AI Agent
One agent for one job, wired to your channels and data.
From $8,000
- Agent with tools and retrieval
- Eval suite in CI
- Review console and hand-off to a person
A deposit, then billed by milestone.
Services
We build AI agents that answer customers, take orders and bookings, qualify leads and hand the conversation to a person when they should. Each agent works from your catalog, prices and policies, and passes its evals before it talks to a customer.
We read real conversations and write down what the agent handles, what it never does and when it hands off to a person.
Tools for your catalog, calendar or CRM, and retrieval over your documents, so every answer has a source.
Graded test cases from your conversations, with a pass threshold. They run in CI on every change, and again when the model or the prompt changes.
A first group of real customers, a console to review conversations and hand-offs, and a second provider that takes over if the main model is down.
One agent for one job, wired to your channels and data.
From $8,000
A deposit, then billed by milestone.
WhatsApp, through Meta's official WhatsApp Cloud API, and a chat widget on your website. Other channels are scoped per project.
It is built to answer only from your data and to hand the conversation to a person, with the context, when it can't. The evals test exactly those cases.
Before launch it has to pass a set of graded cases taken from your real conversations. The set runs on every change, and the agent stays off until it meets the threshold we agree with you.
Claude, from Anthropic, by default. A second provider takes over when the first one fails, so a model outage doesn't stop your customers.
The AI Agent engagement starts from $8,000, and the proposal fixes the price of each milestone. Model usage and WhatsApp messaging fees are billed by those providers to your own accounts.
How an agent runs on your own WhatsApp Business number, what Meta bills and what we build.
The home page of this site replays a pull request: spec, plan, changes, tests, deploy. This guide walks through that pull request, the one that added AI triage of new leads, and what a person did at each step while agents wrote the code.
A chatbot follows a menu someone wrote. An AI agent reads what the customer wrote and looks up the answer. Both run on WhatsApp, both have a place, and the right one depends on what your customers ask.
A demo shows the answers someone picked. Evals are graded test cases with a pass threshold, and an agent stays off until it meets it. This is how we write them, with the evals behind this site's own lead triage as the example.
These are the four steps we follow to build an AI agent on WhatsApp, with what Meta's platform asks for at each one. It's written for the person who decides whether to build one, with enough detail for the engineer who will.
Building an AI agent with us starts from $8,000, at a fixed price per milestone. Running it costs model usage and channel fees, billed by those providers to your own accounts. This guide explains what moves both, and what to ask any team before you hire them.
iOS and Android apps from one codebase, with the API and admin behind them.
Multi-tenant platforms, portals, dashboards and admins, with auth, roles and billing.
Pipelines, integrations and reconciliations that add up to the cent.
The spec, the reviews, the tests and the evals behind every service.
A person reads every brief and replies with questions or a first plan.
On this site
The lead triage on this site has 31 graded cases and has to pass 90% of them before it's turned on.