Skip to main content
AmigoFish

Run AI Agents Safely with Docker + Tessl

From Docker · · 32 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.

If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.

Watch on YouTube

Not rated yet

Description

Skills are quickly becoming the new unit of software, but most of them are written once, never versioned, and never tested. In this episode, Oleg from the Docker dev team sits down with a guest from Tessl to talk about how AI-native development is changing the way we build software. They dig into why skills need real package management, how evals prove whether a skill actually adds value, and how Docker sandboxes keep AI agents isolated and safe. Along the way they cover practical cost savings, the integration between Tessl and Docker sandboxes, and why contributing skills to GitHub without versioning or quality control can do more harm than good.

What you will learn: • Why skills are the new unit of software, and how they compare to classes, packages, and npm modules • How skills get assembled into larger reusable units like plugins and extensions • Why AI context "rots" the same way software does, and why versioning and a registry matter • What evals are, and how comparing model behavior with and without context measures real "lift" • How a lack of lift can signal a skill is now obsolete, saving you tokens and money • Why a cheaper model with good context can outperform an expensive model without it • How the Tessl registry adds quality, security, and eval scores to skills • How Docker sandboxes isolate AI agents using micro VMs, secrets injection, and network rules • How Tessl "kits" provision tools and skills inside a sandbox for repeatable, shareable setups

Chapters 00:00 Intro 01:09 Skills are the new unit of software 02:42 Assembling skills into plugins and extensions 04:32 Why writing skills just for yourself falls short 05:17 How Tessl brings package management to skills 07:42 What evals are and why they matter 09:16 Evals vs. tests: measuring real lift 14:22 When a skill becomes obsolete (and saves money) 16:40 Cheaper models with context: Haiku vs. Opus 19:32 Inside the Tessl registry and quality scores 21:14 Tessl meets Docker sandboxes 22:39 What kits are and how they work 23:58 Live demo: spinning up a sandbox with Tessl 25:52 Secrets and vaults inside the sandbox 27:34 Network rules for sandboxes 28:50 Pulling skills into the sandbox from Tessl 31:17 Recap and where to find Tessl

🔥 Want More Docker Content? If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!

Where to find Docker: Docker: https://www.docker.com/ LinkedIn: https://www.linkedin.com/company/docker Bluesky: https://bsky.app/profile/docker.com X: @docker Instagram: @dockerinc

Back to Docker · Report a problem