Call Analysis
A supervisor who used to open the audio now reads the call instead: what it was about, how it went, how both sides sounded, what was asked for, what it scored. One reading, so the six answers never disagree.
One pass over the transcript
validatingChosen per vertical. Says what matters on this kind of call.
Wrapped and treated as data, never as an instruction to the model.
The keys and their shapes. Nothing a prompt can reach.
- summaryInvoice issued at the old rate; reissue and credit agreed, renewal call booked.in shape
- sentimentnegativein shape
- tonalityagent measured · customer frustrated · overall tensein shape
- intentions3 intents · 2 commitments · callback_requestedin shape
- scoresoverall 6 · communication 8 · resolution 5 · compliance 9in shape
- spam_urgencyspam 0.02 · urgency normalin shape
Every requested dimension present and in shape. Written to the call in one transaction.
Product figures from the platform’s own defaults - not customer averages
How it works.
Six readings folded into one
Summary, sentiment, tonality, intentions, scores and the voicemail spam reading used to be six separate calls, each re-sending the same words. They are one instruction now, so the six answers agree with one another instead of being reconciled by whoever reads them.
Your vertical, then your floor, then the part nobody can move
Guidance for the vertical goes first. Your own context is added underneath it, inside a tag tied to your workspace so it reads as background rather than as orders. The fixed part is added last, out of code. You can change what a reading looks for on your calls. You cannot change what comes back, which is why every call reads the same way as the one before it.
A caller cannot talk their way into the analysis
Whatever somebody says out loud ends up in the words we hand the model, so each run picks a random marker after the audio already exists, blanks anything in the transcript that matches it, and strips the invisible characters somebody would use to hide an instruction from a reviewer.
Half an answer is not filed as an answer
Every answer is checked against its own rule: words matched against the permitted set, numbers checked against their range. A miss comes back with its reason, the reading repeats once, and a second miss fails the lot rather than leaving you half a call.
Two moments in every read.
Every read passes through the same seven. Call Analysis is the lit ones, 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.
8 facts- Dimensions
- Summary, sentiment, tonality, intentions and scores. Spam and urgency on voicemail only
- Request
- A single text call per analysis, capped at 3500 output tokens by the orchestrator
- Malformed answer
- Rejected with a reason, repeated once, then failed. Nothing partial is saved
- Out of range
- Refused rather than trimmed. A score of 85 does not quietly become a 10
- Needs words first
- Any text dimension forces transcription; if that fails the run stops there
- Where it lands
- One row per source, unique on type and identifier, so a re-run replaces rather than adds
- Starting one
- Automatically when a recording finalizes, or by hand at thirty runs an hour per person
- Not the same as
- This is the pass itself. The summary, the scores and the sentiment are its fields
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
11 capabilitiesAI that proposes edits to the record - an insight becomes a field once you accept it.
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.
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.
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 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 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.
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 call analysis on your own floor.
Thirty minutes, your numbers and your data. We will set call analysis up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included