Alex Otsubo · automate100

I put AI to work inside your operation — and show you the number.

WhatsApp support that answers in seconds, integrations that never duplicate an order, AI cost cut by 89%. All in production, all measured. If it can't be measured, I don't sell it.

Measured in production

96 s
median reply time on a client's WhatsApp
−89%
cost per audio in an AI education system
+38%
fleet capacity without buying hardware
0
duplicate orders after the serial queue

Who it's for

Service businesses that lose money between the lead and the reply

Schools, clinics, e-commerce with a CRM, professional firms. If your customer arrives on WhatsApp and someone is slow to answer, this site is for you.

Support that answers

Business WhatsApp with AI in two modes: replies on its own or drafts for a human. Measured in seconds, not promises.

Systems that talk

Store, ERP, CRM, spreadsheet, learning platform. Integrations that never duplicate, never lose, and alert when something is off.

AI cost under control

Triage before the model, caching, a benchmark before switching vendors. Same result for a fraction of the cost.

Cases

Each one with what was built, what was measured, and what the client did not have to do.

AI in Education

AI-powered pronunciation feedback for an online English school

Five teachers correct students' pronunciation every day using a system that listens to the audio, compares it to the lesson's target, and returns feedback — at a per-audio cost 89% lower than the first version.

R$ 0.26
per 100 audios (was R$ 2.29)
41,651
audios screened in a single day, zero errors
AI Customer Support

AI-powered WhatsApp support, measured in seconds

A school's business WhatsApp began responding with a median time of 96 seconds, complete with a monitoring dashboard, imported history, and two response modes — without changing the number or the phone.

96 s
median response time (before: hours)
4 tabs
dashboard: conversations, queue, metrics, pairing
Integrations

Online store and ERP talking to the CRM — without duplicating a single order

Orders from Nuvemshop and Bling now automatically become deals in the CRM. The duplicate race that showed up during every sales spike was eliminated with a serial queue and a safety sweep.

0
duplicates after the serial queue
77
automated tests
Transcription and audio at scale

+38% capacity across a transcription fleet, without buying hardware

A benchmark of 789 real audio files revealed that the speech recognizer was resampling up to six times per file. Fixing one parameter cut −27% off processing time per audio file, confirmed in production the same day.

+38%
fleet throughput (3.56 → 4.90 audio files/s)
−33%
time per audio file on the tightest machine
Voice and agents

Voice agents: from HUD to a voice-driven terminal

Three voice systems in production: a WhatsApp assistant that talks, a JARVIS-style panel with camera and tools, and a bridge that lets you give a code agent voice commands and get a spoken summary back.

30
voices in the gallery, cached
72
tests on the voice → terminal bridge
Infrastructure and continuity

Infrastructure that fits in $5/month and comes back on any machine

Everything runs on Cloudflare (Workers, Pages, R2, KV, D1) with a cost ceiling enforced in code. Encrypted backup to two destinations, and a recovery kit that restores the entire environment on a clean machine — tested, not just promised.

< US$ 5
per month, limit enforced in code
30/30
items restored in the clean-HOME test

How it works

Three formats, one clear next step

1. One-page diagnostic

In 5 business days: what is costing you, where AI fits, how much you can gain — measured, not guessed. If the measurement kills the idea, I say so.

2. 30-day implementation

A system in production, with a restore point first, automated tests, and the number we agreed on the wall.

3. Monthly operations

Review, alerts and continuous improvements. One report per month with verified findings.

Questions that come up in the first call

Do I need to switch systems?

No. Everything in the cases was built on top of what the client already used — WhatsApp, store, ERP, learning platform.

What if it does not work?

That is what the diagnostic is for: measure first. It has happened that the measurement killed the proposal — and I delivered the "not worth it" instead.

Who are the clients?

Anonymized by default. In a call, with each client's permission, I share names and references.

Do you work in English?

Yes. Calls, proposals and delivery in English or Portuguese. Based in Brazil; hours arranged by time zone.

Start with the number

Tell me where your customer waits. In 5 business days you get one page with the math done.