People decide · AI executes
Drag / tap
Your company, smarter
every month
We connect what you already use —WhatsApp, email, Drive, your ERP— to AI that works by your rules.
Flow examples
Talks to
A Xenth AI product
Conecta
Connect your company's WhatsApp Business to the AI you already use
MX$499 · a month per number · 15-day trial
The cost of manual work
Your team loses hours to work it should not do by hand.
Keying in invoices, building quotes, copying data from an email into a sheet, chasing pending items. Every hour there is an hour not spent selling or serving customers.
Typical example · 2 people × 3 h a day keying and reconciling
Calculation: 2 × 3 h × 22 days ≈ 132 h × $120 = $15,840/month; 80% = $12,672/month freed; $35,000 ÷ $12,672 ≈ 2.8 months; 12 × $12,672 − $35,000 ≈ $117,000. Illustrative figures, not a client result; your case is measured in the diagnostic.
What we do
You do not worry about it.
We implement it.
We work as your company’s AI department: we build it and teach your team to use it.
- 01
Automate processes
Invoices, quotes, operations and reports, connected to your systems and in production.
- 02
Train the team
Your people work with AI day to day, with clear rules of use.
- 03
Connectors and custom software
If your platform will not integrate, we build the missing piece.
- 04
WhatsApp with AI, when it adds up
One more channel, not the whole product. If it does not help, we do not force it.
Typical example · before and after
The same work, in fewer hours.
| Process | Before | After |
|---|---|---|
Invoices | Someone keys in each invoice and checks it against the order. | AI reads it, matches it to the order and leaves the record ready. Your team reviews only the exceptions. |
Quotes | 30 to 40 minutes per quote, assembled in a spreadsheet. | A draft on your template in minutes; the salesperson reviews and sends it. |
Reports | Someone pulls data from three systems every week. | The report reaches management on its own every morning. |
Illustrative example, not a client result. The figure for your case is measured in the diagnostic, before implementing.
How we start
Not sure where to start with AI? We build your strategy.
- 01
Diagnostic
We understand the business and measure where the hours and the money go.
- 02
Priority
We pick the process that pays to automate first, with a written success criterion.
- 03
Implementation
We build it: connected to your systems and in production.
- 04
Training and growth
Your team runs it; the next process is chosen with data.
How we work
You decide what gets approved.
We do not replace your legal counsel: we hand them a concrete design and an audit log they can review.
- 01
Permissions per tool and folder
AI sees only what you authorize.
- 02
A log of every action
With date and actor, to reconstruct any step.
- 03
Access in your company’s name
The keys do not stay with the vendor.
- 04
A person approves where mistakes cost
Discounts, payments, messages to customers: AI proposes and someone on your team decides.
Who's behind it · Derian Castillo, founder
Ten years building software for companies.
- 35+
Projects since 2016
Web platforms, CRMs and mobile apps for construction, fuels, real estate, education, sports and foundations.
- Big 4
Senior AI Fullstack Engineer
Technically leading an international team.
- Lead
Engineering Lead & Manager
A financial platform in production and a crypto wallet.
Figures from my own team, not a client
Proof
Accredited by Anthropic
2 credentials issued by Anthropic. Each one verifies in 1 click.
- Claude Certified ArchitectProfessionalVerify on Credly
- Claude Partner BadgeClaude CodeVerify on Credly
Anthropic certifications
18 completed courses. Each one verifies at its public link.
- AI Fluency for nonprofits
- Claude with the Anthropic API
- Claude Code in Action
- Claude with Google Vertex AI
- Claude with Amazon Bedrock
- Deploying Claude Enterprise with Confidence
- Introduction to Model Context Protocol
- Model Context Protocol: Advanced Topics
- Teaching the AI Fluency Framework
- AI Fluency for Builders
- AI Fluency for educators
- AI Fluency for students
- AI Fluency: Framework & Foundations
- Claude 101
- Claude Code 101
- Introduction to agent skills
- Introduction to Claude Cowork
- Introduction to subagents
More verifiable certifications (34)
DeepLearning.AI
Udemy
- AI Engineer Agentic Track: The Complete Agent & MCP Course
- AI Automation: Build LLM Apps & AI-Agents with n8n & APIs
- n8n + MCP: Automation and intelligent AI agents
- 12 Strategies for Dealing With Difficult People
- Hybrid Leadership: Essential skills to lead from anywhere
- Leadership: Leading When You Are Not In Charge!
- Leading & Managing People [Effectively]
- Leading with Purpose
- Leading Yourself and Others
- Project Management with ChatGPT
- DevOps & Cloud with Azure DevOps, App Service Pipelines & Git
- Conflict Resolution for IT Professionals
- From Engineer to Technical Manager: A Survival Guide
- Optimizing Web Performance and Critical Rendering Path
- Modern JavaScript: A Guide to Mastering the Language
- Mastering Clean Code in JavaScript
- SOLID Principles and Clean Code
- TypeScript: Your complete guide and handbook
- 10
- years building software for companies
- 35+
- projects delivered since 2016
- 85%
- of commits AI-assisted, in a real team
- 5
- people led as Engineering Lead
The fine print, for your IT team
- 90.7% test coverage on the financial platform
- 443 PRs with a 2.4 h median lead time (DORA Elite band)
- 1 release every 4.6 days, with release engineering built from zero
- 228 endpoints, 60 controllers and 182 database migrations
- 248 of 309 architecture decision records written
- 327 AI skill, agent and rule files in operation
Clients
Companies that already trusted us.
Design, development and architecture projects delivered since 2016. AI consulting is the evolution of this work, not a leap into the dark.
Services
Four ways in
Most engagements start with the first or the third.
- 01
Designing and connecting the ecosystem
The full job: mapping, network design, integrations with n8n and custom APIs, automated documents and templates, permissions and an audit log. It grows in phases, not all at once.
- 02
Deep research and analysis
Competition, market and your own data, analyzed in depth with AI. The output is a document with what you weren't seeing and a prioritized list of what to attack first.
- 03
An audit of the AI you already have
You already have a bot or automations running and nobody knows what they can reach. I review permissions, close what's open beyond need, install an audit log and hand you the map of what touches what. It's the cheapest work on the list and the one that removes the most risk.
- 04
Training so you don't depend on me
I sit down with your team and teach them to use AI in their actual work, with clear rules of use. What I do keep is the integration layer, because that's where everything breaks if it's done badly.
Pricing
What it costs, before we talk.
Every figure is a floor, not a hook. In the first conversation we scope it and give you the number for your case in writing.
First conversation
You leave that call knowing whether AI applies to your operation. If it doesn't, I tell you then and there's no commercial follow-up.
30 minutesUnderstand
Nothing gets built here yet: you leave with the plan and the quote to build it.
Diagnostic of one area or process
You stop guessing where to start. One area, what it costs to run today, and the first process to connect with its success criteria in writing. Building it is not included; if you continue to the project, it is credited in full.
from 3 weeksWhole-company mapping
You see your company as a system, not as separate areas. The output is the map of everything connectable, ordered by what costs most today, and the phased plan to work through it. Building is not included: you get the quote for the connected process or ecosystem, discounted if you continue.
from 5 weeksBuild
Connect processes and leave them running with your team.
One connected process
One process stops needing someone typing it. It runs end to end, with permissions and an audit log, and your team is trained to operate it. This is where most engagements start.
from 4 weeksConnected ecosystem
Your processes stop sitting in isolation and start talking to each other. Documents that generate themselves, an operations dashboard, and reports that arrive without being asked for. Handed over documented to your team.
from 8 weeksOngoing support
The ecosystem keeps growing every month without you pushing it. It ships ready to run without me; this is for when you'd rather someone keep expanding it.
optionalProduct · Conecta
Your whole company, connected to your AI.
Connect all your company's tools to the AI you already use
- 01
CRM
Contacts, leads and each customer's history in one place: the base of the platform, which your AI reads and writes.
- 02
WhatsApp Business
Your AI reads conversations and sends messages and templates from your number. It respects the 24-hour window and every send goes through your permissions or approval.
- 03
In-person meetings
Records your face-to-face meetings and keeps what was said, so your AI consults it with the same context.
- 04
Business intelligence
Conecta's own AI, connected to the platform, makes suggestions in WhatsApp and, soon, in your social media.
- 05
Email, calendar and Drive
They connect directly to your AI, which runs the connection as the intermediary: it reads, sorts, schedules and files.
- 06
Custom modules
Your store, your ERP or the process no tool covers: we build it as a module inside the platform.
No surprises
Four commitments in writing.
Payment in stages
50/50 on short projects, 30/40/30 on long ones. Never everything up front.
Three months of technical warranty
If something breaks in that period, it gets fixed at no cost.
Success criterion in writing
Before building. If the pilot misses it, the next phase is not billed.
Everything stays in your name
Access, documentation and training. If the relationship ends, the system keeps running.
Questions
What gets asked before signing
Is this only for WhatsApp?
No. WhatsApp is the example that lands fastest because almost every Mexican company already uses it, but the work is connecting everything connectable: email, Drive, sheets, calendar, Shopify, your ERP, your CRM, and custom APIs where no off-the-shelf integration exists. The value shows up when processes connect to each other, not when one gets automated on its own.
What is n8n and why does it matter?
It's where the connections live: the layer that moves information between your systems, triggers the processes and enforces the permissions. It can run on your own infrastructure, which means the data doesn't have to leave your control. It's the hard layer of the work and it's the part I build.
Will my data train an AI model?
No. The models operate under terms where your information isn't used for training, and access is limited to the folders and sheets you authorize, one by one. The permissions stay in your company's name, not mine.
What about the data protection law and my privacy notice?
The law in force since March 2025 does not explicitly address AI processing, and the supervisory body changed. In the diagnosis we review what purposes your current privacy notice declares and whether the use you want to make of your historical data fits within them. I'm not your lawyer and I don't replace your legal counsel: I hand them a concrete design and an audit log they can review.
I already have a bot running. Is it worth anything?
It's worth something as a starting point, and usually as a warning. The audit reviews what it can reach today, which permissions are open beyond need, and what isn't being logged. It's the cheapest work on the list and the one that removes the most risk.
Does this replace my team?
No. It replaces the work of typing the same thing three times. What happens in practice is that the team stops entering data and starts serving clients. If your goal is cutting headcount, I'm not the right provider.
Do I have to change my systems?
No. It's built on the tools already running. If something did have to change, it's stated before we start and justified with numbers.
And if the AI gets it wrong?
That's what the person at the expensive points is for. The AI proposes the appointment and the client confirms it; the AI prepares the quote and someone approves it. Where that control point sits is defined with you before building, and every action is logged so what happened can be reconstructed.
What happens if you stop being available?
The access and credentials belong to your company from day one, everything is documented, and your team is trained to run it. The system is designed to survive my departure, not to depend on my availability.
Next step
Let’s start with a
conversation.
At no cost.
To find out whether this applies to your operation and where it makes sense to start. If it does not apply, we tell you right there and there is no sales follow-up.
AI proposes. A person approves.