Blog: How Lawyers Can Control AI Outputs With Effective Prompts
Improve the quality of your AI outputs by using prompt engineering.
AI is increasingly used in legal work for summarisation, analysis, and drafting, but the quality of outputs depends entirely on how you ask the question. This is where prompt engineering comes in.
What is Prompt Engineering?
Prompt engineering is the practice of crafting effective questions or instructions to guide the behaviour of an AI model. A well-designed prompt influences what information is retrieved, how tone is shaped, and the structure of the response.
Why It Matters for Legal Professionals
The quality of AI outputs depends on how you ask.
Lawyers can control tone, structure, and risk exposure through well-engineered prompts.
Structured, specific, and context-aware prompts are everything when working with an LLM.
The GOLDEN Framework
The best prompts are structured, specific, and context-aware. For legal professionals wanting clarity, compliance, and consistency, we recommend the GOLDEN framework:
G — Goal:
Define the Task
“Summarise this contract in plain English…”
O — Output Format:
Specify the Structure
“…in a 5-bullet executive summary with key risks highlighted”
L — Legal Context:
Provide Setting, Audience, and Jurisdiction
“…for a general counsel reviewing a SaaS agreement under Australian law”
D — Data Provided:
Include Source Material or Specify Where to Find It
“Use the contract text pasted below”
E — Examples:
Show what Good Output Looks Like
“Example of desired output: [Insert format or sample]”
N — Nuance & Constraints:
Add Tone, Exclusions, or Compliance Considerations
“Avoid speculative language. Do not include boilerplate summaries”
Sample Legal Prompt Using the GOLDEN Framework
"You are an experienced legal analyst. Summarise the following contract in plain English, focusing on key obligations, risk clauses, and renewal terms. Provide the output as a 5-bullet executive summary suitable for a general counsel. The contract is under New South Wales law. Use only the text provided. Do not add interpretation or legal advice. Keep it under 300 words.”
For legal teams looking to leverage AI safely and effectively, mastering prompt engineering is essential.
