I skipped RAG for my AI app's voice. Static markdown won.
Member-only storyProgrammingSoftware DevelopmentWeb DevelopmentProductivityStartupI skipped RAG for my AI app's voice. Static markdown won.Voice needs a consistent baseline, not semantic search. Here is the $0 file that beat it.Daniel Rusnok7 min read·12 hours ago--ListenSharePress enter or click...
Member-only storyProgrammingSoftware DevelopmentWeb DevelopmentProductivityStartupI skipped RAG for my AI app's voice. Static markdown won.Voice needs a consistent baseline, not semantic search. Here is the $0 file that beat it.Daniel Rusnok7 min read·12 hours ago--ListenSharePress enter or click to view image in full sizeVoice = baseline. Knowledge = retrieval. | Generated with ChatGPTNot a member? Use this link.I was one commit away from putting a vector database behind my AI’s voice. I deleted that plan and used a single markdown file instead. The drafts got better, and the context now costs me $0 a month.The feature is a Note drafter I built into my Substack growth dashboard. You give it a prompt like “build-in-public milestone, 3 variants” and it returns three Substack notes that sound like me. What made it worth writing up was where the complexity actually belonged, which turned out to be somewhere much simpler than I first assumed.The first design I sketched stored every published note and every voice decision in a vector database, and let the model retrieve the relevant pieces per draft. Embeddings and a similarity search in front of the model, the standard RAG pipeline. That setup is built for fetching knowledge on demand, which sounded right until I looked at what voice actually needs.What voice actually isVoice for an AI assistant is a stable identity: who you are and what tone you use. It is the part that should come out…Source: Generative AI Pub — Published — Category: Image AI