One search. Connected ideas.

A citation points to evidence supporting a statement. Source attribution identifies the original document, location, and version. The model can suggest references, but the application must ensure they map to actual retrieved sources.

Faithfulness asks whether the answer is supported by supplied evidence. Correctness asks whether it is right for the task and real applicable facts. Citation quality checks whether references point to supporting sources, not merely existing documents.

Enforce unique operation keys and optimistic draft versions. Keep large original files in protected object storage. Keep model-visible projections small. A document index and conversation cache are rebuildable derived data; claim and approval records need…

A production reference design specifies failed and uncertain outcomes as carefully as successful ones. Evaluation checks behavior before release; observability detects failures in actual runs. Human escalation is an explicit supported outcome.

Requirements: Upload approved PDFs, track ingestion, ask questions, return source references, and abstain when evidence is missing.

AI and LLM fundamentals

Never accept a model's customerId as proof of the current customer. Never let the model supply an unrestricted email URL, SQL query, database filter, or role field.

Apply CSRF protection where cookie-authenticated mutation routes require it, enforce origin/authentication policy, and use appropriate error semantics. A pending task may return 202; a chat sentence claiming success cannot substitute for a claim receipt.

Ask whether the answer depends on external knowledge and whether the corpus is too large or variable to supply directly. Use RAG for private/changing knowledge with source references; use exact tools for live records. If a handful of permitted documents are…

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

Query rewriting restates a request for search, often resolving references from conversation. Multi-query retrieval searches alternative formulations. Query decomposition splits a compound question into smaller questions that may require separate evidence.

A golden dataset is a curated set of representative inputs with expected outcomes, reference evidence, and scoring criteria. Regression testing reruns these cases after changes. AI tests often allow multiple acceptable phrasings while requiring the same…

Enforce unique operation keys and optimistic draft versions. Keep large original files in protected object storage. Keep model-visible projections small. A document index and conversation cache are rebuildable derived data; claim and approval records need…

A production reference design specifies failed and uncertain outcomes as carefully as successful ones. Evaluation checks behavior before release; observability detects failures in actual runs. Human escalation is an explicit supported outcome.

A citation points to evidence supporting a statement. Source attribution identifies the original document, location, and version. The model can suggest references, but the application must ensure they map to actual retrieved sources.

Faithfulness asks whether the answer is supported by supplied evidence. Correctness asks whether it is right for the task and real applicable facts. Citation quality checks whether references point to supporting sources, not merely existing documents.

Never accept a model's customerId as proof of the current customer. Never let the model supply an unrestricted email URL, SQL query, database filter, or role field.

Apply CSRF protection where cookie-authenticated mutation routes require it, enforce origin/authentication policy, and use appropriate error semantics. A pending task may return 202; a chat sentence claiming success cannot substitute for a claim receipt.

Requirements: Upload approved PDFs, track ingestion, ask questions, return source references, and abstain when evidence is missing.

AI and LLM fundamentals

Ask whether the answer depends on external knowledge and whether the corpus is too large or variable to supply directly. Use RAG for private/changing knowledge with source references; use exact tools for live records. If a handful of permitted documents are…

RAG stands for retrieval-augmented generation. It retrieves relevant external information and provides that information to a model before asking for an answer. It connects language generation to a changing knowledge source without retraining the model.

Query rewriting restates a request for search, often resolving references from conversation. Multi-query retrieval searches alternative formulations. Query decomposition splits a compound question into smaller questions that may require separate evidence.

A golden dataset is a curated set of representative inputs with expected outcomes, reference evidence, and scoring criteria. Regression testing reruns these cases after changes. AI tests often allow multiple acceptable phrasings while requiring the same…

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module

AI Engineering learning module