Copilot for Legal Services

Course subjects

Prompting Effectively with Copilot

• Why vague prompts create legal risk

• The Goal-Context-Sources-Expectations prompt model

• Using constraints to control scope, tone, and jurisdiction

• Preventing hallucination, overreach, and implied legal advice

• Refining a prompt once, then validating manually

Legal Document Review and Issue Identification

• Reviewing a contract, policy, or legal document

• Identifying key clauses, obligations, and risks

• Highlighting ambiguity or missing information

• Distinguishing facts from interpretation

• Output: legal issue summary

Drafting and Rewriting Legal Content

• Using Copilot to draft or rewrite legal text

• Controlling language precision and neutrality

• Ensuring outputs remain within drafting assistance boundaries

• Output: draft or revised legal document section

Legal Advice Structuring (Not Advice Generation)

• Outlining possible legal considerations or approaches

• Identifying risks, dependencies, and unknowns

• Preparing internal discussion points rather than advice

• Output: legal considerations outline

Legal Options and Internal Decision Support

• Presenting alternative legal options or interpretations

• Making trade-offs explicit (risk, precedent, compliance)

• Drafting internal justification language

• Output: legal options summary

Researcher Agent: Scaling Legal Research After the Fundamentals

• Why Researcher is not a substitute for legal judgement

• When Researcher is appropriate (case law scanning, legislative comparison, precedent research)

• How to convert manual legal research steps into a Researcher task

• Responding to Researcher clarification questions

• Reviewing and validating Researcher outputs before use