Memory ​

Persistent memory is how the AI keeps context across chats. Instead of starting from scratch every conversation, it reads — and, with the right provider settings, writes — entries here. The Memory tab is the inspector for that store: every saved file, the rolled-up assessment status, and the storage usage.

Memory tab with the persistent file list, total size, file count, health badge, and the rendered Markdown of an InfraScout assessment status entry

Layout ​

The page header carries the AI Integrations title and the Admin Access chip; the tab strip puts you on Memory. Three KPI cards sit at the top of the body:

  • Total size — bytes used by the memory store, with the headroom limit underneath.
  • Files — count of saved memory entries.
  • Health — overall store health, Healthy when no entry is corrupt or stale.

A Sign In chip on the right confirms which Entra identity the memory is scoped to. The Refresh button is to its left.

The body splits into a Files sidebar (left) and a Preview pane (right).

Files sidebar ​

The sidebar lists every file currently in the persistent memory store. Each entry carries a small icon indicating its type and a relative timestamp (or chip) for the last touch. Common entries you will see:

  • environment — environment metadata (domain, tenant, network).
  • assessment-status — the rolled-up assessment status the AI maintains across sessions.
  • ca_policy_, alpha_security_audit_ — entries scoped to a specific assessment domain.
  • expired_certificates_audit_* — exception entries the AI is tracking for follow-up.
  • scem-site-systems-inventory_* — inventory snapshots used as context for SCCM/MECM playbooks.
  • overview, security_event_analysis, security_posture — narrative entries the AI maintains for its own working memory.
  • notes, patterns, users — free-form notes that ride along across sessions.

Click an entry to render its contents in the preview pane.

Preview pane ​

The preview pane renders the entry's Markdown content. The example shows an ITdesign Assessment Status entry: the last update timestamp, the assessment type, an Assessment Coverage checklist, the captured key metrics, and a Known Issues Identified section.

This is exactly what the AI sees when it reads memory at the start of a turn. Editing entries by hand is intentionally not exposed — the store is meant to be written by the AI through the Memory tools, not by humans pasting Markdown.

Rollup behavior ​

Whether the AI is allowed to write memory at all, and whether it can summarize and rewrite existing entries, is controlled per AI provider on the AI Providers tab. Custom memory rollup means the provider runs a tenant-defined summarization pass on each turn; an empty rollup means the provider can read but not modify entries.

Common workflows ​

The two ways operators use this tab: "confirm the AI is remembering the right things" (open the assessment-status entry, scan the rolled-up coverage) and "clear stale memory before a new engagement" (delete entries from the previous customer's project — there is no UI for selective deletion today, but the entry list shows you exactly what is there).