Memories
Most AI tools are stateless. Every interaction starts from scratch, losing valuable context between runs. We take a different approach.
Our agents are built on a cognitive memory system inspired by how the human brain organizes knowledge. Memories are the pieces of knowledge that Agents accumulate as they work with your data: specific events, general patterns, and effective strategies. Memories that are no longer accessed lose relevance over time.
Goals of Memories
- Remember your preferences: metric definitions, preferred chart types, important KPIs
- Learn from feedback: when you approve or reject Discoveries, agents remember what matters
- Build business context: industry-specific terminology, seasonal patterns, key stakeholders
- Avoid repeating mistakes: lessons from past analyses carry forward
- Retain entity knowledge: facts about specific customers, products, or segments persist across runs
Memory Types
Agents structure their knowledge into three categories, mirroring how people naturally learn:
| Type | In short | Description | Example |
|---|---|---|---|
| Episodic | "What happened" | Specific events and experiences tied to a moment | "Revenue dropped 15% during the July migration" |
| Semantic | "What I know" | General facts and patterns derived from experience | "Revenue typically dips in Q3 due to seasonal trends" |
| Procedural | "How to do it" | Techniques and best practices learned through practice | "When analyzing churn, always segment by acquisition channel" |
You experience something (episodic), extract a general lesson from it (semantic), and develop a reliable approach for next time (procedural).
Memory Sources
| Source | Description |
|---|---|
| Agent runs | Agents create memories as they analyze data, detect patterns, and generate discoveries |
| Discovery reviews | When you approve or reject a Discovery, the agent remembers your decision |
Memory Lifecycle
Memories go through four stages:
| Stage | Description |
|---|---|
| Created | An agent records an observation during its work |
| Active | The memory is retrieved and used by agents during their work |
| Consolidated | Similar episodic memories are grouped and distilled into semantic or procedural knowledge |
| Faded | Memories that lose interest gradually decay and are eventually removed |
For example, an agent might record several episodic memories about revenue drops during different months. Over time, these are consolidated into a single semantic memory: "Revenue typically dips during infrastructure migrations." The original details fade while the pattern persists.
Memory Scopes
Memories are organized into a hierarchy of scopes, from organization-wide knowledge shared across all agents down to personal preferences visible only to a specific team member. This lets agents apply the right context at the right level, whether it's a company-wide fact or a detail about a specific business entity.
When agents detect the same pattern across multiple workflows, they can promote it so all agents benefit. At the other end, personal memories keep each team member's preferences private and separate.
Memories and Discoveries
Memories and Discoveries work together in a feedback loop:
- When an agent creates a discovery, it may also create related memories
- Approving a discovery confirms the associated memories
- Rejecting a discovery teaches the agent what doesn't matter, including your feedback if provided
- Over time, agents learn what matters to your team and what doesn't
Relevance and Retention
Agents don't keep everything forever. Each memory has a relevance score driven by importance, recency, and frequency of access. Memories that are frequently used retain their relevance. Memories that stop being accessed gradually decay and are eventually removed.
A configurable decay rate controls how quickly unused memories fade:
| Rate | Best for |
|---|---|
| Daily | Transient context that becomes stale quickly |
| Weekly | Standard observations and patterns (default) |
| Monthly | Long-lived business knowledge and user preferences |
Learn More
- Agents: the autonomous collaborators that create and use memories
- Discoveries: findings that agents generate using their accumulated knowledge
- Insights: charts and analyses that agents remember context about
- Dashboards: monitor metrics with agents that remember your context