The 200-document RAG pipeline that lets any model write in your brand voice

Every brand team that tries to make GPT-4 or Claude 'sound like us' eventually hits the same wall: prompts get longer, outputs get blander, and nobody is sure which example in the system prompt is doing the work.

RAG, retrieval-augmented generation, solves the wrong problem if you treat it as a search engine. Treat it as a brand-voice corpus instead, and the picture changes. Index 200 of your highest-quality past assets (long-form, social, lifecycle, scripts), retrieve the closest 6 by semantic similarity, and inject them as in-context exemplars before the model writes anything.

The chunking strategy matters more than the embedding model. We chunk by rhetorical unit (headline, subhead, opening paragraph, CTA) rather than by token count. The retrieval is then filtered by asset type, so a paid social brief retrieves paid social exemplars, not a 2,000-word blog intro.

The payoff to look for is fewer editor passes per asset, because the model starts from your own exemplars instead of a description of them. Track your own editor-pass count before and after; we have no measured figure to quote.

The full chunking schema, the embedding model we landed on, and the retrieval prompt template are in the appendix.