Example: source-linked decision memory.
Updated 2026-06-07 · Agent-readable markdown available
A concrete example of an Ambience decision memory with source, scope, redaction, and future retrieval.
A source-linked decision memory turns a messy work artifact into a concise, auditable record an agent can reuse.
- Source: the original call, ticket, PR, thread, document, or session.
- Memory: the reusable decision and reasoning.
- Control: scope, redaction, conflict status, and audit.
Source to memory
Source artifact
Granola call
The onboarding sweep asks which app sources are included before the agent scans anything.
Ask before including sources in onboarding sweeps
Onboarding sweeps must show the available app and local sources, then ask the user which ones are included before proposing Ambience memories.
- Source
- Granola call remains the source of record
- Redaction
- Customer names removed before storage
- Audit
- Accepted by product owner during onboarding review
- A future onboarding task retrieves the decision before changing the sweep flow.
- The UI can show the linked source without copying the whole call into Ambience.
Source
Granola call: the team agreed that onboarding sweeps should ask users which connected apps are included before scanning any source material.
Ambience memory
Decision: Ask users to approve included sources before onboarding sweeps. Scope: org. Source: Granola call. Reason: it keeps setup permissioned and prevents accidental import of private context.
Future retrieval
When an agent works on onboarding, Ambience can retrieve the decision and show where it came from before the agent proposes a flow.