Our most capable AI model is now on the Scale plan. See plans

The same screening questions, every time

Screening only works if everyone is asked the same questions in the same way. Your agent runs your pre-screening consistently, saves every answer in the same format, and passes anything that needs judgement to your team.

What your agent does

Asks every question, in order

Your screening questions are asked the same way for everyone, so nothing is skipped or reworded.

Keeps consistent records

Answers are saved to your data list in the same format every time, ready to review or export.

Leaves judgement to people

Anything outside your rules goes to your team, and team roles control who can see the records.

Example conversation

Built with

LAUNCH CHECK

Tested before it talks to a customer

Accuracy

Real customer questions

The check writes realistic questions from your own information, asks your agent each one and grades the answers, so you see exactly which ones it got wrong.

Security

Attacks, before anyone else tries

It tries to trick your agent into revealing its instructions, handing over other customers' details or obeying someone pretending to be you. Nothing it asks for is actually done.

Setup

Settings that would cause problems

It reviews how your agent is set up and flags settings that could lead to wrong answers or expose data, with how to fix each one.

In a few minutes you get a score for accuracy and attacks blocked, with a fix for each problem. Run it again after every change to make sure nothing broke.

FAQ

Compliance & Screening: common questions

Team roles control who can read conversations and records, and every settings change is in the audit log.

You choose how long conversations are kept, can handle customers' data requests from your settings, and can sign a data processing agreement there too.