🚨The timing of all changes discussed in this article remains at the sole discretion of LivePerson and is subject to change.
Introduction
At LivePerson, we are committed to providing you with the most advanced and reliable Generative AI capabilities. To ensure we continue leading the industry in innovation and performance, we are pleased to announce the migration of our AI-powered applications to Google’s latest Gemini models.
Why LivePerson is migrating to Gemini
This transition is driven by our ongoing partnership with Google, which grants us early access to cutting-edge models. Our extensive benchmarking has shown that Gemini models consistently perform as well as—and in several key use cases, better than—our previous models. By moving to Gemini, we are not only ensuring the long-term stability of our services ahead of upcoming model retirements (currently scheduled for October 1, 2026) but also delivering faster, more accurate, and more efficient AI experiences to help you better serve your customers.
➡️ All the rigorous safeguards you rely on today will remain in equal or improved standing with Gemini. Specifically:
- Zero data retention: Your data is processed in-memory and is never stored by the model provider.
- No model training: Google is strictly prohibited from using your data to train their foundation models.
- Robust guardrails: All of our existing Generative AI security guardrails are fully supported to ensure sensitive data is protected.
For a comprehensive overview of our security architecture and data handling policies, we invite you to review our updated Generative AI Security & Privacy Whitepaper.
Impacted products
EMEA and NA regions
- Automated Conversation Summaries
- Copilot Rewrite
- KnowledgeAI integrations in Conversation Assist
- KnowledgeAI agents built in Conversation Builder
- Routing AI agents built in Conversation Builder
- AI agents built in aiStudio
APAC region
- Automated Conversation Summaries
- Routing AI agents built in Conversation Builder
- AI agents built in aiStudio
Product-to-model mapping
Use case | Provider | Subscription | LLM |
|---|
Automated Conversation Summaries | google | summarization | gemini-2.5-flash |
Copilot Rewrite | google | rewrite | Gemini-2.5-flash-lite (EMEA and NA only) |
Copilot Translate* | google | TBD | gemini-2.5-flash-lite (EMEA and NA only) |
KnowledgeAI integrations in Conversation Assist (Copilot Assist) | google | kai | gemini-2.5-flash-lite (EMEA and NA only) |
KnowledgeAI agents built in Conversation Builder | google | kai | gemini-2.5-flash-lite (EMEA and NA only) |
Routing AI agents built in Conversation Builder | google | TBD | gemini-2.5-flash |
AI agents built in aiStudio | google | TBD | gemini-2.5-flash |
*Copilot Translate already uses a Google Gemini model, and self-service configuration of prompts by brands isn't yet available. So, there is no call to action for you if you're using this product. However, as a part of this effort, we will be upgrading the model in use.
General migration process
Step 1 - Optimized system prompts are available.
Step 2 - Optimized custom prompts are available.
Step 3 - Cut over of system prompts.
➡️ For some products, Step 3 happens before Step 2; see the product-specific guidance later in this article. It includes each product's schedule.
Step 4 - Cut over of custom prompts.
Step 5 - "Catch all" cutover.
Each step is described in detail in the sections that follow.
Step 1 - System prompts are available
LivePerson releases new system prompts that are optimized for Gemini models. Depending on the application in question, access these prompts in the dropdown list on the application's configuration page or via the Prompt Library.
Starting on this date, you can preview the Gemini-optimized system prompts if you choose.
Step 2 - Custom prompts are available
By the date for Step 2, you can find within the UI a version of your custom prompt that has been specially engineered by our data scientists for use with Gemini. Here too, depending on the application, access the prompt in the dropdown list on the application's configuration page or via the Prompt Library.
The prompt isn't active. We take the step to add the custom prompt to your account for you, so you don't have to perform this manual work.
On this date, begin to test your custom prompt.
Step 3 - Cutover of system prompts
LivePerson automatically updates all system prompts (the default one and any other) to become ones that are optimized for Gemini.
If your solution uses a system prompt (rather than a custom one), in effect, you are migrated to Gemini automatically at this time.
During the cutover process, LivePerson needs to handle the Gemini-optimized system prompts that we released earlier for preview by you. At cutover, we update their names, so they are prefixed with "Temp - ." In the near future, after we confirm that no brand is using them, we will remove them.
If you are using a "Temp - " prompt in Production, please switch to the new "Gemini - " system prompt that is available upon cutover as soon as possible.
Step 4 - Cutover of custom prompts
On the date for Step 4, if you haven't applied your optimized custom prompts to your Production solution, here's what happens:
In all of your custom prompts in Production, LivePerson automatically updates the Provider, Subscription, and LLM settings, so they point to the preferred Gemini model for the given product (see the product-to-model mapping above). In addition, and importantly, we also update the prompt text so that your new Gemini-optimized custom prompt is used.
Titles of custom prompts remain unchanged.
Cutover affects only a subset of your custom prompts or aiStudio flows. Generally speaking, for most products, this includes the prompts and flows that were active when this initiative began. For Conversation Builder AI agents, this includes the prompts that were created before this initiative began. (For more details, contact your LivePerson representative.)
If you have prompts or flows that don't meet the general criteria above, that is:
- The prompt or flow is much older or inactive.
- You created the prompt or flow after LivePerson retrieved the prompts that needed optimization for Gemini.
- The prompt already points to a Gemini model.
Such prompts or flows aren't included in the cutover.
Call to action before this cutover
- Review all of your custom prompts and flows, and manually migrate them to Gemini before this cutover. For help with optimizing prompt text, please see our best practices on creating prompts; these have been developed with a focus on Google's Gemini models.
Cutover of aiStudio custom flows
On the date for Step 4, if you haven't applied your Gemini-optimized custom flow to your Production solution, LivePerson updates the existing flow to make it compatible with Gemini.
➡️ If you do manually migrate yourself to the Gemini-optimized flow, take care to update the associated Conversation Builder AI agent, so it points to that flow.
Step 5: "Catch all" cutover
At a time of LivePerson's choosing, we will perform a second cutover of custom prompts in order to "catch" and migrate all remaining prompts to Gemini.
As a part of this process, only the Provider, Subscription, and LLM settings of the prompt are updated to point to a Gemini model. The prompt text remains unchanged.
Since such prompts aren't optimized for Gemini, they might not perform as you expect. So, there is an important call to action before this cutover happens:
Call to action before this cutover
- Review all of your custom prompts and flows, and manually migrate them to Gemini before this cutover. For help with optimizing prompt text, please see our best practices on creating prompts; these have been developed with a focus on Google's Gemini models.
Timing of this cutover
These cutovers will happen by model and by region, not by product. Impacted brands will be notified about cutover dates via LivePerson's Status Page portal.
Best practices
Brands in EMEA and North America: We strongly encourage you to refrain from creating new prompts that use an Azure model. Start using the Gemini models that are available. This avoids unnecessary, manual migration work by you.
FAQs
Does Google Gemini keep my data in-region?
Yes. Data residency is a priority, and all data processed via Gemini remains within your designated region. For detailed information on our privacy and security protections, please visit the LivePerson Trust Center to explore our Generative AI safety standards.
A single prompt in the Prompt Library can have multiple versions. Which version of my custom prompt will you optimize?
LivePerson will optimize only the latest version of a custom prompt. (See the previous FAQ for additional constraints.)
While there's an editing history for each prompt in the Prompt Library, this functions more as a failsafe. It only allows you to copy what you need from an older version if you ever need it.
When will I receive my Gemini-optimized custom prompt from my LivePerson representative?
You won't be receiving this prompt from your LivePerson representative. LivePerson will add it to your account in the system for your manual selection and use according to your product's schedule. (Product-specific schedules are discussed below.)
Will LivePerson be updating my Alpha account?
LivePerson will not be automatically cutting over any Alpha accounts to Gemini models.
However, once Gemini-optimized system prompts are made available for your product, they can be used in both Alpha and Production. So, please take care to manually migrate your Alpha account to Gemini if you have one. This requires that you manually select and use a Gemini-optimized system prompt.
Tip: The names of all Gemini-optimized system prompts that use a Gemini model are prefixed with the word "Gemini."
How do I apply my Gemini-optimized custom prompt in Production?
To avoid the forced cutover, apply your Gemini-optimized custom prompt in Production as soon as possible after you perform testing as described below.
- For all solutions except AI agents built in aiStudio, there are no special instructions needed to accomplish this. In your Production solution, simply replace the Azure-optimized custom prompt in use with your Gemini-optimized prompt.
- In the case of AI agents built in aiStudio, LivePerson will update the relevant flow for you.
Can I delete my custom prompts that I no longer need?
Not at this time, but we have a recommended workaround.
Get support
If you have questions regarding your specific implementation, please contact your LivePerson account representative.
Product - Automated Conversation Summaries
Schedule for EMEA
- March 4, 2026: New system prompts are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- March 28, 2026: Cutover of system prompts.
- TBD: Cutover of custom prompts.
Schedule for NA
- March 4, 2026: New system prompts are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- March 29, 2026: Cutover of system prompts.
- TBD: Cutover of custom prompts.
Schedule for APAC
- April 9, 2026: New system prompts are available in the system; preview is available. Also, optimized custom prompts are available in the system; start testing.
- {Determined by LivePerson representative and brand}: Cutover of custom prompts.
Name of Gemini-optimized system prompts
- Gemini - Structured style summary - Summarization
- Gemini - Paragraph style summary - Summarization
Testing
Use the Test and tune feature to test the Gemini-optimized system or custom prompt and compare it to your current prompt. Focus the bulk of your testing time here:
If desired, you can also test the end-to-end flow by creating a "test" skill and configuring your solution like so:
Doc resources
Product - Copilot Rewrite
Schedule for EMEA
- March 4, 2026: New system prompts are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- March 28, 2026: Cutover of system prompts.
- June 28, 2026: Cutover of custom prompts.
Schedule for NA
- March 4, 2026: New system prompts are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- March 29, 2026: Cutover of system prompts.
- July 12, 2026: Cutover of custom prompts.
Schedule for APAC
Name of Gemini-optimized system prompt
- Gemini - Copilot:Rewrite - Default
Testing
Use the Test and tune feature to test the Gemini-optimized system or custom prompt and compare it to your current prompt. Focus the bulk of your testing time here:
If desired, you can also test the end-to-end flow by creating a "test" skill and configuring your solution like so:
Doc resources
Product - KnowledgeAI integrations in Conversation Assist
Schedule for EMEA
- March 4, 2026: New system prompts for Messaging are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- April 4, 2026: Updated system prompts are available in the system; preview is available.
- June 6, 2026: Cutover of system prompts.
- Not actionable: Cutover of custom prompts.
Schedule for NA
- March 4, 2026: New system prompts for Messaging are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- April 5, 2026: Updated system prompts are available in the system; preview is available.
- June 20, 2026: Cutover of system prompts.
- August 2, 2026: Cutover of custom prompts.
Schedule for APAC
Name of Gemini-optimized system prompt
- Gemini - Enrichment Factual EN - Conversation Assist (Messaging)
- Gemini - Enrichment Factual EN - Conversation Assist (Voice)
Testing
Use KnowledgeAI's Answer Tester to test the Gemini-optimized system or custom prompt and compare it to your current prompt. The Answer Tester is designed for rapid, iterative development, so focus the bulk of your testing time here:
If desired, you can also test the end-to-end flow by creating a "test" skill and configuring a dedicated knowledge base-level recommendation rule in Conversation Assist; make sure it's used for testing alone.
Doc resources
Product - KnowledgeAI agents built in Conversation Builder
Schedule for EMEA
- March 4, 2026: New system prompts for Messaging are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- April 2, 2026: Updated system prompts are available in the system; preview is available.
- June 6, 2026: Cutover of system prompts.
- Not actionable: Cutover of custom prompts.
Schedule for NA
- March 4, 2026: New system prompts for Messaging are available in the system; preview is available.
- March 10, 2026: Optimized custom prompts are available in the system; start testing.
- April 2, 2026: Updated system prompts are available in the system; preview is available.
- June 20, 2026: Cutover of system prompts.
- August 2, 2026: Cutover of custom prompts.
Schedule for APAC
Name of Gemini-optimized system prompt
- Gemini - Enrichment Factual EN - Messaging bot
- Gemini - Enrichment Factual EN - Voice bot
Testing
Use KnowledgeAI's Answer Tester to test the Gemini-optimized system (or custom) prompt and compare it to your current prompt. The Answer Tester is designed for rapid, iterative development, so focus the bulk of your testing time here.
Need an example? See our testing discussion in the previous section on KnowledgeAI integrations in Conversation Assist. The testing process in the Answer Tester works the same.
If desired, you can also test the end-to-end flow by creating a test bot and deploying it on a "test" skill.
Doc resources
Product - Routing AI agents built in Conversation Builder
If your solution uses a Conversation Builder Routing AI agent, please proactively migrate its prompts to Gemini yourselves. In this particular product case, you are best positioned to identify your own impacted configurations, so your proactive action helps to ensure a smooth and timely transition.
Schedule for EMEA
- May 3, 2026: New system prompts and optimized custom prompts are available in the system. You can preview the system prompts if desired, and you can start testing the custom prompts.
- June 13, 2026: Cutover of system prompts.
Schedule for NA
- May 2, 2026: New system prompts and optimized custom prompts are available in the system. You can preview the system prompts if desired, and you can start testing the custom prompts.
- June 28, 2026: Cutover of system prompts.
Schedule for APAC
- May 3, 2026: New system prompts and optimized custom prompts are available in the system. You can preview the system prompts if desired, and you can start testing the custom prompts.
- Not applicable: Cutover of system prompts.
Testing
1 - In Conversation Builder, export the bot to JSON, and then import the JSON back into Conversation Builder. This creates a test copy of the bot.
2 - In the Guided Routing interaction in the test bot, change the prompt in use to be the Gemini-optimized one that was provided to you by LivePerson.
3 - Test the behavior.
Migrating the AI agent to Gemini
1 - Perform testing as described above.
2 - After you've verified that the test bot performs as you expect, return to the production bot and, in the Guided Routing interaction, change the prompt in use to be the Gemini-optimized one.
Doc resources
Product - AI agents built in aiStudio
The two most common cases involving aiStudio are these:
- AI agents created from use cases: These agents were created via fully customizable templates.
- AI agents created from scratch: These agents were created by starting from a blank canvas.
Milestones for both are below.
Schedule for EMEA
- April 21, 2026: Flows are available for AI agents created from use cases. Testing can begin.
- May 20, 2026: Flows are available for AI agents created from scratch. Testing can begin.
- August 19, 2026, 8 p.m. British Standard Time: The freeze period begins; learn more below.
- August 20, 2026: Cutover of flows for all AI agents.
- August 21, 2026, 8 p.m. British Standard Time: The freeze period ends.
Schedule for NA
- April 20, 2026: Flows are available for AI agents created from use cases. Testing can begin.
- May 19, 2026: Flows are available for AI agents created from scratch. Testing can begin.
- September 2, 2026, 7 a.m. Eastern Standard Time: The freeze period begins; learn more below.
- September 3, 2026: Cutover of flows for all AI agents.
- September 4, 2026, 7 a.m. Eastern Standard Time: The freeze period ends.
Schedule for APAC
- April 21, 2026: Flows are available for AI agents created from use cases. Testing can begin.
- May 20, 2026: Flows are available for AI agents created from scratch. Testing can begin.
- {Determined by LivePerson representative and brand}: Cutover of flows for all AI agents.
Testing
Perform testing within aiStudio (use the flow tester and start a conversation, use simulations to batch test queries, etc.). If you find any issues, contact your LivePerson account representative, so we can engage our Data Science team to examine the issue and collaborate on a solution.
Migrating an aiStudio flow to Gemini yourself
LivePerson recommends that if you haven't already migrated your custom flows, please do so before the cutover. Learn about self-migration in our article.
Cutover process
1 - On the specified date, a 48-hour "freeze" on brand activity starts. LivePerson asks that all brands refrain from making changes to existing flows and from creating new ones. LivePerson retrieves necessary data on existing flows.
2 - On the specified date, LivePerson migrates all existing flows to Gemini. LivePerson prepends "[Gemini]" to the name of the Gemini flows that are active once the cutover is completed.
➡️ Flows that already point to a Gemini model are unaffected.
3 - On the specified date, the 48-freeze period ends.
Once the cutover is completed:
1 - Verify that the active Gemini flows perform as you expect.
2 - For the sake of keeping things tidy and organized, we also recommend that you delete old prompts and flows that are no longer in use.
FAQ 1: How can I know if I am impacted by the cutover?
If you created a new aiStudio flow after February 4, 2026, you are likely excluded from the cutover. (This was the date on which we retrieved data on existing flows.) In this case, contact your LivePerson representative to request a Gemini-optimized flow. Once you receive it, you can migrate the flow to Gemini yourself. Contact your LivePerson representative if you need assistance.
If you are unsure about whether you are impacted by the cutover, contact your LivePerson representative.
FAQ 2: What is the impact if I make additions or edits to prompts and flows during the freeze period?
If you make changes during the freeze period, those changes may be overwritten as a part of the cutover. Please refrain from making changes during this time.
Change history
As we make updates to this article, we'll update the change history below. Check here to understand what's changed in this article and when.
Date | Description of change |
|---|
July 22, 2026 | Added the date of August 2, 2026 for the North America region for the cutover of custom prompts that use KnowledgeAI. |
July 16, 2026 | For aiStudio flows, added info on the cutover process. |
July 15, 2026 | For Conversation Builder Routing AI agents, expanded the info on testing and self-managed cutover processes. |
July 9, 2026 | Added info on the "catch all" cutover process (step 5 in the overall migration process). |
June 17, 2026 | Added dates for cutover of Copilot Rewrite custom prompts. Augmented the information on the process of cutting over custom prompts. |
June 3, 2026 | Added dates for cutover of system prompts for Conversation Builder Routing AI agents. Added best practices for EMEA and North America. Updated several APAC dates to "Determined by LivePerson representative and brand." |
May 19, 2026 | Updated the EMEA and NA schedules for KnowledgeAI integrations in 1) Conversation Assist and 2) KnowledgeAI agents built in Conversation Builder |
April 29, 2026 | Updated the schedules for Routing AI agents built in Conversation Builder. |
April 22, 2026 | Updated all product-specific schedules, setting numerous dates to "TBD." |
April 20, 2026 | Updated all product-specific schedules. |
April 16, 2026 | Changed dates for cutover of KnowledgeAI prompts (for Conversation Assist, and for Conversation Builder KnowledgeAI agents) to "TBD." |
April 14, 2026 | Updated the APAC date for the following milestone re: AI agents built in aiStudio: Prompts are available for AI agents created from use cases. Testing can begin. |
April 13, 2026 | Reset some milestone dates to "TBD" for 1) Automated Conversation Summaries, 2) Copilot Rewrite, and 3) solutions using KnowledgeAI (i.e., Conversation Assist, Conversation Builder KnowledgeAI agents) for EMEA and NA regions. |
April 8, 2026 | Added migration schedules for APAC for impacted products (not all products are impacted). |
April 1, 2026 | Updated scheduled for products integrating KnowledgeAI (i.e., Conversation Assist and Conversation Builder); updated dates for aiStudio AI agents and added testing guidance for same |
March 16, 2026 | Updated the date for the cutover of system/default prompts for brands in the NA region to be March 29, 2026; this will still happen for brands in EMEA on March 28, 2026. |
March 12, 2026 | All APAC schedules set to "TBD." Removed APAC-specific note in "General migration process." |
March 12, 2026 | Clarified the language regarding models and inferencing in "General migration process." |
March 11, 2026 | APAC: Updated the cautionary guidance in the "General migration process" section to be APAC-specific; check the note with the red "stop" sign. Also, added APAC-specific schedules for all products; please see the product-specific sections in this article.
All regions: Updated the dates for Gemini-optimized prompts for Voice solutions to read "TBD," as these prompts are delayed. Also, added testing guidance for Routing AI agents built in Conversation Builder.
|
March 10, 2026 | Added partial migration schedule for Copilot Rewrite in the APAC region. |