Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
June 15, 2026
·
Doha
Inside Maestro: How to use MCP as a separation of concerns layer
Learn how to use MCP for separation of concerns in AI. Explore independent packages for screenshot compression, avatar generation, and multilingual speech, composed into a generative UI.
Overview
Independent library plus MCP-exposed packages, and the orchestration layer that composes them into Maestro - the voice-first generative UI featured in last week’s AI Tinkerers Post-Training newsletter.
I’ll walk through each package live, with the codebase open:
-
- Pandini: a browser-API-only screenshot compressor I built to stop blowing up my Claude Code context windows. 60 MB screenshots collapse to under 400KB with no quality loss, no install, no API. The “why this exists” alone is a useful builder takeaway about working with coding agents at scale.
-
- HQIQ Avatar Generator: full avatar lifecycle as a package: text-to-image via Replicate, character sheet generation, original voice, wardrobe, YAML manifest output. Exposed via Fast MCP so Maestro can invoke avatar creation as a tool at build time or runtime.
-
- HQIQ Avatar Locales: paired demo with the Avatar Generator. Same separation-of-concerns pattern: this package’s only job is making any avatar speak any language. Skill-MD-driven, MCP-exposed, fires on demand. I’ll add a new Arabic locale live during the talk and have Fatima speak it within minutes - no code change, no redeploy.
Links
Tech stack
Finding related talks...
Compose Email
Sending...
Email preview
Loading recent emails...