Copilot Adoption Analytics
Interprets GitHub Copilot adoption and acceptance-rate telemetry for a synthetic team and recommends concrete next steps, extending the GHCP Adoption Telemetry project.
Deterministic metrics + AI narrative — synthetic team data, not live telemetry
Adoption rate (active users ÷ seats) and acceptance rate (lines accepted ÷ lines suggested) are GitHub's own published Copilot usage metric definitions, computed deterministically from a fixed weekly record for the team you select — an AI model never invents these numbers. Only the narrative read, likely driver, and recommended actions underneath are AI-generated. The four team profiles are synthetic, illustrative examples of common adoption patterns, not a real engineering org's telemetry.
Try it
Select a synthetic team to see its adoption metrics.
Loading teams…
Pick a team above to begin.
How it works
Pick one of four synthetic teams to see its weekly seats, active users, suggestions shown/accepted, adoption rate, acceptance rate, and trend — computed the same way GitHub's own Copilot usage metrics ↗ are defined — then ask the adoption advisor agent to interpret what the numbers mean and what to do next.
Why this exists
This extends the GHCP Adoption Telemetry project record's theme of turning raw usage signals into evidence-based adoption decisions: the same adoption-rate and acceptance-rate definitions that project's Dataverse telemetry captured, applied here to a synthetic team so anyone can see what a healthy — or stalled — rollout looks like and what a team lead should try next.
Production checklist
- Adoption rate and acceptance rate use GitHub's own published metric definitions.
- Trend classification compares the first half of the window to the second half, computed, not guessed.
- The AI layer only narrates the already-computed summary; it cannot alter any number.
- Dedicated Foundry prompt agent, versioned and isolated from the portfolio chatbot.
- Automated backend tests cover a high-adoption and a low-adoption team case.