Module 3 of 6Lesson 2 of 3~15 min
Write a production system prompt
The system prompt sets the assistant's behavior on every exchange, and a sloppy version shows up as inconsistent answers. This lesson teaches you to write and review a production-grade system prompt, while knowing exactly what it can never guarantee on its own.
Lesson objective
By the end of this lesson, you will be able to write and critique a structured system prompt (role, context, rules, uncertainty handling, format, edge cases) and explain what it cannot guarantee.
Topics covered
- system prompt
- prompt engineering
- AI assistant
- system instructions
- LLMs in production
In the glossary
Where it fits
Design the experience and behavior
How should the assistant present itself, answer, say "I don't know" and hand over?
Lessons in this module
- Design the conversational experience
- Write a production system prompt (this lesson)
- Specify the response format for the interface
What you will learn in the course
This lesson is part of the course Build an AI assistant for your product
- Identify a use case that justifies an AI assistant and write its framing brief (problem, users, allowed actions, out of scope, success criteria).
- Design the conversational experience: entry point, tone, handling uncertainty, handoff to a human and response format.
- Choose and justify a knowledge strategy (instructions, injected context, RAG, fine-tuning) and a conversation memory strategy.
- Specify the assistant's tools and actions (data read, actions written, confirmation, permissions) and choose how to build it.
- Identify the risks (injection, leaks, excessive actions, costs) and design layered guardrails that go beyond the prompt.
- Design an evaluation plan with a reference dataset, criteria, grading methods, release thresholds and a regression rule.
- Define production metrics (product, quality, cost, latency), alert thresholds and the loop from user feedback to the evaluation set.
Related courses
- Design a RAG architecture that fits your productAdvanced · ~3 hr 30 min
- Evaluate an AI feature: test sets, metrics and LLM judgesAdvanced · ~3 hr
- Ship and monitor an AI feature in productionExpert · ~3 hr