diff --git a/README.md b/README.md index 6ace1aa..b7f4341 100644 --- a/README.md +++ b/README.md @@ -21,13 +21,13 @@ Every codebase has unwritten conventions like the order tasks appear in Ansible When an LLM agent needs to follow these conventions, it usually has two bad options: -1. **Stuff every existing file into context** — 15 Ansible roles = 5,000 tokens. You'll hit the context window by the third example. -2. **Guess from one or two examples** — the LLM infers a pattern and often gets it wrong. +1. **Stuff every existing file into context** - You'll hit the context window by the third example. +2. **Guess from one or two examples** - the LLM infers a pattern and often gets it wrong. Dervish replaces both with a **one-call MCP tool**: pass your sequences, get back a ~60-token grammar. By leveraging **Minimum Description Length (MDL) scoring**, Dervish treats the grammar discovery problem as an optimal compression task. the resulting rule is optimized to consume as few tokens as possible without losing the pattern. -**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all — a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say: +**Without Dervish:** token cost scales linearly with examples. **With Dervish:** one compact grammar describes them all In a ~60–200 token rule instead of thousands of tokens of raw examples. Try it out and you too will say:

Dervish animation

@@ -60,7 +60,7 @@ The primary interface is a **Model Context Protocol (MCP)** server. Connect any ### Agent workflow -An LLM agent uses the MCP to discover an unwritten convention from existing examples — compressing hundreds of files into a single ~60-token rule: +An LLM agent uses the MCP to discover an schema from existing examples, thereby compressing hundreds of files into a single ~60-token rule: ```text User: Generate a new Ansible role for installing PostgreSQL.