# Inbound and outbound assistants: campaigns and messaging

> Designing assistants that start conversations as well as answer them: consent and compliance, campaign and mailing design, two-way replies, voice outreach, architecture and the metrics that keep you honest.

Source: https://conversationalaidesign.com/modules/13-inbound-outbound.html. Author: Nelson Abacherli Kawakami. Reviewed October 27, 2026.

## What you will learn
- Distinguish inbound and outbound design problems
- Apply consent, opt-out, timing and identification principles
- Design a campaign: audience, trigger, message, reply handling and handoff
- Add guardrails to AI-written mailings and messages
- Measure outbound programs with outcome and complaint metrics


> **Not legal advice**
> Messaging, calling and email rules differ by country, channel and industry, and they change. This module explains design principles and examples of what exists. Confirm requirements for your markets with qualified counsel and your channel providers before you launch.

## Inbound and outbound are different problems

An **inbound** assistant waits for someone who wants something. An **outbound** assistant starts the conversation, which changes almost everything.

| | Inbound | Outbound |
|---|---|---|
| **Who starts** | The customer | You |
| **Permission** | Implied by the request | Must be established and recorded |
| **Attention** | The customer is motivated | You are interrupting |
| **Identity** | Often verified by login | You must reach the right person first |
| **Timing** | Customer's choice | Your choice, and a source of complaints |
| **Context** | What they just said | Your reason for contacting them |
| **Failure cost** | A bad answer | Complaints, opt-outs, fines, brand damage |

Common outbound uses: appointment and delivery reminders, payment and renewal notices, onboarding nudges, surveys, alerts, re-engagement, and campaigns or mailings across email, SMS, messaging apps, push notifications and voice.

## Consent and compliance principles

The details vary, but the principles are consistent:

- **Get consent and keep a record** of when, how and for what. Don't assume it.
- **Honor opt-outs instantly and everywhere,** and confirm them. Keep a suppression list that every sender checks.
- **Identify yourself** clearly: who is contacting, and why.
- **Respect timing:** local time zones, quiet hours and frequency caps.
- **Disclose automation** where required or expected, and never present a bot as a person.
- **Stay within the channel's rules.** For example, business-initiated messaging on some platforms uses pre-approved templates, and bulk text messaging may need sender registration. Check each provider's current policy.
- **Authenticate email** (for example with SPF, DKIM and DMARC), include a working unsubscribe, and keep lists clean.
- **Don't reveal personal information** before verifying you have the right person.

Examples of laws and rules that may apply include the US Telephone Consumer Protection Act and CAN-SPAM, EU data-protection and e-privacy rules, Brazil's LGPD and Canada's CASL, plus industry-specific rules. In 2024 the US FCC confirmed that AI-generated voices count as "artificial" voices under the TCPA, which is covered in the case study.

> **A case you should read**
> The FCC ruling on AI voices in robocalls changed what outbound voice teams in the United States must plan for: consent first. See the case study.

## Designing a campaign

- Audience and consent → Trigger or schedule → Message and channel → Delivery and throttling → Replies handled by the assistant → Handoff or resolution → Measurement and suppression

1. **Audience.** Segment by need and consent. Exclude anyone who opted out, was contacted recently or is in an active support case.
2. **Trigger.** Event-based (an order shipped, a bill is due) usually outperforms and annoys less than blast schedules.
3. **Message.** Identify yourself, give the reason, offer value, and ask for one clear action. Make opting out easy.
4. **Channel.** Pick the one the customer prefers, and keep sensitive content out of insecure channels.
5. **Throttle.** Send in batches, watch complaints and opt-outs, and stop automatically if they spike.
6. **Replies.** Decide in advance how each reply is handled. Handle keywords (STOP, HELP) deterministically. Send everything else to the assistant, with the campaign context attached.
7. **Measure** outcomes and harms, not only opens and clicks.

**An outbound reminder that earns the conversation**
> **Bot:** Hi Ana, this is the Northline Rail assistant. Your trip to Lisbon leaves tomorrow at 09:10. Want your boarding pass sent here, or would you like to change anything? Reply STOP to opt out.
> **User:** Can I move it to the afternoon?
> **Bot:** Yes, your fare allows one free change. Seats are open at 14:30 and 17:40. Which would you like? I'll confirm before I change anything.

Notice that the reply moves straight into the inbound assistant, with the booking already known.

## Mailings and AI-written content

AI can personalize at scale, which raises the stakes for control:

- **Approved building blocks.** The model fills slots in approved templates and claims, rather than inventing offers, prices or promises.
- **Guardrails on content** (module 10): no invented discounts, no unapproved claims, brand and tone rules, required legal text and unsubscribe links.
- **Human approval** for campaigns, with samples reviewed across segments and languages.
- **Preview and test sends,** including rendering in common email clients.
- **Logging:** keep the prompt version, the data used and the final text sent.

## Voice outreach specifics

- **Identify yourself** immediately, state the purpose, and make it easy to stop.
- **Wrong person.** Plan the script when someone else answers or the person is unavailable.
- **Verify before disclosing** anything personal.
- **Voicemail and answering machines.** Decide whether to leave a message and what it may contain.
- **Call windows and retry cadence** respect local time and limits.
- **Recording and disclosure** follow the rules of each region. See module 19 and module 20 for the speech side.

## Architecture

- Consent and preference service → Campaign engine → Messaging gateways: SMS, messaging apps, email, voice, push → Conversation service and assistant → CRM and support systems → Analytics

A pre-send check is a small, high-value guardrail:

```python
from datetime import datetime
from zoneinfo import ZoneInfo

def can_send(contact: dict, message: dict, now_utc: datetime, recent_count: int) -> tuple[bool, str]:
    """Decide whether a message may go out right now."""
    if not contact.get("consent", {}).get(message["channel"]):
        return False, "no consent for this channel"
    if contact.get("opted_out"):
        return False, "opted out"
    if not message.get("template_approved"):
        return False, "template not approved"
    local = now_utc.astimezone(ZoneInfo(contact["timezone"]))
    if not (9 <= local.hour < 20):                  # example quiet-hours window; set from your rules
        return False, "outside allowed hours"
    if recent_count >= message.get("max_per_week", 2):
        return False, "frequency cap reached"
    return True, "ok"
```

Log every decision, including the reason a message was held. That log is part of your compliance record.

## Measure outcomes and harms

| Metric | Why |
|---|---|
| Delivery and bounce rate | Technical health and list quality |
| Reply rate and reply sentiment | Whether the message was welcome |
| **Opt-out and complaint rate** | The early warning. Set automatic stop thresholds |
| Conversion or task completion | The outcome you wanted |
| Resolution of resulting conversations | Whether the follow-up worked (module 17) |
| Cost per successful outcome | Includes human follow-up |

Open and click rates are increasingly unreliable signals, so weight replies, outcomes and complaints more heavily. And always attach **guardrail metrics** to experiments: a campaign that raises conversions while doubling opt-outs is not a win.


## Key takeaways
- Outbound starts without an invitation, so consent and value must come first.
- Make opting out instant and honored everywhere.
- Every outbound message is the start of an inbound conversation: plan for the reply.
- Rules vary by country and channel, so check them with qualified advisors before launch.

## Sources
- Case study: FCC ruling on AI voices in robocalls: https://conversationalaidesign.com/case-studies/fcc-ai-voice-robocalls.html
- The Register: FCC says AI robocalls are illegal: https://www.theregister.com/2024/02/08/sorry_scammers_the_fcc_says/
- Cooley: FCC AI-generated robocalls under the TCPA: https://cooley.com/news/insight/2024/2024-02-15-fcc-ai-generated-robocalls-illegal-under-the-tcpa