AI Field Generation
Describe what you track, or paste the columns off a spreadsheet, and get back a named group of fields with types, options and placeholders already chosen, each one approved or refused on its own.
Generating a field group
proposalFields for a motor claim: policy, incident, vehicle, and who is handling it.
Product figures from the platform’s own defaults - not customer averages
How it works.
Eleven types to choose between
Text, number, email, phone, web address, date, yes or no, one from a list, several from a list, currency and file. The instruction pushes the right one for the shape and asks for the options to be written out where a list is involved.
Reserved names are handed over before it starts
The columns a record kind already owns are computed and given to the model as names it may not take, leads included. A proposal therefore comes back clear of the built-in columns, and the collision check on the way back has almost nothing left to catch.
A spreadsheet is read before the model sees it
Headers and a sample of values are parsed, types are inferred from the sample, and a compact description of the columns goes into the request. The raw file is not what travels.
Approval is per field, and the conversation carries on
Each proposed field starts pending and is confirmed or denied individually. Asking for a change preserves what you already confirmed and only resets the parts being reworked, then the group and its fields are created the ordinary way.
One moment in every read.
Every read passes through the same seven. AI Field Generation 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.
8 facts- Field types
- Eleven, including a file field the by-hand form does not offer today
- Record kinds
- Four, on tabs of their own. Whichever one you are standing on decides which reserved names travel out with the request
- Inputs
- A description, the conversation so far, and pasted spreadsheet rows
- Photographing a form
- A photograph goes through the same reading a spreadsheet does, so what reaches the model is a description of the columns rather than the image
- Required flags
- Everything comes back optional unless you explicitly asked for one to be required
- Starting points
- Six built in templates, narrowed by the workspace industry where one is set
- Permission
- Manage settings on the workspace, because it creates real columns
- Not the same as
- This designs the columns. Filling them from a conversation is the writeback 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
13 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.
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.
Communication, resolution, satisfaction and compliance scored nought to ten beside a separately judged overall, on every call that clears the analysis gates.
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.
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.
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.
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 ai field generation on your own floor.
Thirty minutes, your numbers and your data. We will set ai field generation up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included