AI agents

Chunking and indexing strategies

• Chunking Strategies for Retrieval: Size, Overlap and Boundaries
• Ordering Retrieved Chunks for Cache Hits
• Choosing a Pass Threshold for Recall After a Refresh
• Fact-Boundary Chunking: One Claim per Chunk
• Index Refresh: Rebuilding and Re-Embedding When Documents Change
• Re-Embedding After Index Refresh: Batching, Cost and Cutover
• Re-Embedding vs Re-Chunking: Which Refresh Do You Need?
• Span IDs as the Primary Key After a Re-Chunk
• Storing Provenance Alongside Vectors: A Schema for the Index
• Storing Provenance Through a Re-Chunk
• Trust Tiers for Indexed Sources: What a Retriever May Return
• Versioning Embeddings So a Refresh Can Roll Back
• When a Re-Embed Changes the Answer Set
• When a Source Changed on Purpose: Versioning the Ingest Contract