Compliance Scoring
One of the five numbers from the reading, weighed against what the vertical says matters rather than against a list of required phrases. That is both the argument for it and the honest limit on it.
Compliance on an analysed call
scored at analysis, not at audit- Required disclosures given
- Right party verified before any detail
- No threats and no harassment
- Disputes and cease-contact requests honoured
- No financial identifiers written back to the record
The required disclosure was not given before the balance was discussed, and the call continued after the customer said the amount was disputed.
Product figures from the platform’s own defaults - not customer averages
How it works.
There is no phrase list underneath any of it
Nothing checks that a particular sentence was uttered. The preset describes what compliance means on this kind of call, so the same figure carries a different meaning on a collections floor and an admissions line.
The presets name their deductions out loud
Collections asks for a strict reading of disclosures, right party verification and any cease contact request. Financial services adds suitability and marks pressure down. Healthcare keeps clinical detail out of the record fields and asks for clinically urgent wording to be raised.
Under six counts as a failure, and that lives in the rollup
The threshold sits in the overnight aggregate rather than in any prompt, so the figure and the verdict stay separable. Anything beneath it increments a failure count for that person on that day while the number itself is kept intact.
A missing figure is never counted as a passing one
Failures divide by a separate count of calls that actually returned a compliance number. An earlier build divided by every call, which turned an absent reading into a silent pass and flattered everybody.
Two moments in every read.
Every read passes through the same seven. Compliance Scoring 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.
7 facts- What it is
- One number from 0 to 10 out of the same reading, sitting beside the other four
- Weighed against
- The preset guidance for the vertical. No required phrase list exists anywhere
- Failure mark
- Beneath six, held in the overnight aggregate rather than in any prompt, so the figure and the verdict stay separable
- Denominator
- Only calls carrying a compliance number. Absent ones are excluded, not passed
- Reasoning
- The one sentence covers all five numbers. There is no compliance only note
- Treat it as
- A reading to be reviewed. It is not an audit result and claims no standard
- Not the same as
- This is one of the five numbers a call is given. The telephony side's own screening, against do-not-call and litigator lists, is a different thing under a similar name
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.
Positive, neutral or negative on every analysed call, stored in a column of its own so the ones that went wrong are a filter rather than a listening exercise.
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.
Four of six speech paths return the channel each side was recorded on, so the transcript knows who spoke rather than guessing, and one control swaps a pair.
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 compliance scoring on your own floor.
Thirty minutes, your numbers and your data. We will set compliance scoring up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included