# Case Study: A Support Assistant Over Policy Documents — Prompt & Context Engineering

Source: https://www.skillbyai.com/en/prompt-context-engineering/e-case

> Apply the techniques end to end.

## From overflowing prompts to a lean context

A hypothetical team runs a support assistant over 3,000 policy pages. Symptoms: occasional context-length errors, slow answers, and citations of outdated policies. Their fixes, in order: a token budget with a trimming priority; retrieval filtered to current policy versions and the user's region; a relevance floor and de-duplication; best chunks first and the question last with a short rules reminder; history as a summary plus four recent turns; stable content first for caching; JSON output with citations validated in code; and a not-found path. They test each step with an ablation on 200 real questions. This scenario is illustrative; your own measurements decide which steps matter.

## The assembled pipeline

Each stage maps to a topic in this course.

```text
request
 -> load pinned state + summary + last 4 turns
 -> retrieve (ACL + current versions + region) -> min score -> dedupe -> compress
 -> budget check (reserve output, trim docs, then history)
 -> render template: [system][examples][history][documents best-first][question][reminder]
 -> call model (cache-friendly prefix, max output tokens)
 -> validate JSON + citations -> retry once -> fallback / NOT_FOUND
 -> log versions, tokens, cache hits, stop reason
```

## Fix the biggest failure first

Sort failures from the evaluation by cause (retrieval miss, wrong version, format error) and fix the most common cause before polishing wording.

**Quiz:** In the case study, what fixed citations of outdated policies?

- [ ] Sending all 3,000 pages
- [ ] Raising the temperature
- [x] Filtering retrieval to current policy versions
- [ ] Removing the question

*Answer:* Filtering retrieval to current policy versions. Metadata filtering beats hoping the model notices dates.