# Drift alerts > Get told when an agent's score, cost or latency moves sharply, with a link to the runs that caused it and the blueprint version in force. A screening tells you how an agent performs today. Drift alerts tell you when that has quietly changed. Badge compares each day's numbers for an agent with the days before it, and raises an alert when a metric moves further than normal noise would explain. Drift alerts are off unless your deployment turns them on. When they are off, the **Drift alerts** card does not appear on the Manage page, the Trends chart shows no alert markers, and the newer series (score, measured cost, p95 latency) and version notes are empty. Those series then read "Not enough data". What is measured [#what-is-measured] Four metrics, one point per day: | Metric | Alerts when it | Unit | | --------- | -------------- | ----------------------------- | | Score | drops | points on the 0 to 100 score | | Pass rate | drops | share of runs that passed | | Cost | rises | measured cost per run, median | | Latency | rises | median, milliseconds | Only **Verified** and **Traced** runs feed these numbers. Simulated runs are not plotted and never raise an alert. Cost uses measured cost only: a cost the agent reports about itself does not move the cost series, because it can understate what the agent really spends. The Trends chart draws latency as the 95th percentile, because that is where slow tails show up. Alerts compare the daily median, so a single slow run does not raise one. Scheduled screenings are the best source of points, because they run on a steady cadence. See [Scheduled screenings](/docs/guides/scheduled-screenings). Manual runs count too. When an alert fires [#when-an-alert-fires] For each metric Badge takes the previous days as a baseline (14 days by default, and at least 5 days with runs) and compares the latest day with it. An alert needs **both**: * a move of at least the **sensitivity**, a z-score threshold (2.5 by default), measured in baseline standard deviations, and * a change at least as large as the metric's **minimum change**, in the bad direction. The defaults are 5 points for score, 5 percentage points for pass rate, 10% for cost and 20% for latency. The second condition stops a very steady agent from alerting on a trivial change. Cost and latency also have a fixed absolute floor under their percentage: a change must be at least $0.0005 per run for cost, and 50 ms for latency. A 20% jump from 5 ms to 6 ms is not an alert. The Manage page shows this floor next to the setting; you cannot change it. A metric raises at most one alert per agent per 24 hours. If a pass-rate alert and a score alert fire together, they travel as one message: the score message, with the pass-rate alert's id in `related_alert_ids`. Who is told [#who-is-told] Alerts always appear in the app, on the Manage page and the Trends chart. Webhook deliveries and the daily digest email are sent to owners on a paid plan. On the Free plan, alerts are in-app only: there is no webhook and no digest email. Badge checks after a scheduled screening finishes. You can also press **Check for drift now** on the Manage page, once per minute per agent; if you press it sooner, the page says how many seconds to wait. There is no background polling. On the agent page [#on-the-agent-page] The **Trends** card shows the four series. It sits on the **Improve** tab of the agent page, which only people who can edit the agent see, and it has its own link (`/agents/?section=improve#drift`) that webhook deliveries point to. A red marker sits on each day that raised an alert and links to the first run behind it. A dashed line marks each day the agent's blueprint version changed, with a note under the chart such as "v3 → v4". A drop that starts at a dashed line usually points at the change you made. Version numbers are shown to the owner only. For a public agent, the public API lists only the metric, the day and the direction of each alert. It never includes numbers, runs or blueprint versions. Drift that happened while the agent was private is never shown publicly, even after you make the agent public. The chart is a labelled graphic with a text summary for screen readers, and every marker can be reached with the keyboard. Manage alerts and thresholds [#manage-alerts-and-thresholds] On the agent's **Manage** page, the **Drift alerts** card lists each alert with the observed value, the baseline it was compared with, the z-score, the blueprint version and links to the triggering runs. **Acknowledge** marks one as seen. The same card holds the thresholds form: an on/off switch for the whole agent, the sensitivity (a z-score threshold), the baseline window, and for each metric an on/off switch and a minimum change. Saving replaces all of these together. | Setting | Allowed range | | ------------------------------- | -------------------------------------- | | Sensitivity (z-score threshold) | 1.5 to 10 | | Baseline window (days) | 5 to 60 | | Score minimum change | 1 to 50 points | | Pass rate minimum change | 0.01 to 0.5 | | Cost minimum change | 0.01 to 5 (a fraction of the baseline) | | Latency minimum change | 0.05 to 5 (a fraction of the baseline) | Raise a minimum change or turn a metric off if an agent is naturally noisy. Lower it if you want to hear about smaller moves. Webhooks [#webhooks] Subscribe a webhook to `agent.drift.score`, `agent.drift.cost` or `agent.drift.latency` in [Settings](/settings). A pass-rate alert is delivered as `agent.drift.score`; the `metric` field says `pass_rate`. Deliveries carry the usual `X-Badge-Signature` header; see the [REST API reference](/docs/reference/rest-api) for the verification recipe. ```json { "event": "agent.drift.score", "timestamp": "2026-10-14T10:00:00+00:00", "data": { "alert_id": "6f1f6c1e-0000-4000-8000-000000000001", "agent": { "id": "00000000-0000-4000-8000-000000000001", "name": "Support Agent" }, "metric": "score", "direction": "down", "bucket_date": "2026-10-14", "baseline": { "mean": 72.4, "std": 1.1, "window_buckets": 14 }, "observed": 55.0, "z": -15.8, "delta": -17.4, "run_ids": ["run-id-1", "run-id-2"], "blueprint_version_id": "3d2c9a40-0000-4000-8000-000000000002", "blueprint_version_number": 4, "chart_url": "https://badgeia.com/agents/00000000-0000-4000-8000-000000000001?section=improve#drift", "related_alert_ids": [] } } ``` | Field | Meaning | | ------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | | `event` | `agent.drift.score` (score and pass rate), `agent.drift.cost` or `agent.drift.latency`. | | `timestamp` | When the delivery was created. | | `data.alert_id` | The alert's id, the same one the Manage page lists. | | `data.agent` | The agent's `id` and `name`. | | `data.metric` | `score`, `pass_rate`, `cost` or `latency`. | | `data.direction` | `down` or `up`. | | `data.bucket_date` | The day the alert is about. | | `data.baseline` | The mean and standard deviation of the baseline, and how many days it covered. | | `data.observed` | The latest day's value. | | `data.z` | How many baseline standard deviations `observed` is from the mean. | | `data.delta` | The change from the baseline mean. | | `data.run_ids` | The runs behind the latest day. | | `data.blueprint_version_id` | The blueprint version in force, or `null` if none is recorded. | | `data.blueprint_version_number` | That version's number, or `null`. | | `data.chart_url` | The agent's drift chart. | | `data.related_alert_ids` | Ids of other alerts this message stands for, such as a pass-rate alert that fired together with this score alert. Empty when there are none. | Limits [#limits] * An alert says a number moved. It does not say why. Use the run links and the version note to find the cause. * Too little history means no alert. Until a metric has 5 days with runs there is no baseline to compare with. * The baseline follows the agent. A slow decline over many weeks moves the baseline with it and may not trip an alert; the Trends card still shows it.