# AI foundations and design — Learning path | Yishto

Canonical page: https://yishto.com/en/learn/ai-foundations/

Author: [Yishto](https://yishto.com/en/about/)

Understand learning, attention, multimodality, and model adaptation.

Choose model capabilities and explain their limits.

## AI foundations and design

- [Understand neural networks and language models through their objectives](https://yishto.com/en/learn/ai-foundations/learning-attention-and-language-models/index.md): Connect training objectives and token prediction to model behavior, use a softmax experiment to understand aggregation, and distinguish the full architecture from application evaluation.
- [Turn model capabilities into testable task contracts](https://yishto.com/en/learn/ai-foundations/prompts-context-and-capabilities/index.md): Define capabilities, context, outputs, and abstention for classification and extraction, then verify facts, provenance, and execution permissions beyond valid structured output.
- [Handle images, speech, and video inside an application](https://yishto.com/en/learn/ai-foundations/multimodal-image-and-speech/index.md): Separate teaching-media processing into modality tasks, input checks, timing, assets, and review, with explicit evidence limits for sampling, generation, and recognition.
- [Decide between fine-tuning and application changes](https://yishto.com/en/learn/ai-foundations/finetuning-inference-and-model-adaptation/index.md): Compare prompting, retrieval, fine-tuning, and serving through classification failures, including leakage, LoRA assumptions, memory estimates, and recovery of related model artifacts.
- [Define execution responsibility when connecting tools and agents](https://yishto.com/en/learn/ai-foundations/agent-protocols-and-sdk-boundaries/index.md): Distinguish MCP tools, A2A tasks, SDK loops, and skill resources, then use a narrow read contract to check authorization, parameters, and responsibility for results.
- [Build knowledge applications whose failures can be located](https://yishto.com/en/learn/ai-foundations/retrieval-orchestration-and-knowledge-apps/index.md): Separate knowledge applications into ingestion, retrieval, generation, and audit, checking provenance, permissions, abstention, and framework state to locate the failing stage.