Applied AI for businessBrazil2 slots a month

Your first AI agent in production in 45 days. Or we keep working for free.

Custom AI agents that answer customers, sell and book appointments on WhatsApp — and take the repetitive work off your back office. Built by a team with 15+ years of putting software into production. Tested before launch. Measured after.

Mechanism, not magic

This is what actually runs. Not a slide deck.

Every decision the agent makes leaves a record: what it understood, which tool it called, what it answered. That's how you audit it, measure it and make it better.

Simulation of a BYIA conversation · fictional data

agent://front-desk · demo-clinicsimulation
09:41:02 whatsapp ← "hi, can I see dr. paula on thursday?"
09:41:02 classify → intent=booking confidence=0.97
09:41:03 tool.call  calendar.find_slots(provider="paula", day="thu")
09:41:03 → 3 open slots: 9:30am · 2:00pm · 4:30pm
09:41:03 tool.call  patients.lookup(phone="+55 62 ····")
09:41:04 → returning patient · insurance active
09:41:04 whatsapp → "Hi Marina! On Thursday I have 9:30am, 2pm or 4:30pm. Which works best?"
09:41:31 whatsapp ← "2pm"
09:41:32 tool.call  calendar.book(slot="thu 2:00pm")
09:41:32 tool.call  reminders.schedule(-24h, -2h)
09:41:33 ✓ appointment confirmed · no human needed
response time
1.4s
tools called
4
human needed
no

The cost of doing nothing

While you read this, someone messaged your company on WhatsApp. They're still waiting.

  1. The 10pm customer

    They asked for a quote after hours. Nobody answered. By morning, they'd signed with whoever replied first.

  2. The pilot that died on a slide

    Everyone has built an AI demo. Almost no one has put one into production, with integrations, metrics and an owner. Demos don't pay the bills.

  3. The team fighting fires

    Expensive people copying data from one system to another and answering the same question for the hundredth time. Work a machine does better.

  • Support
  • Sales
  • Scheduling
  • Back office
  • Documents
  • Data

The offer

AI in Production Sprint

Your first AI agent answering on WhatsApp — in production in 45 days.

Investment: set after the diagnostic

  • 2 Sprints per month
  • Founder pricing for the first 5 clients, in exchange for a case study
Get my AI X-Ray
  1. An AI X-Ray (Raio-⁠X) of your process

    A map of your current flow, volume and cost per conversation, plus a numeric goal, agreed in writing.

  2. A custom-built agent

    Built for your process and plugged into what you already use: calendar, CRM, spreadsheets, ERP.

  3. Guardrails and evals

    A test suite built from real, anonymized conversations. The agent goes live only if it passes.

  4. Observability dashboard

    Every conversation, cost and error, visible to you. No black box.

  5. Prompts your team can edit

    Change the tone and the rules yourself — no waiting on us for every small tweak.

  6. Handoff to a human

    When a conversation needs a person, the agent hands it over with the full context.

  7. 30 days of hands-on support

    We review the agreed metric with you every week and keep tuning the agent.

  8. ROI report on day 60

    Before and after, with your numbers.

  9. Bonus: a roadmap for your next 3 automations

    Ranked by return and effort.

Acceptance guarantee

If the agent doesn't pass the acceptance criteria defined in the AI X-Ray, we keep working at no cost until it does.

How it works

You bring the process. We bring everything else.

  1. Week 1

    AI X-Ray

    Interviews, data and a goal in writing.

    You: two 1-hour calls.

  2. Weeks 2–5

    Build and evals

    Agent, integrations and a test suite.

    You: review sample conversations.

  3. Day 45

    In production

    Live, with a dashboard and a human handoff.

    You: sign off on acceptance.

  4. Day 60

    ROI report

    Before and after, and the roadmap for what comes next.

    You: choose the next process.

Product

In beta with its first client clinics

We built our own before building yours.

BYIA is a WhatsApp front-desk agent for medical clinics, wrapped in a complete practice-management system. It comes from the same team behind Kadash — and it's already in beta with its first client clinics, which help shape every release before general availability. It's the same rigor we bring to your project.

  • Calendar with day, week and month views, synced with Google Calendar
  • Patient records, SOAP notes and pre-visit forms
  • Health-plan billing with TUSS codes (Brazil's standard)
  • One inbox shared by the team and the agent — voice notes transcribed, images and documents read
  • The clinic tunes the agent by talking to it; prompts are versioned
  • Reminders, confirmations and satisfaction surveys
BYIA inbox with replies sent by the AI; contact names and phone numbers blurred
Inbox
The agent's profile in BYIA, describing who it is in plain language
Who the agent is
The agent's step-by-step conversation flow, including the rule to put safety first in urgent cases
Step by step
Agent capabilities switched on and off: booking and rescheduling appointments, questions about health plans and about the clinic
What the agent does

What we build

We start with WhatsApp. We don't stop there.

Back office and documents

Reads invoices, contracts and receipts; checks, classifies and enters them into your system.

Example of what we measure: documents processed per hour, review rate.

Internal knowledge base

Your team asks, the agent answers with the source — manuals, policies, history.

Example of what we measure: questions resolved, search time saved.

Data and reports

Questions in plain language become queries and reports, without waiting in the data team's queue.

Example of what we measure: reports generated, time to an answer.

Process automation

Agents that run workflows across systems, with rules and approvals.

Example of what we measure: hours saved per month, errors avoided.

Engineering

AI with mission-critical discipline.

Our team comes from platforms where mistakes are expensive. We bring the same rigor to AI.

WhatsApp · Web · EmailGuardrailsAgentTools: calendar, CRM, ERPModels: OpenAI · AnthropicObservability and evalsHuman in the loopWhatsApp · Web · EmailGuardrailsAgentModels:OpenAI · AnthropicTools: calendar, CRM, ERPObservability and evalsHuman in the loop
  1. Multi-model

    OpenAI and Anthropic, chosen per task, cost and latency. No lock-in to a single vendor.

  2. Guardrails

    Business rules, action limits and forbidden answers, defined before the first test.

  3. Evals

    Suites of real, anonymized conversations the agent has to pass before every release.

  4. Observability

    Every call, cost and decision logged and traceable (LangFuse).

  5. LGPD and data

    Minimal data, anonymized test sets and role-based access, under Brazil's data-protection law (LGPD).

  6. Edge infrastructure

    Applications on Cloudflare Workers: close to your users, scalable, and no servers to manage.

Diogo Guedes

Who's on your project

Diogo Guedes

Founder · Software engineer and architect

15+ years putting software into production — backend, platforms, distributed systems, cloud/edge and applied AI. At Kadash since 2020, he runs projects end to end: diagnostic, architecture, build and operation.

  • 15+years of our team putting software into production
  • 4M+transactions a day on platforms our team contributed to
  • R$30B+in daily volume on those same platforms

Our team has built production software for

Genesis ConsultingB3VLIV4 CompanyHub ConexaAliareSiaconBoom CafésLG lugar de genteGreat PagesSenac GoiásCENTI

Questions

What everyone asks before we start.

What if the AI gets it wrong?

It will, sometimes — people do too. That's why the agent has guardrails, goes live only after passing its evals, and hands the conversation to a human when it isn't sure. Every mistake is logged and becomes a test.

Is my data safe?

We use only the data we need, anonymize it for testing and control access by role. We handle everything under Brazil's data-protection law (LGPD) and put in writing who can access what.

Do I have to replace my systems?

No. The agent plugs into what you already use — calendar, CRM, spreadsheets, ERP. If something has no integration, we build it.

How much does it cost?

It depends on the process, the volume and the integrations — so the AI X-Ray sets the investment, in writing, before you commit to anything. The first 5 clients get founder pricing.

What happens after the 45 days?

The agent stays live, with 30 days of hands-on support from us. On day 60 you get the ROI report and decide: we keep running it, we move on to the next process, or you take it over.

Who owns what gets built?

Your prompts, your rules and your data are yours. Code ownership terms are spelled out in the contract, before we start.

AI X-Ray · free

Find out how much an agent could win back for you — using your own numbers.

Fill in the calculator. If the number makes sense, request the full AI X-Ray: a 30-minute call and a one-page report within 72 business hours, covering the recommended process, feasibility, risks, a goal and an investment estimate.

Which process?

72 hours a month you could get back; R$3,240 in potential value a month; R$38,880 a year.

Estimate based on your numbers: volume × minutes × % repetitive × cost per hour. Not a promise of results — it's the starting point of the X-Ray.

Get my full AI X-Ray

We use your data only to answer this request. Privacy policy