Skip to main content

Merlin Engage Agents - Collect & Qualify

What is a Merlin Engage Collect and Qualify Agent?

The Collect and Qualify Agent is a Merlin Engage agent that has a conversation with your leads by text or email to collect whatever information Merlin Qualify needs to make a confident decision.

How it works with Merlin Qualify

The Collect and Qualify Agent is linked to a Merlin Qualify profile, which is what tells it what information to look for. When Qualify can't make a confident call on a lead, the result comes back Inconclusive, or with a Low Confidence. The Collect and Qualify Agent automatically starts the conversation based on this, and sets out to collect more information.

How it gathers information

The agent asks the lead directly for whatever's missing, updating the matter as it goes. Once it has enough, it hands the matter back to Qualify, which re-evaluates the lead with the new information and lands on a final outcome category (Chase Hard, Refer Out, Reject, or whatever your firm uses.)

Can hand off to another agent

Once a lead qualifies, it doesn't have to end there. You can route it straight into a Booking Agent to start scheduling, or into a different Collect and Qualify Agent. From the lead's perspective, it feels like one continuous conversation.

See Merlin Handovers for how that connection works.


Setting Up an Agent

Merlin Engage agent setup happens entirely inside Merlin in your left navigation. Before you start:

  • You need at least one Merlin Qualify agent set up, since Engage agents must be linked to one.

  • Your firm needs at least one SMS number configured. Merlin Engage sends and receives texts through this number, and it won't run without one.

1: Create the agent

From the left navigation, go to Merlin → Engage → New Agent.

Collect and Qualify Agents use the Collect Missing Info Agent Objective.

It links to a Qualify profile and follows up over SMS/email to fill in gaps.

Give the agent a name

This is an internal-only name, used exclusively by your team. This name is not ever used by the agent with your leads.

Link the agent to a Merlin Qualify profile

This is required for Collect and Qualify Agents, it's how Engage knows what information to look for.

Optional: Analyze My Firm's Tone

This scans your firm's past text messages to suggest a tone and starting instructions. It's optional: Engage works well without it, and skipping it saves setup time.


2: Identity & Tone

Agent Identity

Set an Identity Name

You can name it like a real team member (e.g., "Artie") or something generic. This is the name it'll use to introduce itself to leads.

Optional: Identity Role

This is used as another identifying option for the agent, like "Intake Coordinator."

Add Supervisors

These are the users who'll be notified if a message needs approval or a conversation needs to be escalated.

Communication Tone

Choose Professional, Balanced, Casual, or Empathetic as the base of your agent's voice and style of communiciation.

Channels

Choose which channels the agent can use (SMS, email, or both) and mark one as primary. If you enable a second channel, the agent can fall back to it if a lead replies there, or if it fits the content better.

If Email is toggled on, you'll want to configure your email settings, including:

  • Subject - Used for the first email in a conversation. Merge fields are supported.

  • Send From - Role options (Lead Attorney, Matter Owner, …) resolve to that matter’s assigned user at send time. Unassigned roles send from the firm mailbox.

  • CC/BCC - Any users or relationship types are available

  • Email Signature - either appends the sender’s signature, with the firm signature as fallback, or customize one for the specific agent:

    • Footer: Appended to the bottom of every email (e.g. firm name, contact line).

    • Disclaimer: Appended when to the bottom of every email (used for common for law-firm confidentiality notices.)

    • Physical mailing address: Shown in the footer and required for CAN-SPAM unless the signature already carries it.

    • Font & Font size

Agent Instructions

Agents come with default instructions that they will always follow. You can also use Custom Instructions to further refine how the agent should behave, and Never Say Rules to block specific words or phrases.


3: Engagement Settings

When to Engage

By default, Engage automatically activates when its linked Qualify profile scores a matter as Inconclusive. You can also turn on a toggle to activate on Low Confidence scores, which generally a good idea, since a low-confidence score usually means information is still missing.

Conversation behavior

Operating mode

Choose how much autonomy the agent has:

  • Manual Review

    • Every message is drafted and held for a supervisor to approve before it sends. This is the default, and we recommend starting here for your first few tries so you can see exactly what the agent will say.

  • Autopilot

    • Messages send automatically, no human review needed. Most firms move to Autopilot once they're comfortable with the messages Engage is generating.

AI Disclosure

Set your AI Disclosure preference: either Escalate to a Human immediately or Acknowledge & Confirm before moving on with the conversation. If you choose Acknowledge and Confirm, you have the option for a custom confirmation message:

Cadence Settings

  • Initial outreach and replies during an active conversation always go out immediately. For example, a lead who came in at midnight gets an immediate response.

  • Follow-ups to an unresponsive lead are time-restricted. Set how often follow-ups goes out by adjusting the Follow-Up Pace slider, and how long follow ups can continue for:

  • Quiet hours are on by default and only only to these follow-ups. Adjust the days and hours here to control when unresponsive-lead follow-ups are allowed to go out.

Note: recurring follow-ups sent by text count against your firm's total SMS volume.

Engagement Summary

Determine if you want the agent to add a conversation summary to the matter's notes after engagement ends

Notifications

Supervisors will be notified when a drafted message is waiting for approval, or when a conversation completed, was escalated to your team, or stopped because an exit condition was met.

When to Stop Engaging

Beyond your own exit conditions, the engagement also ends automatically if all required information has been collected, the lead texts STOP, or frustration or incoherence is detected. These safeguards are always on and can't be turned off.

Matter-based exits

Set whether stage or status changes should stop the engagement

Conversation Limit

A soft cap on total messages; the agent wraps up gracefully rather than cutting off abruptly)


4: Handover

Route qualified leads by their Merlin Qualify category, and choose what happens next for every other outcome.

When a lead qualifies, each outcome category from your linked Qualify profile (Chase Hard, Chase, Refer Out, Reject, Inconclusive, etc.) gets its own Next Step:

  • Hand off the lead to another Booking Agent or Collect and Qualify Agent, so it moves straight into a new conversation with a new goal.

  • Human intervention, which notifies a supervisor.

  • Stop here, which simply ends the engagement with no notification.

All other outcomes (Unsuccessful, Declined, Unresponsive, Message Limit Reached, Opted Out, and Escalated) work the same way and notify a supervisor by default, but you can route any of them to another agent instead.

When a lead is handed off, the conversation continues seamlessly. The next agent doesn't reintroduce itself or start over, it just picks up where things left off.


5: Test the agent

Before turning your agent on, use the Test Agent tab to simulate a conversation without sending real messages. Pick a matter that's currently Inconclusive in Merlin Qualify, and walk through the exchange. You can approve or revise each drafted reply. This is a safe way to see exactly what a live conversation will look like before any lead sees it and without affecting your SMS count.

Test mode never updates your actual matter data, so it's safe to run on any real matter.


6: Activate

Once you're happy with how the agent performs in testing, turn it Active from the upper right corner:

Did this answer your question?