Module 2 of 6Lesson 2 of 3~12 min
Write the framing brief
An assistant with a fuzzy scope promises everything, delivers nothing and becomes impossible to evaluate. This lesson teaches you to frame your assistant before the first line of prompt, by setting who it works for, what it must handle, what it will not do and how you will know it succeeds.
Lesson objective
By the end of this lesson, you will be able to write an assistant's framing brief: problem, users, target questions, allowed actions, explicit out-of-scope items and measurable success criteria.
Topics covered
- product scoping
- AI assistant
- functional scope
- success criteria
- framing brief
Where it fits
Frame the assistant
Does my product need an assistant, and to do what exactly?
Lessons in this module
- Identify a use case worth an assistant
- Write the framing brief (this lesson)
- Understand the anatomy of an LLM assistant
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