Understand the mechanism

Parse documents, split on structure with target token ranges (often ~300–800), keep heading paths, add limited overlap, attach metadata, then embed.

Read the chunking path as a pipeline for the employee handbook assistant. At each stage, name the representation, the owner, and how information can be lost. Identifiers must mark prompt versions, model versions, indexes, and policies so “randomness” is not the default explanation for every bug in chunking.

If exceptions live 120 tokens after a rule and chunks are 80 tokens with no overlap, retrieval can return the rule without the exception—measurable as citation-support failures. Scoped specifically to chunking / employee handbook assistant / mechanism.

Keep the unit and the denominator visible when you discuss chunking. A percentage without a base, or a latency without a percentile, hides the failure mode this chapter cares about on the employee handbook assistant.

Learned stages estimate; deterministic stages enforce. A fluent result from the employee handbook assistant does not prove chunking used the right evidence. Preserve intermediates when privacy allows—candidate lists, traces, scores, citations—so you can see the first broken stage in the chunking path.

Operational correctness for chunking includes deadlines on the employee handbook assistant. If stages that feed this workload sum past the user’s patience, trim earlier—usually pack less, retrieve less, or parallelize—before blaming the model vendor for chunking. Mechanism diagrams that ignore time are incomplete.

Also pin one numeric memory from this chunking chapter: If exceptions live 120 tokens after a rule and chunks are 80 tokens with no overlap, retrieval can return the rule without the exception—measurable as citation-support failures. That number is not decoration; it is a template for how claims about chunking on the employee handbook assistant should look in design docs. Scoped specifically to chunking / employee handbook assistant / mechanism.

People confuse chunking with neighboring buzzwords when debugging the employee handbook assistant. Before changing prompts, ask whether the broken stage was evidence gathering, the chunking judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried chunking and it failed”) that blocks the next team on the employee handbook assistant. Scoped specifically to chunking / employee handbook assistant / mechanism.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to chunking for rag rather than generic AI advice.