Codimir Docs
Codimir Docs
OverviewGet Started
About Codimir
API Reference
Codimir Codec SDK
Concepts
Codimir AI Fabrick
ArchitectureMCP LayerMetrics & SLAsOrchestrationOverviewRoadmapRolesStandard Flow (Light ↔ Heavy)Whitepaper — Codimir Fabrick
Use Cases
Codimir AI Fabrick

Metrics & SLAs

Quality, UX, cost, and safety metrics for the Fabrick.

Metrics & SLAs

UX

  • E2E latency (p50/p95): prompt → first token → ready
  • Continuation rate: % tasks requiring resume
  • SLA adherence by tier (light/heavy)

Quality

  • QA pass rate by role
  • Rework count per task
  • Bug regression rate (post-merge)

Cost

  • $ / successful task
  • GPU minutes per heavy run
  • Tokens per role

Safety

  • PII leakage flagged (target 0)
  • High-risk action confirmations captured
  • Policy violations per 100 runs

MCP Layer

Model Context Protocol bindings for plug-and-play tools.

Orchestration

Overseer, Router, Proctor — decision policy, QA gates, and escalation.

On this page

Metrics & SLAsUXQualityCostSafety
AI Assistant
Assistant
Hi! I'm your AI assistant. Ask me anything or describe your task.