Conversational Revenue Orchestration for non-profits, NGOs and charitable trusts

Build, deploy and manage AI agents that answer supporters and act in your systems, so the person who reads your appeal at eleven at night becomes a first gift, a monthly donor, a volunteer on the rota, and someone who hears what their gift did.

Book a demo
Live orchestration · 10:42:07
Channels · today
WhatsApp
Voice
SMS / RCS
Instagram
Messenger
Email
Web chat
L
Lantern Foundation
Zigment agent
    Your systems
    Donor CRM
    Donation platform
    Volunteer calendars
    Email and SMS tools
    Ad platforms
    Approved content

    Zigment is the agentic orchestration layer that non-profits and NGOs use to build, deploy and manage AI agents. Powered by the Conversation Graph.

    Running in production for humanitarian relief and charity trust
    Hope For UkraineBBB Wise Giving AllianceHope For UkraineBBB Wise Giving AllianceHope For UkraineBBB Wise Giving AllianceHope For UkraineBBB Wise Giving AllianceHope For UkraineBBB Wise Giving AllianceHope For UkraineBBB Wise Giving Alliance

    Silos between your customers and your systems.

    A bot here, a voice provider there, marketing in another tool, and people updating the CRM and tickets by hand.

    Your Systems
    • Donor CRM
    • Donation Platform
    • Volunteer Calendars
    • Email · SMS Tools
    • Ad Platforms
    • Approved Content
    • Donation Forms
    • Chatbot Vendor
    • Telecalling Agency
    • Email Newsletters
    • Volunteer Spreadsheets
    • Helpline Inbox
    • Receipt Scripts
    • CRM Updates
    • Data Syncs
    • Manual Follow-ups
    Zigment Orchestration Layer+ Conversation Graph
    Supporter Touchpoints
    • WhatsApp
    • Voice
    • SMS / RCS
    • Instagram
    • Messenger
    • Email
    • Web chat

    Built for the trust your supporters place in you.

    Certified and audited before a single conversation goes live, and deployed where your team needs it: Zigment cloud, your own cloud, or your data centre. The agent answers only from content you have approved. When the answer is not there, it says so and hands over to a person, and every refusal is logged with the rule that produced it.

    • Model agnostic · Zigment inference or your own cloud
    • AES-256 at rest · TLS 1.2 or higher in transit
    • Role based access with complete audit logs
    Approved content onlyImpact answers come from what your team has signed off, and a gap is handed over
    Residency you configureZigment cloud, your VPC or on-prem, on your model
    Never trained on your dataYour donor database stays yours, audit logs included
    Certified and audited
    • ISO/IEC 27001
    • SOC 2
    • GDPR

    From the first click to the impact update nobody has time to send, your agents run the work.

    The first gift, monthly giving, volunteering, help for the people you serve and the updates after it, on the channel each person already uses, with the context from one stage carried into the next.

      • Click to WhatsApp appeals

        The agent answers the moment an appeal ad is tapped, in the supporter's own language, and writes it to your donor CRM.Appeal ad taps become real conversations, written to your donor CRM.

      • Website and social agents

        One agent across your website, Instagram and Facebook, answering where the money goes before the visitor leaves.One agent across web and social, answering before the visitor leaves.

      • Late-night questions

        The story moved them at eleven at night. The agent answers then, while they still care, and keeps the thread open.Every late-night question answered while the supporter still cares.

      • The questions that decide a gift

        Where the money goes, the impact story, the tax receipt and the monthly option, answered from your approved content.Where it goes, the receipt and the monthly option, from approved content.

      • Donation links in the chat

        A secure link from your donation platform, sent when the supporter is ready and confirmed in the same conversation.A secure donation link, sent and confirmed in the same conversation.

      • Receipts on time

        The receipt goes out by email the moment the gift clears, and the gift is written to the supporter's record.Receipts sent the moment a gift clears, and logged on the record.

      • Monthly giving

        After a first gift, the agent offers the monthly option at the right moment and sets it up on your donation platform.Offers monthly giving at the right moment, and sets it up for them.

      • Failed payments and lapsed donors

        When a monthly gift stops, the agent asks why, kindly, and sends a new link if the supporter wants one.Asks kindly when a monthly gift stops, and sends a new link.

      • Major-gift signals

        The major prospect goes to the right development officer, with the impact area and the last question attached.Routes major-gift prospects to an officer, with the context attached.

      • Volunteer sign-up

        The agent explains what volunteering involves, takes the details your team needs and sends them to the right programme.Explains what's involved and signs volunteers up to the right programme.

      • Shifts and reminders

        Open shifts from your volunteer calendar, a reminder the day before, and a dropped slot offered to the next person.Books shifts from your calendar, reminds, and refills dropped slots.

      • Helpline and beneficiary support

        People looking for help are answered from approved content in their language, and handed to your team when needed.Points people to help in their language, and hands over when needed.

      • Thank-yous and impact updates

        The thank-you, the photo from the field and the impact update arrive on the same thread the supporter gave on.Thank-yous and impact updates on the thread the supporter gave on.

      • The next appeal, in context

        The next appeal is a message built from the supporter's own history, sent on the channel they actually reply on.The next appeal built from their own history, on their own channel.

      • Handover with the whole thread

        When a supporter needs a person, the agent hands over the entire thread, so nobody tells their story twice.Hands over the full thread, so no one tells their story twice.

    Proven for missions that run around the clock.

    Humanitarian relief · supporter questions on the website

    A humanitarian non-profit working through an active war chose one surface, its website, and did it properly: an agent built on approved content, with human oversight from day one.10 hrsa week returned to the team18languages, met at the moment of intent15%of conversations in a language other than English

    Hope For Ukraine case study

    Every conversation makes the next one smarter.

    One memory per supporter, shared across every channel and every system you run. Every message, gift and appeal sits on one timeline, so the agent in August opens with what it learned in March.

    S
    Supporter Sample supporter
    Supporter since
    2 Mar
    Mumbai
    Hindi and English
    Gives monthly
    Prefers
    WhatsApp, evenings
    Today
    AdWhatsAppIn personYour systems
    One memory per supporterEvery message, gift, shift and appeal on one continuous timeline, with the source of each fact kept against it.
    Context that travelsThe conversation follows the supporter across every channel, and the officer or coordinator who steps in opens with the whole thread.
    Signal back to your stackIntent and gift signal flow into your donor CRM as structured, usable data, and conversions go back to your ad platforms.
    Explore the Conversation Graph

    Every answer traceable to the content and rule behind it.

    Your team can read any transcript, trace any answer back to the approved content it came from and the rule that fired, see every point where the agent handed a supporter to a person, and change what it does next without waiting for a release.

    Reports/All programmes · last 14 daysSample workspace
    Conversations answered3,240at any hour
    First gifts418given in the chat
    Monthly gifts restarted96after a failed payment
    QA score95 / 100auto-scored, every chat
    Conversations and gifts, by dayconversations gifts
    30 Sep6 Oct13 Oct
    Handovers · to a person Every one logged
    H
    Asked for help with a case · routed to programmes
    164
    A
    Answer not in approved content · said so, handed over
    118
    QA review · auto-scored
    Monthly gift restart97
    Volunteer sign-up96
    Helpline enquiryneeds a person · routed to the helpline team72

    Every conversation scored

    Against your QA rubric, every one of them, where a team could only read a handful by hand.

    Every handover logged

    Each time the agent passed a supporter to a person, with the rule that fired and what it said.

    Built and changed by your team

    New appeals, languages and programmes added in the studio, and deployed when you are ready.

    One agent, on every channel and every system you already run.

    Nothing is replaced. The agents read from and write back to the systems your team already works in, on the channels your supporters already use.

    CHANNELS · plus any channel with an API
    WhatsAppWhatsApp
    Voice, in and out
    Google MessagesRCS
    SMS
    GmailEmail
    InstagramInstagram and Messenger
    GoogleGoogle Business
    Web chat
    In-app
    Works with the stack you already run · and your own APIs as private apps
    Donor CRMSalesforceSalesforceHubSpotHubSpotZoho CRMZoho CRMgifts, intent and the whole thread written back
    Donations and paymentsRazorpayRazorpayUPI AutoPayAutoPayPayUone-time links and monthly mandates
    Email and SMS toolsYour email toolreceipts, thank-yous and impact updates
    Volunteer calendarsYour volunteer calendarshifts, reminders and freed slots
    Ad platformsMetaMetaGoogleGoogleconversions written back
    Approved contentImpact reports and FAQsthe only source the agent answers from
    See all integrations