hi5agents
Trust · Mechanisms, not promises

How we keep AI honest

The safety story of Hi5Agents isn't policy — it's mechanisms. Every claim below points at code shipped in the product. If you find one that isn't true, tell us and we'll fix the product or fix the page.

Grounded outputHuman approvalsBYOK · Your keys
013 mechanisms

Grounded output — no invented facts

Where our agents summarize numbers or documents, the output is checked against the source before you see it.

  • How it actually works
    Every generated metric summary is re-parsed and diffed against the source query. On mismatch, we retry once, then render the table with a 'summary unavailable' note.
  • How it actually works
    The generator runs an invention checker that flags any numeric or safety claim without a page citation, and a warning-preservation check that never softens or drops manufacturer warnings.
  • How it actually works
    Each candidate score includes an evidence quote extracted verbatim from the resume; if none is found, the criterion is scored as 'insufficient evidence'.
022 mechanisms

Humans decide on money and reputation

Anything that spends money, changes CRM records, replies to customers, or writes to your store passes through your approval unless you explicitly change the policy.

  • How it actually works
    Each of these actions writes to the approvals queue with the exact payload; nothing executes until an approver confirms. Policies are per-workspace and per-action.
  • How it actually works
    Reversible write-backs record the pre-image; one click restores it. Non-reversible actions are labeled as such before you approve.
032 mechanisms

Provenance & labels — AI content is always marked

Anything generated or altered by AI carries a label that follows it out of our product.

  • How it actually works
    Provenance is stored per file and burned into the render spec as an on-frame corner badge; it can't be toggled off in the export.
  • How it actually works
    The generator refuses to emit a claim without a citation index that resolves to a real source page.
043 mechanisms

Your keys, your data, your accounts

BYOK/BYOA is the default. We don't resell your data or lock you in.

  • How it actually works
    Keys are stored per-workspace, encrypted at rest, and used directly to call the provider. Your bill from the provider is your bill.
  • How it actually works
    Every table scoped to a workspace has an RLS policy that checks membership; a member of workspace A cannot read data from workspace B, ever.
  • How it actually works
    Standard retention: operational logs 90 days, generated media 12 months unless deleted sooner. Contact support to purge on request.
052 mechanisms

Published, honest limits

Every agent's public manual has a Limitations section written by a human and reviewed before publish.

  • How it actually works
    Limitations are a required, non-empty section of every agent doc. Drafts are AI-assisted from a curated facts registry, but a human reviews before publish.
  • How it actually works
    Both run a data-sufficiency precheck; below threshold, they emit a 'insufficient data' report naming the missing inputs.
062 mechanisms

Safety escalation — when we hand off

Some domains require a professional. Our agents recognize that and stop.

  • How it actually works
    A safety-domain classifier gates guide generation; matched topics produce a professional-required card instead of steps.
  • How it actually works
    Per-workspace forbidden-topic lists filter outgoing speech; a sampled fraction of live calls are audited post-hoc against the KB.
Find a claim on this page that isn't true?

Email trust@hi5agents.com. We'll fix the product or fix the page. Every claim is backed by shipped code — the audit trail is the git diff.

Row-level security · BYOKYour keys, your data, your accounts