Industry Presets
Fifteen verticals, each a paragraph telling the model what matters on that kind of call. Choosing one swaps the guidance above the contract and does not move a character of the keys beneath it.
Analysis tuned to the floor it runs on
preset 4 of 15Required disclosures, right-party verification, no threats, and any dispute or cease-contact request captured as it was made.
Product figures from the platform’s own defaults - not customer averages
How it works.
A preset is guidance and carries no schema
Each holds one paragraph spanning every dimension: what a summary ought to name, which dispositions are likely, what the numbers should be strict about. None of them contains any JSON, deliberately.
Five steps settle which one runs
An explicitly chosen preset, then the campaign this call belonged to, then the workspace default, then the older single setting, then the platform base. Whichever resolves first wins and the rest are never consulted.
A workspace can own one without ever seeing the base
Its preset is either entirely its own paragraph or built on a platform one, and in that second case the platform wording resolves on the server and is never sent to a browser. Either way its own context is appended afterwards.
Every edit keeps the wording it replaced
Each analysis is stamped with whichever version was live when it ran, so a rewording stays comparable against the calls that went through the one before. The versioning covers a workspace's own preset. The fifteen seeded ones refuse an edit outright, and resetting one to its seed rewrites the wording with no snapshot behind it.
Two moments in every read.
Every read passes through the same seven. Industry Presets 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- Catalogue
- Fifteen seeded verticals. A platform administrator can add more or deactivate one
- A preset changes
- Domain guidance only. The six output keys and their shapes are fixed in code
- A workspace preset adds
- Its own trigger mode, strong language masking, length floor and call opt-in
- Resolution
- Chosen preset, campaign, workspace default, older single setting, platform base
- Workspace text
- Appended inside a tag and labelled as data, so it cannot rewrite the rules above
- Propagation
- Cached for sixty seconds, with an invalidation message so an edit lands sooner
- Versions
- Append only. Each analysis stamps the version that produced it, or stamps nothing
- Not the same as
- This tunes what is looked for. Which calls enter at all is the gate settings
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.
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.
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 industry presets on your own floor.
Thirty minutes, your numbers and your data. We will set industry presets up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included