Full visibility of how AI is accessing and updating your data.
Usage, health and performance — for the whole context layer, one domain, one entity, or one person.
Inspection of the usage, quality, health and performance of your context layer.
Metrics are recorded across the whole context layer: every entity, brief and skill, every domain, every surface. Usage shows which were read, by whom, how often, at what depth, and what each one cost in tokens, and Trends shows how all of it moves over time. That turns AI use of your data from something you guess at into something you manage: you know what is being used and what is not, where consumption is growing, and whether a team's agents are getting what they need. Is anyone using the Renewals domain and why did this rep's Account 360 come back thin are the same tool, asked at different depths.
Quality measures what actually arrived rather than what was intended: how much of an entity the caller's field-level security permitted through, and how sparse the data behind it turned out to be.
And every write an agent makes is recorded in Writes, the write audit log — the user, the agent, the surface, and the field-by-field before and after.
Who changed what, and whenQuality
19 days with traffic · trailing 30 days
Whether agents are getting whole context: how much of what you designed actually arrived, and how often something went wrong.
Domain
Library
Artifact
Surface
Level
Format
Completeness & FLS coverage %
Errors & issues by day
Knowing, instead of guessing.
Usage
What agents read, by whom, on which surface, at what depth and at what token cost. Nothing goes unseen.
Health
Whether what you designed is what arrived. Fields stripped by field-level security and sparse data are shown where and how often.
Performance
Assembly time per request, broken down by element, so a slow entity is traced to its cause. Fast for users, efficient for agents.
Learn more
