Every enquiry arrives ready to quote

Step 01

Intake, handled in the CRM

The straightforward half. A form submission creates the contact, attaches the submission as a note, opens or updates an opportunity, and alerts the team internally.

This runs natively inside the 3rive Marketing Hub. Nothing clever is happening yet, and that is the point: the record exists before any AI touches it, so nothing can be lost if a later step needs rerunning.

Step 02

An AI brain, not a flowchart

This is where most automations fall over. A linear workflow has to guess every path in advance, and an enquiry inbox does not behave. One message is a new booking request, the next is an existing customer chasing a date they already hold.

So we did not build a flowchart. We built a decision layer that holds a set of tools and works out which one the message needs. Each tool triggers a real workflow underneath. The branching lives in the model's judgement rather than in a hundred hard-coded conditions.

Path A

A new enquiry, missing detail

The brain runs the create enquiry workflow, then checks whether there is enough to price. If something is missing it writes back and asks for it, and keeps the thread open until the answer arrives. If the enquiry already has everything, it does not invent a reason to email: it thanks them and tells them a person will be in touch.

Path B

An existing customer, chasing a booking

Same inbox, completely different job. The brain looks the contact up, finds the booking they are asking about, pulls any other bookings held against them, summarises the lot, and hands that summary back to itself before replying. The customer gets a straight answer instead of a holding message.

Step 03

Live chat, handled in the Hub

Chat needed the same outcome by a simpler route, so this one runs natively in the 3rive Marketing Hub. The conversation is tagged by what the visitor actually wanted, summarised into notes, and written onto the right opportunity, creating one if none exists.

We flagged that this opens an opportunity for chat visitors who were never going to book. The client wanted it that way, so that is how it was built.

Step 04

Making it readable

Two channels were now writing notes against the same contacts, from the email agent and the chat agent. Accurate, and a mess to read. Nobody wants to reconstruct a booking from a stack of timestamped notes.

So we added a clean-up pass. It fires whenever a record changes, finds the open enquiry, formats what has been captured into the opportunity's own fields, and clears tags that no longer apply. The team reads a structured record, not a transcript.

Step 05

Nothing goes quiet

Qualified enquiries still go cold if nobody picks them up. The last piece watches the pipelines for opportunities that have sat untouched past a set number of days, alerts the team, and raises a task against the record so the chase is assigned to someone rather than hoped for.

The result

The qualifying conversation happens before anyone clocks in

The back and forth that used to eat a morning now happens on its own, at whatever hour the enquiry lands. What reaches the team is a structured opportunity with the answers already in the fields.

The people who used to chase details now write quotes. That is the whole trade: not a tool the team has to operate, but work that is already done when they arrive.