Intent Detection
What the customer asked for and what the agent promised, returned as two separate lists because they are two different obligations and only one of them is yours to keep.
What each side meant
reading the transcript- Invoice reissued at the agreed rateprimary
- Credit rather than a carry-over
- Renewal conversation
- Reissue the invoice today
- Raise a credit note
- Book Thursday and send the terms
Product figures from the platform’s own defaults - not customer averages
How it works.
Two lists, and they are never merged
Customer intents on one side, agent commitments on the other, both as short labels rather than paragraphs. A single dominant intent is named separately and stored beside them, so a call can also be counted by the one thing it was mostly about.
A disposition is proposed from a closed set
Eleven codes: interested, not interested, callback requested, appointment set, voicemail left, wrong number, do not call, no answer, follow up needed, completed, other. A readable phrase comes with it and that phrase is not constrained at all.
The proposal stays a hint and does not click
It appears only while no disposition has been set, and setting one hides it. Your own catalog is what a rep picks from, because those eleven codes are the model's vocabulary rather than your reporting categories.
Leave this out and the review queue is empty
The proposed record edits and the proposed follow-ups ride inside this one answer rather than beside it, so a run that skips it leaves your reviewers with nothing to review. A sentence of notes sits underneath the lists.
One moment in every read.
Every read passes through the same seven. Intent Detection is the lit one, and everything either side of it is a different page in this category.
- 01Source
the call or the thread it reads
- 02Transcribe
audio into words, with speakers
- 03Read
the pass over the whole of it
- 04Judge
the score, the sentiment, the intent
- 05Extract
the fields and follow-ups pulled out
- 06Write
what lands back on the record
- 07Review
a person checking the machine
The specifics.
7 facts- Returns
- A list of customer intents, a list of agent commitments, and one dominant intent
- Disposition
- One of eleven categories plus a free phrase. Neither is written onto the call
- Applying it
- By hand. Nothing maps those eleven codes onto the codes your floor uses
- Shown
- Only while the call carries no disposition. Choosing one removes the hint
- Also carries
- The proposed column edits and the proposed follow-ups. They are fields of this block
- Shape
- Free JSON on the analysis row. Its presence is checked, its interior is not
- Not the same as
- Labels and a code. The summary answers the same call in readable prose
What it reads, and what reads it.
Nothing here invents its input. These are where the material comes from, and where the verdict goes afterward.
More in Intelligence
12 capabilitiesAI that proposes edits to the record - an insight becomes a field once you accept it.
One to six sentences on the record covering why the call happened and what was agreed, so nobody reading the list has to open the audio to find out.
Finding yesterday's bad calls is a filter, not an afternoon. Positive, neutral or negative on every analyzed call, kept in a field of its own you can sort on.
How the agent sounded, how the customer sounded, one word for the pair. Chosen words rather than a fixed list, so a call can close politely and grudgingly.
A month of calls gets reviewed by whoever had time. Every call carries five numbers instead, and the overall is judged in its own right rather than averaged.
Nobody re-listens to check the disclosure went out. Every call is scored against what compliance means on your floor, with a missing one excluded, not passed.
A coaching note never quotes the customer back at a rep who did not say it. Four of six engines return the channel each side was on, one control swaps them.
A collections call and an admissions call are not judged the same way. Fifteen verticals ship knowing the difference. What comes back still reads the same.
A thread is read only when somebody on it is one of your leads. No match and nothing is sent anywhere, so mail that is not about a customer is left alone.
A draft or a rewrite that lands in the composer and stops there. The subject is a suggestion, every word editable, and nothing leaves until a person sends it.
The field group you would otherwise build one field at a time. Describe what you track or paste a spreadsheet's columns, then approve or refuse each field.
Type the list you want and it builds the filter and the sort. Then it says in one sentence what it understood: a filter nobody typed has to say what it did.
OpenAI, Azure, Anthropic, Gemini, Bedrock and ten more. When one starts timing out mid-afternoon the work moves down the chain rather than stopping on you.
The rest of the platform.
Five more categories, all on the same record and the same bill. Each card names three of its capabilities, so you can tell from here whether it is worth opening.
Intelligence
See intent detection on your own floor.
Thirty minutes, your numbers and your data. We will set intent detection up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included