Skip to content
Heidelberg AI
Curriculum
Heidelberg AI
Desk
Search the whole curriculum
Search
‹
☰
Course index
Journeys
Learn by Level
List
Matrix
All books
Compare the outcome you want, then open a book. Filter by level and track.
Level
All levels
L01 · User
L02 · Power user
L03 · Builder
L04 · Integrator
L05 · Operator
Track
All tracks
T01 · Foundations & judgement
T17 · Structure & understand
T02 · Chat & assistants
T03 · Prompting & context
T09 · Create media
T15 · AI in research
T18 · AI for lab data
T04 · Your documents & knowledge
T05 · Automation
T06 · Build apps
T07 · Agents
T21 · Delegate desk work
T20 · AI harnesses
T08 · Write code
T19 · Share & review code
T10 · Data & analysis
T14 · Connect your tools
T11 · Run your own AI
T12 · Security, privacy & governance
T13 · Adoption & enablement
T16 · Choose tools
Sort
Curriculum order
Shortest reading time
All books
Not started
In progress
Completed
Progress is saved in this browser only.
1 book
Clear filters
Agents
1
T07-L03
Build a Small Agent Your Colleagues Can Run, Test and Stop
An agent folder (instructions, permissions file, reference files, test cases with expected results, check script, README naming maintainer and deputy) that a colleague clones and runs; it passes when their check run prints PASS, nothing outside the output folder changed, and they produce one real draft from the README without asking you.
Builder
20 min read
Tools
AI models