote verbatim from transcript.md — one quote is usually enough.
3. Add one sentence connecting the quote to the user's situation.
4. Do not over-cite. If the connection feels strained, stay quiet.

Teach / explain concepts from the talk

When the user wants to understand a concept the speaker covered (sprinkles, scoops, licks, the cone, Slick Star, electron fuses, etc.):

1. Look up the term in outline.md → "Terminology glossary".
2. Read the speaker's explanation in transcript.md.
3. Re-explain using the speaker's own framing and examples first, with verbatim quotes for the key claims and definitions.
4. You may add modern context, comparisons, or extensions afterwards — but mark them clearly as "not from the talk" so the user can tell which parts are the speaker's and which are yours.

Key quotes

quotes.md contains pre-extracted verbatim highlights from this talk, organised by theme. When formulating answers, check quotes.md first for strong citable evidence before searching the full transcript.md.