livepeer / livepeer/livepeer-data-mcp

[Feedback] :thumbsdown: negative — Scope WAU and engagement metrics

Open
#44 0 comments 0 reactions 0 assignees View on GitHub
feedback-negative mcp-feedback
Dominant language
TypeScript
Stars
0
Forks
1
PR merge metrics
No merged PRs in 30d

Description

## Feedback (negative)

**Question:** Scope WAU and engagement metrics
**Tool:** `describe_dataset`

### Corrected answer
scope_cloud_events only captures remote inference (cloud) sessions. Local Scope usage — where users run AI inference on their own GPU without using Livepeer's cloud infrastructure — generates NO telemetry of any kind. WAU numbers from any Scope data source therefore represent only cloud users, and undercount total Scope usage by an unknown amount. This caveat should be stated explicitly whenever reporting Scope WAU or engagement metrics.

### Notes
This is a fundamental measurement gap that affects all Scope analytics. It was discovered mid-session and required updating the dashboard and hypothesis document. The scope_cloud_events dataset description and the user_daily_engagement dataset description should both prominently state: 'Scope metrics reflect cloud/remote inference users only. Local Scope usage (own GPU) is not instrumented and not reflected in any metric.' This context should also be included in route_question routing hints for Scope.

---
_Feedback ID: `c40657c3-e8cf-4315-8cab-4fa40a20003a` | Recorded at 2026-03-11T00:53:27.041Z_

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the scope_cloud_events and user_daily_engagement dataset descriptions, then inspect the route_question routing hints and the dashboard and hypothesis document mentioned in the report. Update each relevant Scope analytics explanation with the cloud-only measurement caveat, and verify that WAU and engagement reporting consistently reflects the documented limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.