LLM Systems Foundations
Build a connected mental model from tokens through retrieval evaluation security and operations.
0/31 required evidence gates
Learning workspace
Follow prerequisite-safe paths, practice decisions in deterministic labs, and turn learning into exportable project evidence. Progress remains private in this browser.

Active path
--
0 of 37 concepts
Mastered
--
Weakest evidence: activity 0%
Labs completed
--
Of 15 available
Projects active
--
Of 7 tracks
Active path
How model inputs become discrete identifiers and why token boundaries affect cost and meaning.
Why: This is the next prerequisite-ready concept in the active path.
ContinueApplication contracts
Establish model interaction output tool and context contracts.
Grounded product
Connect retrieval provenance generation and full-stack product boundaries.
Operating system
Gate and operate the product with testing tracing security and economics.
Applied evidence
Demonstrate the path through current assessments, lab attempts, and project evidence.
Choose a route
Build a connected mental model from tokens through retrieval evaluation security and operations.
0/31 required evidence gates
Design an observable full-stack LLM product from capability validation through interfaces retrieval evaluation security and operations.
0/43 required evidence gates
Build evidence-carrying retrieval systems from ingestion and provenance through search reranking grounded generation and evaluation.
0/26 required evidence gates
Engineer bounded tool-using systems with explicit workflows state protocols evaluation observability security and human control.
0/31 required evidence gates
Turn product intent and risk into representative evaluations release gates traces service targets and continuously improving regression evidence.
0/21 required evidence gates
Understand inference engines memory scheduling batching routing scaling distributed execution lifecycle controls observability and economics.
0/23 required evidence gates
Master formal semantic modeling, RDF/OWL triple stores, Domain-Driven Design integration, enterprise Data Mesh virtualization, and Neuro-Symbolic GraphRAG.
0/9 required evidence gates
Learn how blockchain systems execute and reach consensus, build and secure smart contracts, reason about rollups and data availability, understand zero-knowledge and verifiable computation, evaluate decentralized AI compute/storage systems, and design AI agents capable of safely interacting with programmable wallets and on-chain protocols.
0/12 required evidence gates
Tokenization and Context Window Visualizer
Inspect deterministic token approximations and allocate a finite context budget.
Prompt RAG Fine-Tuning or Tool-Use Decision Lab
Match system symptoms and constraints to an appropriate intervention strategy.
RAG Pipeline and Retrieval Parameter Visualizer
Tune chunk size retrieval breadth hybrid weight and reranking in a deterministic pipeline.
AI Architecture Decision Workbook
not startedProduce evidence-backed architecture decisions for model access context tools state evaluation security and operations.
Production AI System-Design Casebook
not startedDesign three constrained AI systems and defend boundaries data flows failure handling evaluation and operating choices.
Production RAG Blueprint
not startedSpecify an evidence-carrying RAG system from source onboarding and indexing through retrieval citations evaluation and operations.
Visual completion grid across 6 production AI engineering domains.