Vom Prompt zum Loop: Die Evolution der KI-Steuerung · Part 2 of 8
Kontext ist König
Context Engineering, Memory und Retrieval-Augmented Generation verstehen
How to give a language model the right knowledge: context windows, memory and retrieval-augmented generation.
Listen on
Preview on Spotify
About this audiobook
A model only knows what is in its context. Part 2 explains the working memory of an AI, why the context window is the scarcest resource you manage, and how retrieval-augmented generation feeds the model your own knowledge at the right moment.
It covers building a knowledge base on a vector database, shaping behaviour with system prompts and memory, and dosing context so answers stay precise instead of drifting into hallucination.
Published in German, 38 minutes. For anyone building their own AI systems or improving the ones already in use.
Chapters
- Das Arbeitsgedächtnis der KI
- System-Prompts, Memory und RAG
- Kontext richtig dosieren
Want to apply this in your own business?
The audiobooks explain the ideas. In the Kickstart workshop your team builds its first tool in one day.
See the courseVom Prompt zum Loop: Die Evolution der KI-Steuerung
-
1. Das Handwerk der WorteRoles, few-shot examples, chain of thought and system instructions: prompting as a craft, not a guessing game.
-
3. Die Entstehung der AgentenFrom answering machine to actor: tool use, function calling, ReAct and the Model Context Protocol.
-
4. Das Harness und die UmgebungThe environment decides whether an agent is production-ready: guardrails, sandboxes and automatic evaluators.
-
5. Die Geburt von Loop EngineeringPlan, execute, observe, refine: why autonomous work cycles beat single prompts on every long task.
-
6. Anatomie eines perfekten LoopsStop conditions, context rotation, memory and a human emergency stop: what keeps an autonomous loop safe.
-
7. Verifizierung und Self-CorrectionA model must not grade its own work: generator-evaluator loops, hard tests and fallbacks for AI you can trust.
-
8. Das autonome ÖkosystemTeams of specialised agents, hierarchy versus swarm, and the human as architect, auditor and conductor.