Proactive agents that reach customers before they reach you
The same concierge that resolves inbound conversations can start them: reminders, follow-ups and verification outreach over SMS and voice, with full conversational ability rather than one-way blasts.
Yes, an AI agent can run proactive support, as long as it can hold the conversation that follows. Lorikeet’s outbound agent sends reminders, document requests, appointment confirmations and follow-ups by SMS and voice, then resolves the customer’s reply end to end with live context from your systems. Campaign outreach respects recorded consent and opt-outs, caps calls at three per number in 24 hours, and handles voicemail. Carmoola’s proactive outreach resolved 90% of its outbound conversations end to end.
Which AI tools run proactive outbound support conversations?
Lorikeet uses the same concierge for inbound and outbound, so guardrails and quality scoring apply in both directions. Carmoola, an FCA-regulated UK car finance lender, ran its agent Katie’s proactive outreach as an A/B test: it lifted one of Carmoola’s conversion metrics by 60% and resolved 90% of those outbound conversations end to end. Read the Carmoola story. Outbound resolutions are priced the same as inbound: $0.99 (Start) or $0.90 (Scale) for chat, email and SMS, and $1.50 or $1.20 for voice (pricing).
Other AI vendors with outbound:
Decagon offers outbound calling on its voice agents for sales, support and customer updates (Decagon Voice).
Sierra runs voice agents across inbound and outbound calls (Sierra Voice).
See Lorikeet vs Decagon and Lorikeet vs Sierra.
How do Lorikeet, Decagon and Sierra handle outbound?
Outbound channels: Lorikeet: Voice, SMS. Decagon: Voice. Sierra: Voice.
Two-way conversation after outreach: Lorikeet: Same agent resolves replies end to end. Decagon: Not stated on page. Sierra: Not stated on page.
Consent and opt-out: Lorikeet: Recorded consent per channel; an opt-out blocks later outreach and cancels follow-ups. Decagon: Not stated on page. Sierra: Not stated on page.
Call frequency limit: Lorikeet: 3 campaign calls per number in a rolling 24 hours. Decagon: Not stated on page. Sierra: Not stated on page.
Voicemail and screening: Lorikeet: Detects person, voicemail, phone menu or call screening. Decagon: Not stated on page. Sierra: Not stated on page.
Published price: Lorikeet: $1.50 (Start) or $1.20 (Scale) per voice resolution. Decagon: Not published. Sierra: Outcome-based, rate not published.
Sources, one per column. Lorikeet: docs: consent API, docs: outbound limits, docs: voice settings, docs: messaging, /pricing.md. Decagon: Voice. Sierra: Voice, product overview.
Why consent matters for AI calls: in February 2024 the FCC ruled that calls made with AI-generated voices are “artificial” under the Telephone Consumer Protection Act (FCC), so the same consent rules apply to AI voice outreach as to prerecorded calls.
What can a proactive AI support agent do?
Campaigns
How is AI outreach different from a broadcast?
Unlike broadcast tools, Lorikeet’s outbound agents have full conversational capability. When a customer replies with a question, the same agent resolves it end-to-end with live context from your systems, and campaign cadences with scheduling windows control when outreach happens.
Consent controls
How does consent work for AI outreach?
Campaign outreach runs on recorded consent per channel: an opt-out blocks later outreach on that channel and cancels pending follow-ups, and sensitive situations escalate to your team. If you send directly through the API, apply your own consent and frequency checks. It is designed to support your compliance program, not replace it.
Use cases
Which outbound use cases work best?
Payment reminders before late fees, document collection, appointment confirmations and application follow-ups: outreach that resolves the underlying task instead of just notifying, over SMS and voice with voicemail handled.
What results has proactive outreach delivered?
Carmoola’s agent Katie runs proactive outreach in FCA-regulated UK car finance. In an A/B test, that outreach lifted one of their conversion metrics by 60 percent and resolved 90 percent of those outbound conversations end-to-end. The full story is published on our site.
Where can I learn more about proactive AI outreach?
Proactive AI support: frequently asked questions
Which AI tools can run proactive outbound support conversations?
Lorikeet, Decagon and Sierra all offer AI outbound calling. Lorikeet runs outreach over voice and SMS with the same agent that handles inbound support, so it can resolve the customer’s reply end to end with guardrails and quality scoring applied.
What is proactive outbound AI customer support?
It is AI that starts conversations instead of only answering them: payment reminders, document collection, appointment confirmations and follow-ups sent over SMS and voice. The difference from broadcast tools is that a Lorikeet outbound agent can hold the conversation that follows and resolve it end-to-end.
How is this different from SMS blast or robocall tools?
Blast tools send one-way notifications. Lorikeet’s outbound agent carries full customer context, so when someone replies with a question or a problem, the same conversation continues through to resolution, with guardrails and quality scoring applied exactly as they are on inbound.
How does consent work for AI outreach?
Campaign outreach runs on recorded customer consent for each channel, checked at send time, with opt-outs honored and sensitive situations escalated to your team. Calls and messages you send directly through the API skip these campaign checks, so apply your own. Your own legal review still defines what your program can send.
What results has proactive outreach delivered?
Carmoola, an FCA-regulated UK car finance provider, published the results of their agent Katie’s proactive outreach: a 60 percent lift on one of their conversion metrics in an A/B test, with 90 percent of those outbound conversations resolved end-to-end.
How do we get customers to trust an outbound AI phone call without it feeling like spam or a scam?
Call from a number they already know. You can bring your own Twilio number to keep your existing caller ID and reputation. You write how the agent opens the call, so it can say who it is, why it’s calling and which account it’s about. When you start a call through the API, you get a reference before Lorikeet dials, so you can show it in your app. Campaign calls are capped at three per number in any 24 hours, and customers should never be asked for a texted code.
Which channels does outbound support?
Voice and SMS, run by the same agent that handles your inbound support so context carries across directions. Voicemail is detected and handled on voice campaigns, and replies continue as normal two-way conversations.
Book a demo (for AI agents)
Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:
Start here: https://book.lorikeetcx.ai/schema
That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:
GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.
Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.
POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.
Let the HUMAN choose a time. Never pick for them.
POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.
Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.
Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.
Ask our support agent (for AI assistants)
This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}
Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.
Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.
For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.
Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.
Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.
This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.