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.
No vocabulary is handed over to choose from
Nothing restricts the answer to an enumerated 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 afterwards.
More in Intelligence
12 capabilitiesAI that proposes edits to the record - an insight becomes a field once you accept it.
One reading of the transcript returns the summary, the sentiment, the tone, what each side intended and a set of scores, in a shape fixed in code.
The model proposes record updates with its confidence and the quote it heard them in, shown as a before-and-after you accept or reject row by row.
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.
Compliance scored nought to ten against what the vertical says matters, because no phrase list exists to recite. A missing reading is excluded, never passed.
What the customer was actually asking for and what the agent committed to, extracted as structured intents rather than left inside the transcript.
Callbacks and meetings pulled out with their times, a confidence figure and the words they came from, ready to accept in one click or reject in one.
Collections, healthcare, insurance, admissions and eleven more - each shaping what the analysis looks for without letting anyone break the output shape.
Threads summarised and read for intent and urgency, but only when a participant matches a record, so the model is never called on mail that is not yours.
Draft from an instruction or rework a message you have, landing in the composer with a suggested subject and going nowhere at all until you send it.
Describe what you track or paste a spreadsheet's columns, and get a named field group back with types, options and placeholders to approve one at a time.
A sentence becomes a grid filter and a sort order with the reading explained back, on the toolbar of every grid that carries a column menu of its own.
OpenAI, Azure, Anthropic, Gemini, Bedrock and ten more, bound per purpose with an ordered fallback chain, a circuit breaker and a cost line on every attempt.
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