The video could not be loaded. Press Play to try again, or read the transcript below.
- With the player focused:
- Space play or pause
- C captions
- JL back or forward 10 seconds
- F full screen
AI Memory in ServiceNow
Memory is what transforms a chat into a relationship.
Transcript
When it comes to AI, memory is one of the most essential, and least understood, ingredients of intelligent applications.
Most people imagine memory as a static database: information goes in, and later, if you’re lucky, it comes back out. But inside ServiceNow, memory isn’t a bolt-on. It’s a dynamic system embedded into the AI framework, so agents can learn, recall and personalise interactions across time.
Memory is what transforms a chat into a relationship.
At the heart of ServiceNow’s memory system are three layers that mirror how humans think and recall.
Short-term memory is the context within a conversation. It helps the agent keep track of the current flow and respond coherently. Episodic memory is the historical record of interactions and events: chats, incidents and actions. And long-term memory holds the enduring facts and preferences that persist across sessions, linked to individual users.
Long-term memory lets an agent say, “Welcome back, I remember your last laptop issue,” without ever needing a case history in front of it.
Behind the scenes, this runs on a clean schema. Memory categories define what types of information can be remembered. The agent-category mapping controls which agents can access which memories. And the memory table stores the individual facts, tied to users and categories.
Each memory has a relevance score, which increases when it’s recalled successfully. That teaches the system what’s most valuable to remember.
When a user mentions something memorable, like “I prefer Teams calls”, the agent checks whether it’s allowed to store that fact. If it is, it saves it under the right category.
In a future session, when the context calls for it, the agent retrieves the fact, injects it into its reasoning, and responds accordingly.
The more a memory is used, the stronger its relevance becomes, which keeps the system personal and efficient.
Once you start customising memory, it gets interesting. Each layer offers a place for intelligence and control.
The agent layer defines when an agent should remember or forget. A conversational agent might store preferences, and a troubleshooting agent might remember configurations. The retrieval layer decides how memories are fetched and ranked, using relevance scores or recency filters. The governance layer adds privacy rules, retention limits and user-controlled deletion, to balance usefulness with trust. And the prompt layer decides how and when memories surface in the conversation, from “Last time you said” to silent context.
Memory isn’t just a feature. It’s the connective tissue between conversations, data and experience. In ServiceNow, it’s what lets AI agents evolve from reactive assistants to proactive collaborators. Combine memory with orchestration, retrieval and reasoning, and you get systems that know what’s happening now, and remember what happened before. That continuity is the essence of intelligence.
Memory in ServiceNow isn’t magic. It’s built from tables, like any other feature in the platform. As AI agents mature, memory will define their personalities as much as their capabilities. The so-called smartest systems won’t just generate answers. They’ll remember why those answers matter.
