Call Scoring & QA
Five numbers between nought and ten, judged on a call that has been analysed. The overall is judged in its own right rather than averaged out of the other four, so a gap between them is a reason to listen.
Quality scoring on a finished call
every analysed call, not a sampleJudged above its parts.
Renewal closed on the call with the discount terms stated plainly and repeated back.
Product figures from the platform’s own defaults - not customer averages
How it works.
Four parts, then a verdict of its own
Agent communication, issue resolution, customer satisfaction and compliance are each rated, and the overall is rated separately in the same reading. Nothing derives one from the others, which is precisely what makes their disagreement informative.
Only the overall is compulsory
A secondary number that comes back missing does not sink the run, since the dashboards key on the overall. Anything present still has to be clean: coerced from text if need be, checked against the range, then rounded to a whole number.
Out of range is refused, never corrected
Trimming an eighty five down to a ten would manufacture a pass nobody earned, so the write boundary turns it away, the reading runs again, and a second failure shows on the call instead of being filed quietly.
Not every leg belongs in a coaching figure
The overnight aggregate keeps answered inbound and outbound conversations off the call record and nothing else. Internal legs and bot calls are dropped, voicemail is dropped with them, the agent name is snapshotted so a reused login cannot rewrite old rows, and a seven day movement is computed beside the average. Both are served to the coaching view from one endpoint, so the figure and its direction are read together.
Two moments in every read.
Every read passes through the same seven. Call Scoring & QA 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- Scale
- Whole numbers from 0 to 10. Text is coerced, then range checked, then rounded
- Dimensions
- Communication, resolution, satisfaction, compliance, and a separately judged overall
- Required
- The overall. The other four are checked when present and tolerated when absent
- Justification
- One sentence covering the whole block, not one line per number
- Filtering
- The call list offers four floors: nine, seven, five and three out of ten
- Left out of coaching
- Internal legs, bot calls, voicemail, and anything that never reached answered, so a coaching average is built from conversations only
- Averaging
- A day's figure is a plain mean of the calls that returned that number
- Not the same as
- This rates the handling. Compliance is one of these five, argued on its own page
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.
Chosen words rather than a fixed list for how the agent sounded, how the customer did, and the conversation overall - the manner behind the sentiment.
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 call scoring & qa on your own floor.
Thirty minutes, your numbers and your data. We will set call scoring & qa up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included