Start the conversation

Outbound SMS that knows when to stop.

Six steps between receiving a message and sending one back. The AI reads the full conversation, decides what to say, and decides when to end. The code doesn't second-guess it.

Book a discovery call

6 stepsreceive → compliance → context → AI → save → send

320 charshard limit enforced in code, not left to the AI

2 providersTwilio primary, Guni secondary — switchable per campaign

0 double sendsidempotent pipeline — MessageSid checked before every send

How it works

Every message runs the same six-step pipeline.

Inbound webhooks validate, enqueue, and return 200 OK immediately. The pipeline runs asynchronously — so burst traffic from a large campaign doesn't stack up behind slow AI calls.

Twilio webhook validates the request and writes to the message queue
Worker picks up the job and runs compliance before touching the AI
Context assembled fresh on every turn — full conversation history included
AI reads everything and returns a typed response with directive and reasoning
Turn persisted to the database before the outbound send fires
Send failure triggers automatic retry — 60s, then 300s, then flags for review

Message pipeline

1
Receive
Twilio webhook → message queue → 200 OK
2
Compliance check
Opt-out, time windows, frequency — before any AI call
3
Assemble context
Campaign config + full conversation history injected
4
AI call
Claude returns directive, message, reasoning, confidence
5
Persist turn
Written to DB before send — idempotent by MessageSid
6
Send
Outbound via Twilio or Guni — retry on failure

Built-in compliance

Compliance runs before the AI. Every time.

Opt-outs, time windows, and frequency limits are enforced in code — not left to the AI's judgment. The AI never receives a message that compliance has already handled.

Zero false negatives on opt-outs.

Hard opt-out keywords — STOP, UNSUBSCRIBE, CANCEL, and common variants — are matched using word-boundary-aware logic to avoid false positives on words like "stopping by".

Opt-out flag set permanently — never overwritten by reimport
7-day silence window and 30-day opt-out window enforced automatically
Every compliance check — pass or intercept — written to the audit log
Opted-out contacts cannot be re-added without explicit operator action

Compliance checks per message

Opt-out keyword scan — STOP, UNSUBSCRIBE, CANCEL + variants
Contact opt-out flag — permanent record checked before every message
7-day silence window — closes conversations with no activity
30-day messaging window — blocks non-opt-out messages after expiry
Frequency cap — bump intervals enforced per campaign config
Audit row — every check logged with outcome and timestamp

Bump scheduling

Follow-ups that know when to give up.

Bump intervals are configured per campaign as an array of minimum hours between touches. The scheduler derives the maximum number of bumps from the array length — no separate cap to manage.

Configurable intervals

Each campaign defines its own bump_intervals array — for example [24, 48, 96] means bump after 1 day, then 2 days, then 4 days. The platform enforces minimum hours between each touch.

How it works: How it works: max_bumps is derived from array length. A 3-item array means 3 bumps maximum — no separate field to keep in sync.

Business hours enforcement

Bumps only fire within configured business hours and timezone. The scheduler checks eligibility before enqueuing — contacts are never messaged at 2am because a job happened to run then.

How it works: Timezone-aware: multi-segment hour strings supported. Configure different windows for weekdays and weekends per campaign.

Burst traffic handling

All scheduler eligibility queries use FOR UPDATE SKIP LOCKED — multiple workers can run simultaneously without processing the same conversation twice, even under heavy load.

How it works: Queue-backed: Redis + RQ absorbs burst traffic. Worker restarts don't lose queued jobs — all state is persisted in PostgreSQL.

Automatic retry on failure

If an outbound send fails, the platform retries at 60 seconds, then 300 seconds. After three failed attempts, the turn is flagged for operator review — no silent failures.

How it works: Idempotent by design: MessageSid is checked before every send. A recovered worker can never send the same message twice.

Ready to run your first
outbound campaign?

One campaign. One contact list. We'll have you sending in days, not weeks.