Outline - Slick

Speaker

The source metadata lists Simon Maple, but the transcript suggests the on-stage presenter may be Lars. Treat attribution as ambiguous.

Safety Status

This is a safety-redacted public outline. Operational control mechanics and sensitive integration details are omitted.

Thesis

Browser-native agents can become more useful when their UI, context, skills, and helper agents are designed as one cohesive experience. That usefulness must be balanced with clear capability boundaries.

Section Map

1. Motivation for an agent beside the user's web workflow.
2. Skills as a way to make agents useful in specific contexts.
3. The self-referential browser-agent concept.
4. Live demo: the presentation is itself rendered through the agent experience.
5. Product vocabulary: cone, sprinkles, licks, scoops, and dips.
6. Helper agents and focused delegation.
7. High-level architecture of the agent loop and UI shell.
8. Redacted operational integration details.
9. Safety lessons for browser-native agents.
10. Closing demo summary.

Concepts

• Browser-native agent: An agent experience that lives close to the user's web context.
• Skills: Packaged knowledge that helps the agent understand a specific domain or interface.
• Sprinkles: Small UI components that can interact with the agent.
• Licks: Events that connect UI components and agent behavior.
• Scoops: Focused sub-agents.
• Cone: The main agent surface and interaction point.

Not Included

• Detailed browser-control mechanics.
• Desktop application control steps.
• Token handling details.
• Public endpoint wiring.
• Debug-mode or bypass-like workflows.
• Runnable examples from the live demo.

Safe Use

Use this talk to discuss agent UX, product architecture, event-driven interfaces, and capability-scoped design.