Natural-Language Filtering
A sentence about what you are looking for, turned into a grid filter and a sort order with a line back explaining the reading. That last part matters, because a filter you did not write yourself is only worth trusting when it says what it did.
Reading the sentence
parsedhot leads in California, newest first
Two conditions, both of which must hold, and no date range because you named none.
Product figures from the platform’s own defaults - not customer averages
How it works.
The columns travel with the question
The request carries the grid's own column definitions, so the answer names fields that exist rather than fields it imagined. A grid asking on behalf of leads and one asking on behalf of deals therefore get different answers out of the same sentence.
Four families of condition come back
Text with contains, equals, starts with and their negatives. Numbers with the comparisons and a range. Sets with a list of values. Dates with a from and a to. A sort order arrives beside it as a column and a direction.
An explanation travels with the answer
It states what was understood, in one sentence, and that sentence is shown with the result. Reading it is how you tell a filter that answered your question from one that answered a nearby question convincingly.
Both halves are applied on the same pass
The filter model and the sort model are handed to the grid together, so the rows narrow and reorder in one paint rather than settling twice. Once they land they are ordinary grid state, which is why the ordinary clear control takes them off again.
One moment in every read.
Every read passes through the same seven. Natural-Language Filtering 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- Endpoint
- Takes a sentence, a record kind, and the column definitions of the grid that asked
- Returns
- A filter model, a sort model, and one sentence explaining the reading
- Condition families
- Text, number, set and date, each with the operators that kind allows
- Mounted
- On the toolbar of all nineteen grids that carry one
- What it applies
- Both halves. The conditions narrow the rows and the sort reorders them together
- Clearing it
- The grid's own clear control, because what arrived is ordinary filter state
- Shown back
- The explanation sits with the result, so a filter nobody typed still accounts for itself
- Not the same as
- This writes the filter from a sentence. Keeping one you built by hand is Saved Views
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.
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.
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.
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 natural-language filtering on your own floor.
Thirty minutes, your numbers and your data. We will set natural-language filtering up live and you can decide from the thing itself rather than from this page.
14-day trial · no card · migration included