← Coding JARVIS · all lessons
2
Multi-step Agent Loops
AimLearn to sequence dependent agent steps in a plan-act-observe loop, enabling autonomous task execution, to produce a multi-step agent loop.
2Skill · quantified
Skill
Measured by
Data-type family
Rubric
3AI × skill → tasks
AI feature
Handoff
4Artefact → capstone
Deliverable Working Agent Loop
Brief t1_stage_larp.a1_artefacts.briefA documented loop that takes one messy real-world goal, drives an AI agent through act-observe-decide turns until a stated stop condition fires, and returns a finished result you would actually use.
Lesson stages 4 stages · 9 scenes
Stage 1 •arcade arcade
Memory Chain
hook
The Loop That Would Not Stop
hook
Trace The Loop
Stage 2 •dossier dossier
Scenes
Stage 3 •workbench workbench
Scenes
Stage 4 •larp larp
Cold Open
Brief
Rubric
Roles
Execution
Boss Fight