Skip to content
Adoptiv

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

parsed
What you asked for

hot leads in California, newest first

Where
ratingishot
stateisCA
Order
created, newest first
And what it says it read

Two conditions, both of which must hold, and no date range because you named none.

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. The sentence back is how you tell a filter that answered your question from one that answered a nearby question convincingly.
0
families of condition it can return
0
grids carrying the input
0
sentence of explanation with every answer

Product figures from the platform’s own defaults - not customer averages

The mechanism

How it works.

01

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.

02

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.

03

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.

04

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.

Where it sits

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.

  1. 01
    Source

    the call or the thread it reads

  2. 02
    Transcribe

    audio into words, with speakers

  3. 03
    Read

    the pass over the whole of it

  4. 04
    Judge

    the score, the sentiment, the intent

  5. 05
    Extract

    the fields and follow-ups pulled out

  6. 06
    Write

    what lands back on the record

  7. 07
    Review

    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

More in Intelligence

13 capabilities

AI that proposes edits to the record - an insight becomes a field once you accept it.

Call Analysis

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.

Call Summaries

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.

Sentiment Analysis

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.

Tonality Analysis

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.

Call Scoring & QA

Communication, resolution, satisfaction and compliance scored nought to ten beside a separately judged overall, on every call that clears the analysis gates.

Compliance Scoring

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.

Intent Detection

What the customer was actually asking for and what the agent committed to, extracted as structured intents rather than left inside the transcript.

Follow-Up Extraction

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.

Diarized Transcripts

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.

Industry Presets

Collections, healthcare, insurance, admissions and eleven more - each shaping what the analysis looks for without letting anyone break the output shape.

AI Email Analysis

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.

AI Email Writing

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.

Bring Your Own Model

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.

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