AI Intake Triage for Law Firms

Sarah runs a 2-attorney personal injury firm. She gets about 15 inbound leads a month and signs 8. The other 7 still consume time in intake calls, conflict checks, and polite declines. The leads that do convert often sit in her inbox until she finds a gap between other work, which is often at the end of the day. That is exactly the window where faster-responding competitors reply first.

At 8:47 on a Tuesday morning, a new web form comes in. Rear-end collision, passenger injured, commercial policy on the at-fault driver. Before Sarah has pulled up the form, her Intake Triage agent has already extracted the case facts into a structured summary, scored the lead at 82 against her acceptance criteria, run a conflict check against her practice management system and come back clean, drafted a response email offering a consult slot from her Monday afternoon availability, and assembled a one-page consult memo with the facts, the score, the estimated case value, and a recommended opening question.

Sarah reviews the memo over her first coffee, tweaks one sentence of the response email, and hits send. The consult is on her calendar before the potential client has finished their breakfast.

The agent watches your intake channels (web forms, email, referral partner portals) and responds to every new lead in the minutes after it arrives. For each lead, it extracts the case facts into a structured summary, scores the lead against your written acceptance criteria, runs a conflict check against your practice management system, drafts a first-response email tuned to your tone, and prepares a consult memo you can scan in under 2 minutes.

You stay in the pilot seat. Every email is a draft, every memo is a recommendation, every consult slot is a suggestion. The agent does the sorting and the typing. You make the judgment calls.

The agent drafts. You send. It never emails a lead without your review, never books a consult without your confirmation, and never declines a case on its own. Every action is logged in an audit trail that supports ABA Opinion 512's supervision requirement.

Conflict checks run against the practice management system you already use, so the agent sees the same records your paralegal would during a manual check. Client data stays in your account. Nothing is used to train models. If the agent encounters a potential conflict it cannot resolve cleanly, it escalates to you with the matching records flagged rather than making the call itself.