Skip to content
Assay
Request access
How it worksWhy AssayUse casesIntegrationsPricingSecurityLog in

Automatic QA for calls, chats and emails

Your QA team checks 2% of calls.Assay checks every one.

Write your QA scorecard in plain English. Assay scores every call, chat and email against it, shows the exact line behind each score, and sends anything it isn’t sure about to a person on your team.

Request accessSee how it works

Built for QA leads and compliance teams in contact centres.

  • Connects to your helpdesk
  • Never used to train AI models
  • EU hosting on request
  • Trial on 50 of your transcripts

1,284

Checked today

7

Need a person

96%

Agreed with reviewers

Customer callChecking…3 checks in 140 ms
  1. 14

    Agent

    Before I go into your account, can you confirm the first line of your address?

    Identity confirmed before account detailsRecorded automatically

  2. 15

    Customer

    Twelve Mill Lane. And this is the third time I’ve called about the same charge.

    Complaint raisedSent to your review queue

  3. 16

    Agent

    I can see that. I’ll refund it today, you have my word.

    Refunds approved by a supervisorFailed on this line

  • A2B Taxi Ashford
  • Cab4Ride
  • TS Consultancy
  • CSC International
  • Smartcore
  • Acorn Services
  • K1 SECURITY
  • Pro Arkitects
  • DropL Driving
  • NT Training Ltd
  • InvoiceTide
  • Penwell
  • ClearNetX
  • Wisconsin Mutual
  • Brethren Insurance

You write the scorecard. Assay does the listening.

Each check on your scorecard is one plain sentence, such as “The agent confirms who they’re speaking to before discussing the account.” Assay checks every conversation against it and shows the exact line behind each pass or fail.

Most conversations are never checked.

Most QA teams listen to around 2% of calls, a few per agent each month. That sample decides coaching, audit evidence and whether complaints get picked up.

Reviewers score the same call differently, and problems in the other calls only surface when a customer complains.

Reviewing by hand

2 of 100 conversations read. The other 98 are never looked at.

With Assay

100 of 100 checked. 2 failed a check, 5 went to a person, the rest were recorded.

Assay checks all of them, against your scorecard.

Connect your helpdesk, drop transcripts in a bucket, or paste them in. Every conversation is checked line by line, clear results are recorded with their evidence, and the uncertain ones go to your reviewers.

  1. Calls, chats and emails arrive

    Imported from your helpdesk or bucket, uploaded, or sent through the API.

  2. Checked against your scorecard

    Each check is answered yes, no or not sure.

  3. Clear results are recorded

    With the line in the transcript that decided them.

  4. Uncertain ones go to a person

    They land in your review queue.

Integrations

Works with the tools your team already uses.

Finished tickets and chats arrive on their own every 15 minutes, and anything that needs a person is posted to Slack.

See all integrations
  • Zendesk
  • Freshdesk
  • Intercom
  • Front
  • Gorgias
  • tl;dv
  • Amazon S3
  • Slack
  • Zendesk
  • Freshdesk
  • Intercom
  • Front
  • Gorgias
  • tl;dv
  • Amazon S3
  • Slack
  • Slack
  • Amazon S3
  • tl;dv
  • Gorgias
  • Front
  • Intercom
  • Freshdesk
  • Zendesk
  • Slack
  • Amazon S3
  • tl;dv
  • Gorgias
  • Front
  • Intercom
  • Freshdesk
  • Zendesk

One queue for the calls that need a person.

Open a conversation and the lines behind each result are already highlighted, with a sentence on why. Agree or disagree in a keystroke and move on. You can see how often Assay agrees with your team.

Review queue4 need you

Refund query, J. Patel

CustomerThe charge is still on my statement and nobody has called me back.

AgentI’ll refund it today, you have my word.

CustomerRight. I’ll hold you to that.

Refunds approved by a supervisor failed on line 16

DisagreeAgree

Accuracy by check

Agreement with your reviewers, last 30 days

  • Identity confirmed98%
  • Complaint recognised93%
  • Refund within policy96%
  • Call summarised at end88%

Why Assay is different

Most AI QA tools ask a chatbot to read the call and give a verdict. Assay asks one precise question for each check, finds the exact line that answers it, and knows when it isn’t sure. It never makes up a quote.

How Assay compares with reviewing by hand and typical AI QA tools
QuestionReviewing by handTypical AI QA tools Assay
How many conversations get checkedA few per agent each monthAll of themAll of them
What makes the decisionA reviewer’s judgementUsually a language model’s written answerAssay’s decision engine, with a measured confidence for every answer
The evidence you getNotes in a spreadsheetA quote the model writes, which can be wrongThe real line from the transcript
When it isn’t sureDepends who is scoringIt still gives an answerIt sends the conversation to a person
How accurate each check isUnknownRarely shownShown for every check, against your reviewers
More on how results are produced

Built for teams that answer for their conversations

Customer supportIdentity checks, complaint handling and refund promises.Read moreSalesPricing, cancellation terms and product claims.Read moreCollectionsRequired notices, affordability questions and tone.Read moreInsurance and lendingDisclosures, suitability questions and vulnerable customers.Read moreRecruitmentThe same screening questions for every candidate.Read moreAI agentsPolicy breaches and missed hand-offs in bot conversations.Read more

Try it on your own calls

Tell us about your team. We’ll reply within two working days to set up a trial with 50 of your transcripts and your current scorecard.

  • No card or contract for the trial
  • Your conversations are never used to train models
  • We go through the results with you