liveBook · Manning

Prompt

As explained in Self-Improving Agents

Text supplied to a language model as instructions or input for an interaction.

A prompt is instruction text that drives an agent. In a RAG system, it is a distinct artifact that can be improved without retraining the model. section 2.1.1 section 2.6

An offline improvement loop compares prompt variants using a signal, such as an LLM judge, and keeps the better version. The model stays fixed; the prompt changes. section 1.2.1 section 2.6

Lead with the verdict

A support agent answers whether a return after 30 days is allowed. Adding “Begin your reply with a direct yes or no, then explain” makes the answer more direct. section 1.2.1

Before:  You are a support assistant. Answer the customer's
         question using the policy documents.
 
After:   You are a support assistant. Answer the customer's
         question using the policy documents. Begin your reply
         with a direct yes or no, then explain.

Compare the original support instruction with its revised version. section 1.2.1

How Self-Improving Agents covers it

How deep it goes
Shows prompt variants being judged and retained as versions, while leaving model weights unchanged.
Examples
Uses a support-agent return question and adds an instruction to begin with a direct yes or no.
What you can do after
Apply it via Helix, an LLM-as-Judge, and SPO to improve a RAG agent's prompt offline.
How it connects
Connects prompts to retrieval-augmented generation, LLM-as-Judge, and self-supervised prompt optimization.

Also explained in

Compare how 64 books explain prompt →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Self-Improving Agents. The section links point to the parts of the book it draws on.