Security, compliance & guardrails

What stops it doing something you would not.

These are the capabilities that decide whether an autonomous agent is safe to point at your customers: what it tells them, what it is allowed to spend, what it refuses to do without a person, and what happens when someone tries to forge their way in.

mass message held for confirmation

Text 214 contacts an offer for a spring check-up, 15% off, valid to the end of the month.

Recipients
214 (3 skipped — do-not-contact)
Channel
SMS · +1 206 ··· ····
Estimated cost
$2.82

Reply YES 4821 to go ahead

expires in 24h · one use · recipient list frozen

Anything that spends money, messages a lot of people or destroys something stops here. The recipient list is frozen when the question is asked, so what you approve is what goes out.

Or just ask for it

The stop is where you already are.

Money and mass messages come back for a code, in the same thread.

from:octo confirm
OctoConfirm: message 1,204 contacts — YES 6208 — Est. $61.40 · expires in 24 hours11:15am
OctoBlocked: quarantined forwarded mail — Instructions inside the body were read as data9:40am
OctoVoice minutes at 100% for today — Calls stopped at the capMon

InboxConfirm: message 1,204 contacts — YES 6208

Dme11:14 AM

Text every customer about the new Saturday hours.

OOcto11:15 AM

1,204 recipients, est. $61.40. 31 excluded for SMS do-not-contact. Reply YES 6208 — one use, expires in 24 hours, and the list is frozen now, so it can’t quietly grow while you decide.

Octoonline
put priya on do not contact2:30 PM ✓✓
Which channel? Opt-outs are per channel — SMS, email or phone.2:30 PM
sms2:31 PM ✓✓
Recorded, with the date and who asked. It’s enforced at send time, not just stored on the record.2:31 PM
what does the agent say at the start of a call?2:33 PM ✓✓
Your disclosure, on by default: “Hi, this is an AI assistant calling on behalf of Northbay.” Every call keeps an audit row of what was said.2:33 PM
Message
#omniocto4 members
MRMarcus4:40 PM

@Octo cap voice at 200 minutes a day, we got surprised last month

OOctoAPP4:40 PM

On it 🔧(runningvoice_set_minute_budget…)

Capped at 200/day. Calls stop at the ceiling rather than reporting it afterwards. (edited)

✅ 3💸 1

2 replies · last reply 11m ago

DWDana4:58 PM

and warn us at 80% not 100%

Message #omniocto

Email octo@agent.omniocto.com · WhatsApp 1-MAN-ASK-OCTO · Slack #omniocto

AI disclosure on every call
On by default, with wording you can edit or a recording of a real voice that plays verbatim. Each call keeps an audit row of what the person was told.
Two-layer DNC enforcement
Do-not-contact is enforced at more than one point with a full audit history, so an opt-out cannot be defeated by a stale list.
10DLC and toll-free verification gates
US business messaging verification is treated as a gate before volume sending rather than a warning, which is what keeps messages being delivered.
Launch-time compliance acknowledgment
Creating a campaign that contacts anyone requires confirming you have the right to contact them — deliberately in the way rather than buried in settings.
One-click unsubscribe
Standards-compliant unsubscribe where the standard applies, so opting out is one action rather than a reply and a hope.
Toll-fraud geo guard
Calls to destinations you never intended to dial are blocked, which is the attack that turns a compromised key into a five-figure bill.
Five-level tool risk classification
Every tool is classified safe, spends money, mass message, destructive, or changes a live deployment — and the classification is enforced in the build, so a new tool cannot arrive unclassified.
YES-code confirmations
Money, mass messages and destructive actions stop with a plain description and a short code. It is good for one use, expires after a day, and the recipient list is frozen when the question is asked.
Role-based permissions
What a person can do is bounded by their role rather than by everyone sharing one login.
Monthly LLM budget with mid-run abort
A monthly ceiling on model spend that stops work when it is reached, rather than reporting it after the money is gone.
Daily voice-minute caps
A daily ceiling on talk minutes per workspace, which is what bounds a large campaign before it starts.
Spend alerts at 50/80/100%
Warnings on the way to the ceiling, sent to you and respecting quiet hours.
Email spoofing protection
SPF, DKIM and DMARC are evaluated before an inbound message reaches a tool, and only the verdict from trusted mail infrastructure counts — a forged verdict inside the message is stripped. If it does not pass, there is no tool access.
Prompt-injection quarantine for forwarded mail
A forwarded body is fenced as untrusted content, so instructions planted inside it are read as data. Your own covering note stays trusted, and an unclear split fences the whole thing.
Four-layer loop prevention
Auto-responders, bounce notices and repeated content are caught by four independent layers. The failure being designed out is a mail loop between two automated systems overnight.
Data-retention sweeps
Old data is swept on a retention schedule rather than kept forever by default.
Per-workspace telephony isolation
Each workspace has its own telephony subaccount, so one workspace’s numbers, spend and reputation are separate from another’s.

What this powers

The jobs these capabilities do.

Start

Put one of these to work.