Multi-document synthesis with Claude XML

Read across many sources at once and produce a single coherent answer.

How to apply the pattern

1. Give each document a short, unique <source>. Use stable IDs (doc-1, doc-2) the model can cite.
2. Pre-summarize very long documents if needed. If individual passages exceed ~5k tokens, consider a map-reduce: summarize each, then ask for synthesis on the summaries.
3. Be explicit about the comparison axis. "Identify points of agreement and disagreement" or "rank by recency" — vague synthesis prompts give vague output.
4. Ask for a structured synthesis. Use <format> to specify columns or sections.

Worked example

<documents>
  <document>
    <source>doc-1: vendor-A-quote.pdf</source>
    <document_content>{{ vendor_A_text }}</document_content>
  </document>
  <document>
    <source>doc-2: vendor-B-quote.pdf</source>
    <document_content>{{ vendor_B_text }}</document_content>
  </document>
  <document>
    <source>doc-3: vendor-C-quote.pdf</source>
    <document_content>{{ vendor_C_text }}</document_content>
  </document>
</documents>

<instructions>
Compare the three vendor quotes. Produce a markdown table with columns:
Vendor, Price (USD), Support Tier, Notable Caveats. Then write a one-paragraph
recommendation citing sources in [doc-N] format. If any quote is missing a
field, write "not specified" — do not infer.
</instructions>

Tips

• Watch your context window. Even with 200k+ tokens, attention degrades on huge blobs — chunk aggressively.
• Citations are only as good as your source IDs. Use ones that map back to your storage.