Call intelligence
Hear what every caller wanted — and what your team couldn’t answer.
Every inbound call transcribed and scored — that pipeline is built and running. Two reads on top of it are in build: the demand your phone is already capturing, and the questions your team keeps missing.
14-day trial. No card. No contracts.
Top requests this week
In build- Emergency water damage 34
- Blocked drain, same day 27
- Quote for a full re-roof 19
- Gutter cleaning you don’t offer this 12
Questions your team couldn’t answer
In build- “Do you work weekends?” 9 calls
- “Is the callout fee taken off if I book?” 7 calls
- “Can I pay in instalments?” 6 calls
Illustrative rows, not a customer account. We have no customers yet — see below. Demand and unanswered-question detection are in build; the transcription and labelling pipeline underneath them is built.
The status quo
Your phone is the best research you own, and none of it gets written down.
Nobody has time to listen
The recordings pile up and roughly none get played. Whatever the caller said about your price, your competitor or your opening hours died with the call. A business taking forty calls a week is throwing away forty pieces of research a week.
The same questions get fumbled
Someone asks about weekend work, or financing, or whether you cover their suburb, and gets a hesitant answer and a promise to call back. It happens again the next day, to a different person, and no one ever finds out it is a pattern.
Demand shifts land a season late
The requests coming down the phone change weeks before the revenue does. Without anything counting them, you notice a new service, a new competitor or a dead season only once it has already shown up in the bank.
What it does
What your calls already know.
One pass over every call produces all of it: what was asked for, what could not be answered, what it was worth, and where it came from.
Status, plainly: the transcription and labelling pipeline is built and running. Demand intelligence, team feedback, the REST API and the MCP server are not. Each cell below says which.
Every call, not a sample
Every call gets a verdict.
We transcribe each recording, then attach a structured read: what the caller wanted, how ready they were to buy, what was promised, how it ended, and whether it was spam or voicemail. On all of them, not the handful somebody had time to listen to.
- What they wanted. The request in plain terms, plus the questions they asked — the raw material for demand and coaching.
- Outcome and intent. A closed vocabulary of outcomes plus an intent score, so you can filter instead of listening.
- Estimated value. A range, not a false point estimate — anchored to what was actually discussed on the call.
- Spam and voicemail flags. The two categories that quietly inflate call counts and distort every average built on them.
- Traceable labels. Every label points at the part of the transcript that produced it. No black box.
What people actually called about
In buildHear what every caller wanted — including the things you don't sell yet.
Every call carries a request. Aggregated across hundreds of them, those requests are the clearest demand signal a business has, and most of it evaporates the moment the call ends.
Coach from evidence, not memory
In buildFind the questions your team couldn't answer.
The most useful coaching material your business produces is the moment a caller asks something and nobody has a good answer. Those moments are invisible unless somebody listens to every call.
One place for all of it
Keep track of everything, in one place you can audit.
Calls, sources, outcomes and revenue in one view — with the counting rules published, so the numbers survive an argument.
For when you don't want a dashboard
PlannedAsk your calls what happened.
A versioned REST API and a read-only MCP server, so your call data is available to your own tooling and to an AI session without anyone opening a chart.
All of it
One dataset underneath
Every surface reads the same labelled calls, and every number opens the rows behind it.
Demand intelligence
In buildHear what every caller wanted — including the things you don't sell yet.
Every call carries a request. Aggregated across hundreds of them, those requests are the clearest demand signal a business has, and most of it evaporates the moment the call ends.
What callers asked for, grouped and counted, so a rising service shows up as a trend and not a hunch.
Services people asked for that you do not offer, or do not offer in that area — the expansion list your calls are already writing.
Week-on-week movement in what callers want, so seasonality and new competitors surface early.
Every number opens the calls behind it, with the sentence that produced the label.
Team performance
In buildFind the questions your team couldn't answer.
The most useful coaching material your business produces is the moment a caller asks something and nobody has a good answer. Those moments are invisible unless somebody listens to every call.
Questions asked on calls that went unanswered, unclear, or got a promise to call back — ranked by how often they recur.
How each person handles calls, with the specific calls behind the read. Objective input for a one-to-one, not a scoreboard.
Calls that showed buying intent and ended without a next step.
Recurring gaps become a short list of what to teach next, with real caller wording to practise against.
Who it’s for
Any business where the phone still decides the week.
The analysis is the same everywhere. What you do with it is not, so each page below answers one buyer’s version of the question. All solutions.
Business owners
You take the calls every day. See what they add up to without listening to one.
→Home services
Emergencies, quotes and bookings separated, so the urgent job is not treated as an enquiry.
→Multi-location
Compare sites on how they answer the phone, not just how many calls each one got.
→Agencies
Report on what a client’s calls were worth, and show when a lost lead was not the advertising.
→Lead generation
Paid per call: which sources send callers who qualify, and which ones send noise.
→Call networks
One scoring standard on both sides of the desk, so a disagreement has a transcript behind it.
→Connections
Reads from your stack. Writes nothing to it.
This is a roadmap, not a logo wall, and none of it is finished. Ringba and Search Console are in build. CallRail, Retreaver, Sheets, CSV, Slack and MCP are planned. Every integration page states its own status, what we pull, and what it will not do.
Instead of a logo bar
No customer logos yet. We launched in 2026.
There are no customers, so there are no names, counts, quotes or star ratings to put here. Inventing them would be the first thing a careful buyer checks and the last thing they would forgive, so the slot stays empty until there is something real in it.
The same rule governs the rest of the site. Anything not built yet is marked as in build or planned, on the page where it is described.
Built by an operator, on their own calls
This started as internal tooling for a business that lives on inbound calls. The first questions it answered were our own: what are people actually ringing about, and what did we fail to answer. Case study one will be that business, including what it was getting wrong before the tool existed.
Check the counting, not the copy
The methodology page names the exact field we treat as revenue and how duplicate calls are handled, so you can reconcile against your own reporting. The disqualification page says plainly who this is wrong for.
Pricing
Metered on calls analyzed. Not seats, not minutes.
Your phone system already meters your minutes. A second minute-meter on top would be double-dipping, so you pay for a unit you can forecast.
Operator
For the solo operator running their own traffic.
Scale
RecommendedFor operators running real volume across sources.
Agency
For agencies and teams running a book of client accounts.
We do not hold a SOC 2 report. We are too new to have one, and saying otherwise would be a lie you could check. The security page describes what we actually do with recordings, transcripts and credentials. Security.
Start with one week of calls.
Connect a source and we start transcribing and labelling every call — that part is built. The demand read and the unanswered-question list on top of it are in build, and a week of calls is what they will run on.
14-day trial. No card, no contract, cancel any time.