Skip to content
Heidelberg AI Curriculum
Heidelberg AI
Curriculum

1Pick your portal

MatrixListJourney

2Your references

AI newsDailyChangelogDailyFAQTipsHow-tos
CanvasesGlossaryTools indexApp store (opens in a new tab)LLM index (opens in a new tab)Videos
A living curriculum for practical AI work.
  1. Home
  2. Matrix
  3. Run your own AI

Track T11

Run your own AI

Follow this capability from individual use to systems other people can depend on.

05books
T11-L0101

A model on your own laptop

This mini-book is for Level 1 User. You are running one model for your own work, on your own laptop, through a desktop application. If it is slow, wrong, or unavailable, only your work should be affected. You are not creating a service for colleagues or connecting the model to other tools.

User24 min
T11-L0202

A local model your tools can call

T11-L02 · Run your own AI · Level 2 Power user · 30-minute read

Power user30 min
T11-L0303

Containers, honestly

At this level, colleagues depend on something you built. A container makes an application repeatable; it does not make the application persistent, reachable, secure, or recoverable. You own those boundaries and the evidence that they work.

Builder60 min
T11-L0404

Your own AI server

At Level 4 Integrator, company or lab systems and real data can depend on infrastructure you operate. Moving a working local stack to a server is not a copy operation. It adds provider accounts, DNS, Internet routes, certificates, individual access, patching, release evidence, staging, and an outage that affects...

Integrator120 min
T11-L0505

Serving at scale

At Level 5 Operator, a model endpoint is shared capacity. A configuration that answers one prompt can still fail ten colleagues through queue growth, memory exhaustion, unfair admission, or costs nobody counted. Your job is to publish a measured operating envelope, reject excess work safely, and know when another...

Operator120 min
CurriculumAll tracks

Heidelberg AI Curriculum · 2026