Claude

Learn how LLMs like GPT, Claude, and Llama process and generate human language at scale.

Design, version, and evaluate LLM prompts for production — system vs user roles, few-shot, chain-of-thought, and the limits that push you toward RAG, tools, and fine-tuning.

Engineer MCP host–client–server integrations: tools/resources/prompts, Streamable HTTP transports, auth, timeouts, and the 2026-07-28 stateless protocol core—without replacing orchestration or guardrails.

Foundation models, autoregressive and diffusion generation, and the engineering patterns required to ship reliable applications on probabilistic outputs.

Learn why LLMs use tokens, how BPE and SentencePiece work, and how token budgets govern context, latency, and cost.

Understand how LLMs invoke external tools and APIs—including computer use and browser use—to extend capabilities beyond text generation.

Engineer typed LLM tool intents with schema validation, authorization, timeouts, idempotency, observability, and safe production execution.

Engineer reliable LLM context budgets across instructions, evidence, history, tools, and output—with retrieval, truncation, summarization, and production observability.

Why free-text LLM output fails for machines, constrained decoding vs prompt-only JSON, OpenAI JSON Schema, Pydantic validation, and production patterns with Instructor-style retries.

Anthropic Claude family — Sonnet 5, Opus 5, Haiku 4.5, long context, MCP, and workload-based routing vs GPT/Gemini.

Systematically testing prompts — versioning, A/B comparison, format compliance, and regression detection in CI.

Reducing LLM spend — workload-based model routing, prompt compression, caching, batching, and token-aware context design.

Why LLMs hallucinate — next-token prediction is not truth-seeking — and how to mitigate with RAG, tools, structured outputs, abstention, detection, and verification.

Structured path from LLM foundations to production AI — RAG, agents, evaluation, observability, and portfolio-ready engineering habits.