One search. Connected ideas.

AI and LLM fundamentals

Ingestion: approved source → secure parse/OCR → coherent chunks + metadata → embeddings → complete published index.

Use this after studying the full explanations. Spend 10 minutes on vocabulary, 10 on RAG and agents, 10 on security/workflows/evaluation, and 10–30 on the insurance design and scenario answers.

LangGraph essentials: nodes return state updates; reducers define merge behavior; edges control next steps; model routes need validation; production needs durable checkpoint storage and authorized threads. An interrupted node can restart, so pre-pause side…

- Deterministic: known rules and transitions. Best for permission, arithmetic, approvals, and business commits.

Secure action flow: LLM proposal → allowlisted tool → identity/authorization → schema + rules → limits → business service → minimal result.

Evaluate no evidence, stale policies, malformed documents, ambiguous dates, denied access, injected content, restarts, duplicate submissions, and uncertain writes. Track source/model/prompt/graph versions, p95 latency, tokens, cost per successful task,…

Cost formula: input tokens × input rate + output tokens × output rate + tools/retrieval/embedding/infrastructure/review, with applicable caching and provider accounting. Prices must be checked for the real provider/model/account.

“Next.js provides the interface and Node authenticates, validates, and applies budgets. A bounded router selects policy RAG, exact claim lookup, guided intake, or staff escalation. RAG returns applicable policy evidence with citations; tools enforce…

What successful outcome does the client need, and can ordinary code provide it?

A practical textbook for building AI applications, agents, and reliable client solutions.

Ingestion: approved source → secure parse/OCR → coherent chunks + metadata → embeddings → complete published index.

Use this after studying the full explanations. Spend 10 minutes on vocabulary, 10 on RAG and agents, 10 on security/workflows/evaluation, and 10–30 on the insurance design and scenario answers.

LangGraph essentials: nodes return state updates; reducers define merge behavior; edges control next steps; model routes need validation; production needs durable checkpoint storage and authorized threads. An interrupted node can restart, so pre-pause side…

- Deterministic: known rules and transitions. Best for permission, arithmetic, approvals, and business commits.

Secure action flow: LLM proposal → allowlisted tool → identity/authorization → schema + rules → limits → business service → minimal result.

Evaluate no evidence, stale policies, malformed documents, ambiguous dates, denied access, injected content, restarts, duplicate submissions, and uncertain writes. Track source/model/prompt/graph versions, p95 latency, tokens, cost per successful task,…

Cost formula: input tokens × input rate + output tokens × output rate + tools/retrieval/embedding/infrastructure/review, with applicable caching and provider accounting. Prices must be checked for the real provider/model/account.

“Next.js provides the interface and Node authenticates, validates, and applies budgets. A bounded router selects policy RAG, exact claim lookup, guided intake, or staff escalation. RAG returns applicable policy evidence with citations; tools enforce…

What successful outcome does the client need, and can ordinary code provide it?

AI and LLM fundamentals

A practical textbook for building AI applications, agents, and reliable client solutions.

AI Engineering learning module

AI Engineering learning module