Legal Research Assistant
The AI generates outputs for a lawyer to review. It does not act independently.
Human-in-the-Loop · no detailed pattern
Examples
Real workflows mapped to the Loop model. Each example shows which governance pattern fits and why: review, monitor, or own.
The AI generates outputs for a lawyer to review. It does not act independently.
Human-in-the-Loop · no detailed pattern
The human still decides whether to rely on the summary.
View detailed architecture →The system monitors at scale and escalates relevant changes.
View detailed architecture →The system classifies, routes and creates operational consequences.
View detailed architecture →The system may trigger reminders, escalate risk and affect deadline management.
View detailed architecture →External communication creates higher risk. HAL may apply, but some actions may still require Human-in-the-Loop approval.
View detailed architecture →Detailed governance designs for common agentic workflows, including flow, controls, escalation paths, and HAL scores where applicable.
An agent that receives inbound matters, extracts key facts, classifies matter type, and proposes a routing, leaving the assignment decision to a human.
An agent that watches regulatory sources, identifies changes relevant to the business, and drafts impact summaries for the compliance team.
An agent that reviews incoming contracts against a playbook, flags deviations, and proposes redlines for a lawyer to approve.
An assistant that drafts client communications for a professional to review and send, with drafting-only authority enforced in code, because the defining risk at this band is authority creep.
An agent that extracts obligations from executed contracts, schedules reminders, and notifies owners as deadlines approach.
An agent that orchestrates onboarding: collecting documents, running checks, and progressing the case, pausing for human approval at decision gates.
An agent that resolves common customer requests end to end within tight limits, and hands off anything outside its remit.
An agent that monitors transactions and communications for compliance risk, prioritising cases for the surveillance team.
An agent that moderates user content against policy, auto-actioning clear cases and escalating the ambiguous ones.
An agent that approves low-value, low-risk payments automatically within strict limits. This is the highest-autonomy pattern, demanding the strongest controls.