Trusst AI Resource Centre
  • πŸ‘‹Welcome to the Trusst AI Resource Center.
  • Overview
    • 🌏Why We're Here & What We Do
    • πŸ’‘Problem Statement
    • πŸ”‘Use Cases
    • ✨Capabilities
      • πŸ‘‚Lissten (transcribe & translate)
      • 🀝Trussted Agent (conversational AI)
      • 🌊AI Workflows (alerts, triggers, workflows)
      • πŸ‘€InteractIQ (AI powered Insights)
      • πŸ’¬DataDialog (conversational interface)
      • πŸ—ΊοΈTrusst Based Routing (AI powered Decision Engine)
    • πŸ’³Trusst AI Subscription Fees
  • Product Guides
    • πŸ› οΈDeployment Guide (Trusst AI on AWS)
    • πŸ“–User Guide
    • πŸ”‘Integrating Your Identity Provider
    • πŸ‘₯User Roles & Permissions
    • ♻️Suggested Iteration Cycle
    • ☁️Trusst AI Architecture
    • Network Considerations
    • πŸ”Data Security
    • πŸš΄β€β™‚οΈData Lifecycle Management
    • 🫢Advocating for Responsible AI
    • πŸ”§Testing, Troubleshooting & Health Check
    • Shared Responsibility Model
    • πŸ’Support
    • πŸ“ˆAI Model Training & Testing
    • ❓Frequently Asked Questions
Powered by GitBook
On this page
  1. Product Guides

User Guide

This page gives Trusst AI users an overview of how to use Trusst AI

PreviousDeployment Guide (Trusst AI on AWS)NextIntegrating Your Identity Provider

Last updated 18 days ago

Once Trusst AI has been deployed into your account, the first step to take is to add users to enable them to log into Trusst AI.

Setting up Single-Sign-On (optional)

If single sign on is required/preferred, please create a support ticket via the and ensure to provide details regarding your Identity Provider (e.g. Okta/Auth0/Frontegg/Active Directory etc). One of our team will be in touch to provide support with and TrusstGPT.

User Creation (excl. SSO)

Note: TrusstGPT User management and role based access control, coming soon (ETA: 2025 Q1) To enable a user in TrusstGPT, you will need to configure a user directly within an Amazon Cognito User Pool. To do this, you will need to have the appropriate IAM permissions, e.g. AWS technical team.

  1. From AWS Management Console, search and click "Cognito":

  1. Select the user pool:

  2. Select create user and enter details as below and click "Create User". Make sure to select "Send an email invitation" and "Mark email address as verified".

  3. The new user will receive an email from "no-reply@verificationemail.com" with their login details

User Sign-in
  1. Once created, new users will receive an email from "no-reply@verificationemail.com" with their login details. This includes "Username" and a "Temporary Password", along with the link to access your organisations instance of TrusstGPT. To sign in, click the link in the email.

  2. Sign in with the login details from the email in step 1:

  3. Enter a new password, family and given name(s) and click "Confirm":

  4. Install an authenticator app on your mobile device, e.g. Google Authenticator.

  5. From your authentication app on your mobile device, click add (+) and select "Scan a QR code" option or equivalent.

  6. Scan the QR code presented by TrusstGPT which will add a new "code" to your authenticator app:

  7. Enter the generated code from your Authenticator app into the "Code" section of TrusstGPT above and click continue.

  8. Congratulations, you're officially logged into TrusstGPT!

Before you dive in, we suggest having a quick read ofour to familiarise yourself with some of the lessons we've learnt along the way whilst helping other customers maximise the value they achieve with Trusst AI.

Importing contacts

When logging in for the first time, there will be no contacts in the platform.

  1. Before you create an import job, make sure you have the "S3 URI" to the location where the interaction data that you want to import has been stored. e.g. "s3://your-bucket-name/path/to/folder/"

  2. Once you have this, click "Contacts" in the lefthand side navigation bar, and then "New Import":

  3. Paste the "S3 URI" from step 1 into the first field. If you have already made updates to the prompts, select the "Prompt Revision" you created, otherwise leave it blank and it will use the Default Prompts. In the "Job Name" field, you can give the Import Job a relevant name, otherwise you can use the name generated using the name of the S3 bucket. Then click "Create": Note: The s3 location that you specify needs to be accessible by TrusstGPT If you have already created a new Prompt Revision, you can also select this from the drop down. The Default Prompt is used if none have been created or specified.

  4. TrusstGPT will begin ingesting and processing the interactions from the provided S3 location. You can monitor the progress of the Import Job in the status bar: You can also view the status of the individual contacts in the table: Note: The time it takes to complete will depend on the format of the files imported, audio files take more time than transcriptions, as TrusstGPT needs to transcribe the audio prior to analysis.

Filtering contacts
  1. You can filter the list of interactions by any of the columns in the data table, either by using the category bar, or by selecting the filter icon in the column you want to filter by and then selecting the item you want to filter by in the drop down: Note: You can combine multiple filters to drill further into the data, e.g:

  2. Once the data is filtered, you can also select "View Analytics" This will maintain the same filters for an aggregated analysis view in Insights where you can then view the breakdown of the Evaluation Scores, and other insights relevant to the contacts that apply to your filter: You can also click "Go to Import" to return to the "Contacts" view.

Prompt Playground

From within any contact, you can use the Prompt Playground which is available at the bottom of the contact page. Use the Prompt Playground to test prompt adjustments or add questions to a prompt. This enables you to extract answers relevant to the questions you want answered (click the "^" to pull up the Prompt Playground tray):

Understanding the Prompt Types:

Note: If TrusstGPT is unable to provide an answer to the question relative to a contact, the question will be excluded from the results. Chat: This provides generally a more verbose response to your question, and is akin to what a human would respond if you were "chatting" to them about the interaction. Binary: This will respond with a True/False response. e.g. "Did the agent greet the customer by their first and last name?"

Rating: This should be used when you are requesting TrusstGPT to provide a rating between x and y. e.g. "On a scale of 1 to 10, rate the level of customer effort experienced during the conversation".

Single Label: This should be used when you are looking to label the conversation, e.g. "What was the root cause for the customer calling?"

Synthesis: This should be used if you are looking to provide a synthesis e.g. "Summarise what the agent could have done to improve the customer's experience."

Viewing categorisation of interactions (Insights)
  1. The vertical stacked bar graph displays the top 20 categories, which organises conversation topics by volume.

Adapting Insights in Prompt Revisions

Jump on over to "Prompts" from the navigation bar. This is where you will be able to create, read, update, and delete the sets of questions/criteria used (Prompt Revisions) to ask TrusstGPT to provide the insights you're looking to get.

Note: initially there won't be any prompts until you create one. You can either click "Create Prompt" or "View Default Prompt" to edit the default prompt.

To get started with adapting TrusstGPT's responses to answer your specific questions, you can either:

  1. If you already have Prompt Revision created, you can click on one of the prompt revisions from the list. You will be able to then click "Edit", where you can modify and expand on the list of questions, same as above.

    By clicking "Publish" you will make this Prompt Revision "Live" which means that it will be used for all future interactions processed by TrusstGPT (for continuous ingestion) for manual Imports, you will still be able to select a specific prompt revision.

Retry/Regenerate/Re-Import

To accelerate the iteration cycle, we have added the ability to re-perform actions on interactions at an Import Job or Contact level.

  • "Retry Import" action will re-import all contacts within the contact import Job

  • "ReImport Failed" action will only re-import contacts with a "Failed" status within the contact import Job

  • "Regenerate Insight" action will request for regenerating the inference/insight on all calls for a contact import Job

  • "Retry Failed Insights" action allows you to request for inference/insight on calls with failed inference

  • "Regenerate Transcription" action will request for regenerating the transcription on all audio calls for a contact import Job

  • "ReTranscribe Failed" action allows you request for transcription only for audio calls with failed transcription

  • "ReImport Contact" action will re-import the selected contact.

  • "Regenerate Insight" will regenerate insights for selected contact.

  • "Regenerate Transcription" will re-generate the transcription for selected contact. Enabled only on Audio calls (e.g. .MP3/.WAV/.OGG)

Within the prompt playground, questions should be phrased as if you were asking a question to someone who has read the transcript of the conversation, but has perfect memory recall.

Depending on the type of question and the type of response you're looking for, you can also adjust the "Prompt Type" by selecting the appropriate type from the drop down list:

Browse to the "Insights" page from the navigation bar on the left of screen, and select the you created from the drop down:

The vertical bar graph provides a heat map of categories about what your customers interact with you about: Note: To maintain clarity and focus, only the most prevalent categories are shown.

"Prompt Revision Scores" provides an aggregate of the results from the criteria specified in "Prompts" section of TrusstGPT. The percentage displayed, is the % of the aggregate of all contacts for that Import Job. Note: each Prompt Group, i.e. Soft Skills, Compliance etc. is also aggregated. For Conditional prompts created in "Prompts" the parent (condition) displays the percentage of contacts where the condition was met (answer to the question is True), and the child displays the % of contacts where the condition was met and achieved the positive result (True if "positive" is toggled on, or "False" if positive is toggled off in the prompt revision in "Prompts")

Click "Create Prompt", this allows you to modify and expand on the default list of questions.

When creating or editing a Prompt Revision, you can add or delete questions using the "Add Question" or "Delete" button shown below:

You will note that the prompt is broken out into sections, e.g. "Synopsis", "Soft Skills", "Compliance". Synopsis: contains questions that will adapt the outputs produced by TrusstGPT by adding, deleting or modifying questions. Soft Skills/Compliance: Treat these questions as if you're asking TrusstGPT a question about what happened during an interaction. TrusstGPT currently responds with either "True", or "False". If the "Positive" toggle is turned on, a "True" response to the question will result in the agent achieving the weight set for that question. Conversely, if the "Positive" toggle is turned off, a "False" response to the question will result in the agent achieving the weight set for that question, otherwise a score of 0 is achieved. Conditional Question Assessment: If you want to ask conditional questions, you can toggle "CQA" on. This will create a follow up question, e.g: Note: The second question will only be evaluated if the result of the condition (parent) is "True", otherwise it will be marked as "N/A" and will not impact the score of the contact. When the condition is "True", only the score/weight of the second question (child) is calculated for that interactions score. "Weight" is flexible, such that you can use whichever scale of weighting you prefer. Regardless of what scale you chose (1-10, or 1-50, or 1-100), the score is calculated based on Achieved Score/Total Weight possible, expressed as percentage (%). For critical criteria or questions, you can toggle "Auto fail" on. This will result in the interaction receiving a score of 0, whilst flagging the particular question which resulted in the failure. By clicking "Publish" you will make this Prompt Revision "Live" which means that it will be used for all future interactions processed by TrusstGPT.

If you want to regenerate insights of interactions already processed by TrusstGPT, you can do this by clicking "Regenerate Insights" from the Contact Import page. Note: Automated Quality Evaluations will always use the Published Prompt Revision. TrusstGPT will then reprocess the interactions using the revised prompt you created. You can monitor the process in the same way you would a standard .

To re-perform an action at an Import Job level, you can select the drop down in the top right corner of an Import Job:

To re-perform an action at an individual contact level, from within a contact, select the action you want to perform from the drop down:

πŸ“–
Import Job
Trusst Customer Support Portal
integration of your IDP
Suggested Iteration Cycle
Import Job