Genesys Cloud - Main

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

Hello Phaneedra, 

I love this. I would be interested to hear what the rest of the community says also. 

Cheers, 

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

#AICopilot(Agent,SupervisorAdmin)

------------------------------
Phaneendra
Technical Solutions Consultant
------------------------------

Hi Phannendra - Fantastic customization indeed and using Triggers for automation. Congratulations! Great win!

------------------------------
Guru Prasadh Jeevan Rao
Principal Technical Account Manager

Original Message:
Sent: 03-25-2026 07:02
From: Phaneendra Avatapalli
Subject: Win - Using AI sentiment + trend to proactively detect poor customer experiences in Genesys Cloud

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

#AICopilot(Agent,SupervisorAdmin)

------------------------------
Phaneendra
Technical Solutions Consultant
------------------------------

Thank you Guru

Hi Phannendra - Fantastic customization indeed and using Triggers for automation. Congratulations! Great win!

------------------------------
Guru Prasadh Jeevan Rao
Principal Technical Account Manager

Original Message:
Sent: 03-25-2026 07:02
From: Phaneendra Avatapalli
Subject: Win - Using AI sentiment + trend to proactively detect poor customer experiences in Genesys Cloud

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

#AICopilot(Agent,SupervisorAdmin)

------------------------------
Phaneendra
Technical Solutions Consultant
------------------------------

Hey Phaneendra,

Very cool use of triggers. 

I was playing around a few months back when the Sentiment/Topics triggers were released. My test scenario was to alert Team Leaders over MS Teams when there was a specific Topic flagged, so we could investigate and follow up on the call. 

Basically the Workflow was a data action that took a lot of attributes from the call and sent them via a webhook to Teams.  For the test, I created a Teams Channel and in Power Automate created a webhook flow that sent those details to the Teams channel.  At the time I wasn't able to find a solution for a it to work in real time, only post call.  It would be really useful for businesses who might have clients welfare at risk.  Might have to look back into again to see if anything new could make that possible.  

Once you start diving into some scenarios, triggers really unlock what's possible with Genesys.  

Thank you Guru

Hi Phannendra - Fantastic customization indeed and using Triggers for automation. Congratulations! Great win!

------------------------------
Guru Prasadh Jeevan Rao
Principal Technical Account Manager

Original Message:
Sent: 03-25-2026 07:02
From: Phaneendra Avatapalli
Subject: Win - Using AI sentiment + trend to proactively detect poor customer experiences in Genesys Cloud

Hi everyone,

We recently introduced a new approach to proactively identify interactions where customers had a poor experience using Genesys Cloud AI insights.

Previously, we didn't have a structured way to detect these interactions automatically and relied more on manual review.

What we implemented:

• Trigger:

• sentimentOverallScore < -0.4

• sentimentTrendScore <= 0.2

This allows us to focus on interactions that were both negative and not improving, reducing noise from recovering conversations.

• Workflow logic:

• Queue-based filtering using queueId to ensure only our queues are processed

• Ignoring empty queueIds to avoid cross-division noise

• Handling multi-division interactions by using queueId as the source of truth instead of divisionIds

• Enrichment:

• AI-generated summaries

• Agent name lookup

• Trend classification (Declining / Slightly Declining / No Change / Improving)

This has given us the ability to automatically surface interactions where customers had a genuinely poor experience, without relying on manual QA review.

Example notification:

🚨 AI Insight Triggered

Queue: Customer Service Team
Sentiment: 🔴 Negative (-0.893)

Trend: ➡️ No Change (-0.102)

Agent: <Agent Name>

Summary:
<AI insights summary>

Interaction:
https://apps.mypurecloud.com.au/directory/#/analytics/interactions/12345678/admin

Next step:

This can also be used by for evaluating a subset of these interactions using AI Supervisor Copilot to support QA, coaching, and continuous improvement.

Interested to hear how others are using sentiment and trend signals for proactive monitoring or auto-evaluation.

#AICopilot(Agent,SupervisorAdmin)

------------------------------
Phaneendra
Technical Solutions Consultant
------------------------------