Understand the mechanism

Parse document structure, split at semantic boundaries, attach titles and metadata, optionally overlap neighboring text, embed each chunk, and retrieve chunks for a query. Parent-child retrieval can search small child passages while returning a larger parent section for generation. Read that as a pipeline, not magic. At each arrow, name the representation, owner, and possible loss.

A useful trace is input → preprocessing → model operation → postprocessing → action. Preprocessing may tokenize, parse, retrieve, resize, or filter. The model operation estimates a continuation, score, noise update, or preference. Postprocessing may validate a schema, fuse rankings, enforce policy, or attach provenance. Only then should the product act.

For an employee handbook assistant, record identifiers for every changeable stage. If two runs differ, you should be able to ask whether the input, prompt, model weights, retrieved corpus, decoding settings, tool result, or policy changed. Without those identifiers, randomness becomes the default explanation for every bug.

The mechanism guarantees only what its explicit deterministic stages guarantee. Learned components produce estimates based on training and current context. Chunking creates retrievable units; embedding maps units to vectors; retrieval selects candidates; reranking reorders them; generation writes the answer. Increasing top-k cannot reliably repair a chunk that never contained a coherent fact. Therefore a successful-looking output does not prove that the right evidence was used. Preserve intermediate artifacts when privacy permits: candidate lists, cited spans, memory IDs, judge scores, coordinates, or agent handoffs.

Latency and cost accumulate across the path. If stages take 120 ms, 480 ms, and 900 ms sequentially, the lower-bound latency is 1.5 seconds before network overhead. Parallel stages take approximately the slowest branch, but then require merging and timeout behavior. This arithmetic matters because an elegant pipeline that misses the user’s deadline is not operationally correct.

A leave-policy answer spans the final sentence of “Eligibility” and first list under “Exceptions.” With 400-token non-overlapping windows, recall@5 is 71%. Adding 60-token overlap raises it to 86% but duplicates 28% of results. Heading-aware 250-token clauses with parent expansion reach 91% recall and only 7% duplicates. Notice the causal language: an observed input or configuration changed an intermediate artifact, which changed a measured outcome. “The model got worse” is not yet a diagnosis. A diagnosis points to a stage and offers a falsifiable test.

When drawing this mechanism, mark trust boundaries. External documents, user text, images, and agent messages are data, not governing instructions. Tools should receive typed arguments and least privilege. Stored traces and memories need access controls because observability can quietly become a second sensitive database.

1. Did the correct input reach preprocessing intact?
2. Was the intended model, prompt, index, or checkpoint loaded?
3. Which intermediate artifact first differs from a good run?
4. Did postprocessing reject, distort, or silently coerce the result?
5. Did the product action reflect the validated output?

Answer these in order. Jumping directly to prompt edits can mask a parser, permissions, retrieval, or serving defect.