Skip to content
Adoptiv

Call Analysis

Six answers off one reading of the transcript, in a shape that is fixed in code rather than in a prompt. A workspace tunes what the model weighs; it never reaches the keys that come back.

One pass over the transcript

validating
Dana Whitlow · 4:12 · 812 words
Domain guidanceeditable

Chosen per vertical. Says what matters on this kind of call.

Workspace contextappended

Wrapped and treated as data, never as an instruction to the model.

Output contractfixed in code

The keys and their shapes. Nothing a prompt can reach.

  • summaryInvoice issued at the old rate; reissue and credit agreed, renewal call booked.in shape
  • sentimentnegativein shape
  • tonalityagent measured · customer frustrated · overall tensein shape
  • intentions3 intents · 2 commitments · callback_requestedin shape
  • scoresoverall 6 · communication 8 · resolution 5 · compliance 9in shape
  • spam_urgencyspam 0.02 · urgency normalin shape
Write boundary

Every requested dimension present and in shape. Written to the call in one transaction.

The guidance above the model is editable per workspace and per vertical. The shape below it is not, which is how the columns, the writeback and the coaching rollups can all read the same result without anybody co-ordinating a prompt change.
0
dimensions the output contract defines
0
repeat attempt before the run fails
0
output tokens the answer is capped at

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

The mechanism

How it works.

01

Six requests folded into one

Summary, sentiment, tonality, intentions, scores and the voicemail spam reading used to be six separate calls, each re-sending the same words. They are assembled into a single instruction now, so the six readings agree with one another instead of being reconciled afterwards.

02

Three layers above the model, two of them yours

Domain guidance for the vertical goes first, workspace context is appended inside a tag derived from the workspace identifier, and the output contract is concatenated last, out of code. Editing a prompt changes what is looked for. It cannot rename a key.

03

The words arrive wrapped in a tag nobody can guess

Speech to text output is influenced by whoever was on the phone, so each run mints a random delimiter after the audio already exists, redacts anything matching it, and strips the invisible characters used to hide instructions from a reviewer.

04

Checked dimension by dimension before storage

Each requested answer is parsed against its own rule: enums lowercased then matched, numbers coerced then range checked. A miss comes back with its reason, the reading repeats once, and a second miss fails the lot rather than saving half.

Where it sits

Two moments in every read.

Every read passes through the same seven. Call Analysis is the lit ones, 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
Dimensions
Summary, sentiment, tonality, intentions and scores. Spam and urgency on voicemail only
Request
A single text call per analysis, capped at 3500 output tokens by the orchestrator
Malformed answer
Rejected with a reason, repeated once, then failed. Nothing partial is saved
Out of range
Refused rather than trimmed. A score of 85 does not quietly become a 10
Needs words first
Any text dimension forces transcription; if that fails the run stops there
Where it lands
One row per source, unique on type and identifier, so a re-run replaces rather than adds
Starting one
Automatically when a recording finalises, or by hand at thirty runs an hour per person
Not the same as
This is the pass itself. The summary, the scores and the sentiment are its fields

More in Intelligence

11 capabilities

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

AI CRM Writeback

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.

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.

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.

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.

AI Field Generation

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.

Natural-Language Filtering

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.

Intelligence

See call analysis on your own floor.

Thirty minutes, your numbers and your data. We will set call analysis up live and you can decide from the thing itself rather than from this page.

14-day trial · no card · migration included