Does anyone know about long-term memory in servicenow ai agent?

[Tae Kyung Lee]

Hello.

I've found that there are two properties that enables long-term memory for AI Agents. (Link)

- sn_aia.ltm.enable_long_term_memory : Enables long-term memory for AI agents. All previous user interactions are used as context for the LLM.

- sn_aia.ltm.use_memory_for_ai_agent : Enables a long-term memory for AI agents. Previous user interactions are used in AI agent interactions.

Do you how and where they are stored in platform and can be accessed for ai agent?

[Dr Atul G- LNG]

Hi @Tae Kyung Lee 

There’s very limited documentation available for this, so it’s better to log a case with the Now Support team and share the feedback with us. I believe it might be related to a different server or engine.

[warren_chan · Accepted solution]

Yes, this is what we refer to as long-term memory, and it will be stored in the AI Agent Memory [sn_aia_memory] table. You can test this by running the same Agentic AI test case over and over again, and responding to the conversations the same way each time. The long-term memory is user-specific, but this feature may improve over time.

[Tae Kyung Lee]

Thanks for clear answer!

It seems that conversations are categorized by predefined group such as 'Device and Software'.

"User has a Samsung Galaxy Tab A 10.5 (SM-T597V) that is corporate-owned, enrolled, and currently in use, created after 2025-04-20. Uses Samsung Galaxy Tab A 10.5 SM-T597V."

But some of stored information can be changed currently, so I need to test when long-term memory is used and how can I avoid it with prompt if I need.

[Ketan Pandey]

Could you please suggest where to check ,sometime my AI agent skipping the  prompt and sometime it works perfectly. I used the chatgpt help ,it did not work.