Health status & pending recommendations

A health score monitors your LLM APIs. Anything it finds arrives as a pending recommendation, and nothing runs until you approve it.

Live preview (real data from the public demo)

82
Detection“helpfulness” quality is slipping
Quality
95
Errors
100
Safety
100
Follow-up
32

A four-part health score

Quality, errors, safety, and follow-up, each scored 0–100 with daily history. Errors and follow-up are counted from records; quality and safety are model-judged with evidence.

Example

Overall score, last 14 days

Pending recommendations

Findings arrive as proposals with approve / dismiss actions and step-by-step fixes — for wasted cost, with a cheaper model to switch to and the estimated savings. Nothing runs until you approve.

Example
CostModel switch proposalest. −$12/moApprove
QualityFix for “conciseness” dropApprove
✓ Applied · prompt updated2 min ago

Findings notifications

Get notified on your alert channels when a new proposal arrives. Email on Free; every channel, Slack included, on Pro and above.

Email✓ Connected
Slack #ai-alerts✓ Connected
WebhookPro+