Tonality Analysis
How the agent sounded, how the customer sounded, and one word for the pair of them together. Chosen words rather than a fixed list, which is what lets them describe a call that closed politely and grudgingly.
How the call sounded
per analysed callThe customer agreed to the renewal inside a minute and mentioned twice that they were between meetings.
Product figures from the platform’s own defaults - not customer averages
How it works.
Four pieces come back and one is kept
The request asks for the agent's dominant manner, the customer's, a single word for the conversation, and a sentence of evidence. Only the conversation word is validated, and only it is written down, into a fifty character column. The other three are read and dropped.
Nobody wrote the list of words in advance
Nothing holds the answer to a fixed set, so a call can come back clipped, resigned or apologetic without anyone having predicted those in advance. The cost is that these words read rather than compute.
The evidence sentence has to point at something
The instruction asks for a concrete moment rather than a restatement of the label, and nothing enforces it: the sentence is neither validated nor stored. Presets sharpen what to watch for by vertical: frustration and de-escalation on a support line, stress and empathy where a claim is being made.
Tallied, because it cannot be averaged
The overnight rollup counts how often each word appears for an agent and stores the whole spread as counts. Since no list exists in advance, a word nobody expected simply turns up in the tally rather than being swept into an other bucket that explains nothing.
One moment in every read.
Every read passes through the same seven. Tonality Analysis 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- Asked for
- Agent manner, customer manner, one word for the conversation, one sentence of evidence
- Kept
- That single conversation word, in a fifty character column on the analysis
- Vocabulary
- Open. No enumeration, no fixed list, and no number attached to any of it
- Rollup
- Counted per agent per day as a spread, because averaging a word would mean nothing. Written nightly and read as counts
- Per speaker on the record
- Not persisted. The pair is produced by the model and written to no column
- Not the same as
- Sentiment is one enum about the outcome. This is the manner of both parties
- On mail
- Not asked for. Manner of speech is a call idea and the mail path leaves it out
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.
A supervisor who used to open the audio reads it instead: what the call was about, how it went, what was asked for, what it scored. One reading, one answer.
Nothing on an existing lead moves by itself. What the call gave up arrives as proposed edits, each with the value it would replace and the words it came from.
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.
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.
What the customer asked for and what your agent promised, kept as two lists, because they are two different obligations and only one of them is yours to keep.
A promise made out loud is worth nothing until it sits on a day. Callbacks and meetings come off the call with the time said, real the moment you accept.
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 tonality analysis on your own floor.
Thirty minutes, your numbers and your data. We will set tonality analysis up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included