> ## Documentation Index > Fetch the complete documentation index at: https://docs.get-hive.ai/llms.txt > Use this file to discover all available pages before exploring further. # Trustworthy signals: evidence, limits and verified outcomes > The principles behind every Hive signal: show the evidence, name what could not be checked, keep people in control, and learn from verified outcomes. An alert you cannot check is an alert you learn to ignore. Hive is designed so that every signal can be checked: it shows where it came from, what Hive looked at, what it could not see, and — over time — whether acting on it actually helped. Connected tools feed a Hive case with source, evidence, freshness and reasoning; a person approves, denies, comments or waits; the verified outcome feeds back. ## Five questions every signal must answer A concrete event or change, tied to the affected customer, invoice, deal or account. The source and the field behind each reading — up to six readings per signal. Plain-language reasoning, the stake, and any known limitation. A person with the right role, in the review panel. Nothing runs until it is approved or within granted autonomy. A receipt in the audit log and, where it can be checked, the outcome. ## Evidence, not assertion Every reading on a signal names its source connector and field, carries a typed value (money, a count, days, a date, a ratio), and says how it was compared: "past your threshold", "against your usual", "corroborated", "correlated" or "cited". Where Hive compares against a baseline, it shows the baseline. Confidence is labelled honestly. A figure marked "Hive's own estimate" is the model's self-assessment; a figure marked "measured" comes from observed results. Hive does not present one as the other. Links to source records are always secure HTTPS links without credentials. They open the record in the source tool, where that tool's own access rules apply. ## Say what could not be checked If a source is unavailable, a permission is missing, or a piece of evidence expired, Hive says so. For example, if an invoice is overdue but support history cannot be read, the safe proposal is to review the account before contacting the customer — not to pretend there is no dispute. When Hive cannot see the conversation behind an email proposal, the review panel says **Conversation context unavailable — review the source before sending.** The same rule applies to silence. **Zero alerts never automatically means all clear.** The [Coverage](/signals/coverage) tab lists what Hive is watching, so you can tell "nothing happened" from "nothing was checked". ## One situation, one record Repeated detections of the same situation update one signal rather than creating a stream of disposable alerts: the row shows how many times it has been seen and when it was first raised. Related signals that fire together are grouped. In the [Signal Cases](/signals/signal-cases) pilot, this becomes a durable case with owner, comments, decisions and outcome kept together. ## Learning without losing control Hive improves from your team's feedback in ways you can see: * **Dismissal reasons** change future detection — muting a record, counting towards alert fatigue for a type, or flagging a data source. See [Triage signals](/signals/triage-signals). * **Approvals and denials** feed [earned autonomy](/approvals/autonomy-and-blast-radius): after repeated approvals of the same kind of action, Hive can *offer* to automate it. Once someone accepts, it runs automatically within limits, and the kill switch halts it. * **Execution memory** records rules, workflows and exceptions your team has taught Hive; new ones start in shadow. See [Learned behaviours](/brain/learned-behaviours). Outcome-based calibration — comparing what Hive expected with what really happened, to propose better thresholds and priorities — is being prepared as part of the pilot. Calibration can *propose* a change. It never silently grants autonomy or rewrites safety policy; a person or an approved policy decides. Five rungs from Shadow to Suggest, Approve, Auto within limits and Autonomous, surrounded by human controls. ## Proof, not a rented model Models can be swapped. A model saying it is confident is not proof that a business decision was right. What makes Hive's signals more useful over time is the record built around the model: connected business facts and their sources, evidence about what Hive could and could not observe, your team's decisions and corrections, the rules it has learned about how you work, and outcomes that show whether an action worked. That record belongs to your workspace. ## What is available today | Capability | Status | | - | - | | Signals feed, evidence and readings, Coverage tab, role-gated review and approval | Available | | Dismissal feedback, mutes, alert-fatigue gate, grouping and de-duplication | Available | | Earned autonomy offers after repeated approvals | Available | | Durable Signal Cases, verified outcomes, richer coverage states | Pilot — off by default | | Outcome-based calibration and staged autonomy promotion | In preparation — proposals only, never automatic | ## Related How Hive finds and ranks signals. How Hive earns the right to act on its own. The kill switch, spend caps and policy. Every action's receipt, and undo.