Skip to content

Repository files navigation

Conversation Architecture

A practical guide to structuring multi-turn conversations with Claude (or any LLM) so that you get sharper answers, spend fewer tokens, and stop fighting context drift.

Most people treat a chat window like a bottomless notepad — they dump a data set, five tasks, and a vague goal into one thread and wonder why the output feels average by message 15. This repo collects the mental models and templates I use to avoid that.

Contents

  1. Context Window Fundamentals — what a context window actually is, and why "it can hold 200K tokens" doesn't mean "it should."
  2. When to Split Conversations — a decision checklist for staying in a thread vs. starting fresh.
  3. The Scaffolding Pattern — a 4-phase structure for high-stakes or multi-step conversations.
  4. Case Studies — the pattern applied to real workflows:
  5. Conversation Templates — copy-paste starting points for common conversation types.

Key takeaway

Conversation design = output quality. How you split, sequence, and frame your prompts matters as much as the prompts themselves.

About

A practical guide and framework for structuring multi-turn LLM conversations. Contains templates, case studies, and architectural mental models designed to optimize context windows, maximize output quality, and prevent context drift.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors