Official WhatsApp Cloud API · on your own Meta account

AI agents that do the work, not just answer

Most AI agents only talk. They sound helpful and leave your team with exactly the same amount of work, because nothing was written anywhere. I build agents that book the appointment, create the lead, issue the payment link, update the order, and hand off to a person when they should. Whatever the job, on the channels your customers already use, writing into the CRM you already run.

Fixed scope, fixed price You own the accounts Audit log of every decision
conversation 4f8c · decision trail
sample

customer

"can you move my Thursday appointment to 4pm?"

policy engine

allowed

reschedule · within_business_hours · slot_free

write

201 · 340 ms

PATCH /appointments/8812 → your calendar

agent

"Moved to Thursday at 4pm. You'll get a reminder an hour before."

if the write had failed

the agent says so and hands off. It never returns a confirmation for something that did not happen.

Every line above is persisted: input, output, duration, rule applied.

Where this fits

Tell me the systems it touches and we build it

The channel, the industry and the process are yours to choose. Three ways this usually starts:

You know the systems

The agent reads and writes in tools you already run, and those tools have API docs you can link to. Pick a tier below and we start this week.

?

Nobody knows yet

Perfectly normal, and it is what the Audit is for. In five days I map what your stack can actually do, and the fee comes off the build.

You only need answers

Hours, address, prices and nothing written anywhere? Meta's own business agent does that for almost nothing. I will show you how to set it up and charge you nothing for it.

Three shapes

Same engine, three jobs

An agent is worth paying for when it makes something happen: finds the right answer inside your own material, writes the line into your system, or closes the customer's request without going through anyone. Who it works for is your call.

A

For your own team

An agent over the company's own material, in its own panel or inside the app you already run. It searches your documents, answers with the source cited, and each person sees only what they are allowed to see. Contracts, manuals, procedures, precedent, account history.

B

To run the operation from inside

It executes and records: books, confirms, charges, updates the order, writes into the CRM, the ERP or the spreadsheet. If the system refuses the operation, it escalates instead of reporting that it worked.

C

To serve your customer on their channel

WhatsApp, website or phone, wired to the rest of the operation. On WhatsApp it runs on Meta's official Cloud API, on your own number, because an unofficial connection gets the number banned and the ban has no appeal.

What I build

Built around your process, not a template

These are the shapes that come up most. If yours is not here, tell me which systems it would write into and we will build that one.

Booking and scheduling

Checks real availability in your calendar, writes the appointment, sends reminders, cuts no-shows.

Try it live

Lead qualification and routing

Asks the right questions, scores the lead, creates it in your CRM and routes the hot ones to the right person.

Quotes inside your rules

Proposes only what your pricing policy allows. It never invents a discount, because it is not the one deciding.

Orders and post-sale

Status, tracking, exchanges and the second purchase, reading and writing in your commerce backend.

Payment links and collections

Issues the charge, follows up on the agreed date, records the promise to pay.

Support triage

Resolves what it can, opens the ticket for what it cannot, and escalates with the full context attached.

Live demo, no signup

Don't take my word for it. Ask the agent to move an appointment.

A fictional clinic whose ERP is published alongside it. You talk, the row changes in the schedule live, and the decision log shows which rule decided each step. Ask for a last-minute cancellation and watch it refuse. Hit the button that takes the ERP down and watch it escalate instead of inventing a confirmation. That last one is the part nobody demos.

Channels and systems

Your channels, your CRM, your rules

The channel is a setting, not a product. The same agent answers wherever your customer already is and writes into whatever you already run. Multiple channels share one memory, so nobody has to repeat themselves after switching.

Where it answers

  • WhatsApp on the official Cloud API. Set up on your own Meta Business account, on your own number. In most cases Meta's Coexistence flow keeps the number and the history you already have. Never through Baileys, Evolution in QR mode, WPPConnect or Z-API, not even on request.
  • Website widget, on your domain, with the same memory as the other channels.
  • Instagram Direct, on the official API.
  • An internal panel or a screen inside the app you already have, when the agent is for staff and not for customers.
  • A ringing phone is a separate project, my AI Voice Agent. Understanding a voice message a customer sends is included here from Standard up.

What it writes into

  • The CRM you already use. HubSpot, Pipedrive, GoHighLevel, Salesforce, RD Station, Airtable, or the one nobody outside your company has heard of.
  • Calendars and scheduling, checking real availability before it promises a slot.
  • ERP, commerce backend, field service, ticketing, or the spreadsheet that is honestly running the process today.
  • Payments and billing, issuing the charge and recording the promise to pay.

The brand does not decide whether I can build it. One thing does: the system exposes a documented API you can link me to. If it does not, the Audit is the honest starting point, and I say so before you pay for a build.

In every build

The six things that are never optional

These are not tier features. They ship in the cheapest build for the same reason they ship in the most expensive one: without them, an agent that acts is a liability rather than an asset.

The decision sits outside the model

A deterministic engine built from your written rules decides what is allowed. The language model only phrases the answer it was authorized to give.

Auditable log of every step

Every decision is stored with the id of the rule that produced it and the version of the policy in force. Months later you can still prove what decided what.

Confirmation before it writes

An operation that changes data runs only after the person confirmed that specific operation. No silent writes.

A spend ceiling per conversation and per day

With an alert before it is reached and a kill switch that belongs to you, not to me.

The provider accounts are yours

Your keys, your invoice, direct from Meta and the AI providers. I never resell usage with a margin hidden inside it.

Honest escalation

If your system is down, the agent says it could not do it and calls a person, instead of confirming something that never happened.

Pricing

Priced by what the agent touches

Not by how many messages it sends. The number that moves the price is how many of your systems it writes into, because that is where the work actually is.

Starter

One process, one system, one channel.

$1,450

Delivered in 10 days · 2 revisions

  • Writes into 1 system
  • 1 automated process
  • 1 channel
  • Keyword handoff to a human
  • Audit log of every decision
  • 7 days of post-launch support
Start with Starter
Most projects

Standard

Several processes, a decision engine, two channels.

$3,900

Delivered in 21 days · 4 revisions

  • Writes into 3 systems
  • 3 automated processes
  • Rule-based decision engine
  • 2 channels, one shared memory
  • Knowledge base
  • Understands voice messages
  • Recorded test suite delivered
  • 14 days of post-launch support
Start with Standard

Advanced

Custom policy engine, multichannel, self-hosted option.

$8,500

Delivered in 35 days · unlimited revisions for 30 days

  • Writes into 6 systems
  • Unlimited automated processes
  • Custom policy engine built from your written rules
  • Multichannel with multi-agent routing
  • Cost per conversation reporting
  • Self-hosted delivery and license
  • 30 days of post-launch support
Start with Advanced

Not sure what is possible? Start with the Audit

$390

Five days. I map your processes, test whether your systems can actually be written to, and send back a scope with a fixed price. If the honest answer is that you do not need to hire anyone, that is what the report will say. The fee comes off any build you buy afterwards.

Start with the Audit

Running costs are yours. Meta, AI providers and telephony bill you directly on your own accounts, with your own keys. I never resell usage. A typical small business spends $15 to $50 a month.

Live phone calls are a different project. Understanding a recorded voice message is included from Standard up. An agent that answers a ringing phone is my AI Phone Receptionist, priced separately.

A revision is a change inside the delivered scope. Tone, wording, behaviour fixes. A new flow, integration or channel is a scope change and gets its own quote.

Multi-agent

When one agent stops being enough

Push everything into a single agent with twenty tools and a giant prompt and three things get worse together: it picks the wrong tool more often, cost per task climbs as context grows, and you lose the ability to tell where an answer went wrong. Splitting it fixes that and creates a new problem, coordination. So here the coordination is deterministic code, not one more model deciding.

01

Coordinator with specialists

An orchestrator decides which specialist handles which part, in what order, and merges the result. Each specialist holds few tools and one narrow goal, which is what makes the right choice predictable.

02

Panel of perspectives

Several agents examine the same thing from different angles and the result only passes with enough agreement. Worth the extra cost when being wrong is expensive.

03

Producer and verifier

One agent produces, another is instructed to distrust it and try to knock the claim down. What survives becomes the answer. This is what kills the plausible and wrong reply.

04

Stages with a human gate

Where the decision is sensitive, the flow stops and waits for a person to approve, with everything done so far on the screen.

What holds it together

  • An explicit state machine. An undeclared transition raises an error instead of passing as model creativity.
  • A ceiling per stage and per run, because in multi-agent the cost multiplies quietly.
  • An iteration limit, so a disagreement between agents cannot become an infinite loop you pay for.
  • Tool isolation: each agent sees only the functions in its own scope, typed and declared.
  • Predictable degradation: if a specialist fails, the coordinator either continues without it or stops, and tells you which of the two it did.

The honest warning

Multi-agent is slower and more expensive than a single agent. If your problem fits one agent with four tools, that is what I will recommend, even though it is the smaller contract.

The question that decides is not how many agents. It is how many independent decisions the process contains. Two decisions do not justify four agents.

Multi-agent routing ships in the Advanced tier.

Process

How a build actually runs

  1. 1

    Kickoff

    I read your answers and your sample conversations, then send back a flow map and the decision rules in writing. Nothing gets built before you approve that.

  2. 2

    Connection

    The channel goes live. On WhatsApp that means your number registered on your own Meta Business account, with templates submitted for approval. The account is yours from that moment on.

  3. 3

    Integration, before anything else

    I prove read and write against your sandbox before a single flow is built. This is the step where projects like this fail, so it goes first, while there is still time to change course.

  4. 4

    Build and test

    Flows, decision rules and guardrails. You get a test channel early. Then a recorded conversation suite plus abuse tests, with the results shared, not summarised.

  5. 5

    Launch

    Gradual volume ramp-up while your messaging limits climb, monitoring in place, and a kill switch you control. Handover call plus written documentation.

Boundaries

What I do not do

Saying this up front costs me some enquiries and saves both of us the wrong project.

No unofficial WhatsApp libraries. Not even if you ask.

Baileys, Evolution in QR mode, WPPConnect, Venom, Z-API. Meta has been removing these connections since January 2026 and the ban is permanent with no appeal. The number is your asset, not mine, so I will not put it at that risk to save you a hosting fee.

The agent never decides a discount, a deadline or a policy.

A deterministic engine built from your written rules decides what is allowed. The language model only phrases the answer it was authorised to give. Anything outside policy is blocked before it is sent. That is what keeps this defensible when a customer disputes what your agent said.

I cannot recover a banned number.

Bans for unauthorised API use are permanent and there is no effective appeal. Anyone promising recovery is not being honest with you. What I can do is get you operational on a new number, properly, fast.

I do not build FAQ-only bots.

If the agent only answers questions and writes nothing anywhere, Meta's own business agent already does that for almost nothing. I will show you how to set it up and charge you nothing for the advice.

FAQ

Common questions

Will my number get banned?+

Not through me. Everything on WhatsApp runs on Meta's official Cloud API. Bans happen to businesses using unofficial libraries. I never use those for client work.

Can I keep my current number and history?+

In most cases yes, through Meta's Coexistence flow. Tell me the number when you start and I confirm eligibility before you are committed to anything.

Who owns the accounts?+

You do, from day one. Your Meta Business account, your number, your provider keys. If you stop working with me, nothing switches off and nothing has to be migrated.

Does it have to be WhatsApp?+

No. WhatsApp, a website widget, Instagram or voice. The agent is the same and the channel is a setting. Multiple channels share one memory, so your customer never repeats themselves.

Can it make decisions like discounts or eligibility?+

It executes decisions, it does not invent them. Those come from a deterministic engine built from your written policy, and the agent only phrases the answer it was authorised to give.

What does it cost to run each month?+

Platform and AI providers bill you directly, on your own accounts. A typical small business spends $15 to $50 a month. Note that since October 1, 2026 WhatsApp service messages carry a per-message fee, and I design your flows with that in mind.

What if my CRM has no API?+

Then we start with the Audit instead of a fixed-price build. I map what is possible, including the workarounds worth doing, and the fee comes off whatever we build next.

What happens after delivery?+

Most clients move to a monthly retainer for tuning, new flows and monitoring. That is a separate agreement and is never bundled into the build price without you asking for it.

Tell me what should happen automatically

Pick a tier and answer six questions about your systems. The form reads your answers and tells you which tier they actually support before you pay for anything.