Capabilities · Classification
SaaS Churn
HealthyIn-context predictionEndpoint saas-churnProduction v3Challenger v4
Accounts scored / day
18.2K
AUC
.890
At-risk ARR flagged
$2.31M
P95 latency
31ms
Production
3 weeks ago
v3
- AUC
- .890
- P95
- 31ms
- Cost / 1K
- $0.09
Serving 100% of traffic
Challenger
2 days ago
v4
- AUC
- .902
- P95
- 34ms
- Cost / 1K
- $0.11
Shadow evaluation complete · Not serving traffic
Call it from your product
Sandbox
from zerograd import ZeroGrad
zg = ZeroGrad(remote=True) # reads ZEROGRAD_API_KEY
result = zg.predict("saas-churn", {
"plan": "pro",
"seats_active_30d": 12,
"support_tickets_open": 3,
"last_login_days": 14,
}))Response
{
"version": 3,
"classes": ["stays", "churns"],
"predictions": [{
"prediction": "churns",
"score": 0.71,
"proba": {"stays": 0.29, "churns": 0.71},
"prediction_id": "prd_01J9X4P7QA"
}]
}Next step
v4 beats v3 on AUC (.890 → .902) in offline evaluation. Shadow results confirm it on live traffic.
Activity
Today
- 08:00Weekly scoring batch completed — 18.2K accounts
2 days ago
- 14:10v4 created — product usage events added to context
Last week
- 10:02Feature drift detected on seats_active — severity moderate
3 weeks ago
- 17:45v3 promoted to production
Use it from an agent
Every capability is also a tool. Give your agents calibrated predictions instead of letting them guess.
Private preview
One remote MCP server for the whole workspace. Works with Claude, Cursor, VS Code and any MCP client.
Claude Code
claude mcp add --transport http zerograd https://mcp.zerograd.dev/v1 \
--header "Authorization: Bearer $ZEROGRAD_API_KEY"mcp.json · Claude Desktop, Cursor, VS Code
{
"mcpServers": {
"zerograd": {
"type": "http",
"url": "https://mcp.zerograd.dev/v1",
"headers": { "Authorization": "Bearer ${ZEROGRAD_API_KEY}" }
}
}
}Tools exposed
- saas_churn_predictClassificationEstimate the probability that a customer account churns in the next 90 days, with the top contributing factors.
- get_capabilityHealth, production version and live quality metrics.
- list_capabilitiesEvery capability in the workspace.
- record_outcomeSend the real outcome for a prediction_id once it is known.
Tools are scoped by API key. Calls are logged, metered and show up in this capability's observability like any other request.