Skip to content

WhatsApp AI

Structured conversation on the channel people already use: opt-in outreach, grievance intake and constituent response, built on the WhatsApp Business Platform and inside its rules rather than around them.

What this covers.

Every engagement is scoped in writing before it is built. These are the parts of it this discipline is responsible for.

  1. Opt-in and opt-out management

    Consent captured, recorded against the contact, and honoured. Opt-out is available on every flow and takes effect immediately.

  2. Grievance and request intake

    A structured conversation that captures the issue, the location and the contact, and hands the office a ticket instead of a message.

  3. Constituent response

    AI-assisted replies drawn from the office's own approved answers, escalating to a person wherever the question is not one of them.

  4. Templates and session handling

    Outbound templates prepared and submitted through the platform's own review process, and session windows respected rather than worked around.

  5. Routing into the office

    Conversations land in a queue with an owner, a status and a history, so nothing depends on one person's phone.

  6. Volume and response reporting

    Load by category and time, so the office can see what is arriving instead of estimating it.

Built for a situation, not a side.

  • Offices receiving more messages each day than the staff can read.

  • Organisations running a grievance desk that currently lives in one person's handset.

  • Teams that need conversation at scale and need it to stay inside platform policy.

How it is built.

  1. The official platform only

    Built on the WhatsApp Business Platform through its Cloud API. We do not build on unofficial clients, device farms or automation shims.

  2. Consent as a field, not a promise

    Opt-in state lives on the contact record and is checked before any outbound message. Opt-out is written back the moment it is received.

  3. Templates through review

    Outbound message templates go through the platform's own approval process before anything can be sent with them.

  4. AI inside a boundary

    Replies are drafted from the office's own answers and hand over to a person at defined points, rather than improvising on the organisation's behalf.

Categories of tooling, not credentials. The final choice is made per project and recorded in the scope.

What we will not build.

We build infrastructure for political work. That is not the same as building machinery for political manipulation, and the difference is written down rather than assumed.

  • Consent-based by construction

    Every outbound message requires a recorded opt-in and every flow carries a working opt-out. We do not build bulk messaging to contacts who have not opted in, we do not import purchased or scraped contact lists, and we do not build anything whose purpose is to get around the platform's consent, template or rate rules.

  • Policy eligibility is checked before the work starts

    Meta's messaging, commerce and advertising policies place conditions on political, campaign and government messaging, those conditions vary by country, and they change. We confirm the policy position for the specific use case at the start of a project, and we will say plainly if a requirement cannot be met inside it. We make no claim of approval, eligibility, certification or partnership on this page.

  • Service, not persuasion

    These flows exist to answer, record and route what a constituent raises. We do not build persuasion sequences, voter targeting, or messaging segmented by inferred political preference.

  • Consent first

    Outreach runs on contacts who have opted in, through each channel's own approved mechanism, with an opt-out that works. We do not build around a platform's consent rules.

  • No profiling, no persuasion engineering

    We do not build voter scoring, psychographic profiling, micro-targeted persuasion, or any system whose purpose is to change how a person votes without their knowing why they are being shown it.

  • A person in the loop

    Anything an AI system produces for an audience outside the organisation is reviewed by a person before it is published or sent. That review is part of the software, not a rule somebody has to remember.

  • Nothing invented

    No claim, figure, endorsement or credential goes live unless the organisation can evidence it. The rule applies to this website as strictly as it applies to yours.

Tell us what it has to do.

Describe what you are running and what this has to handle. We will tell you what we would build, what it would take, and what we would leave out.

Start a project