AI Consulting · Claude · Medellín, Colombia · US

I take Claude to production.

From Medellín, Colombia, I take AI to production for businesses in Colombia, Latin America and the United States. No demos, no slide decks: systems that run on the company's real data.
I'm Carlos Betancur Gálvez, founder of btodigital and a university professor at UPB and Universidad EIA. I build with Claude (Anthropic) and Claude Code.

Free 30-minute assessment See the Quirurgil case →
5.0 on Google · 141 reviews
Carlos Betancur Gálvez, AI consultant
20+years in digital marketing
500+companies advised
30 minfree initial assessment
In short

What does an artificial intelligence consultant do?

An artificial intelligence consultant helps a company go from the idea to AI running in production: they identify the use case, design the solution (agents, generative AI, automation, RAG systems), integrate it with the business's real data and systems, and leave it measuring results. I do it from Medellín for companies in Colombia, Latin America and the United States (my team and I build it, I don't just recommend it), with Claude (Anthropic) as the main engine.

What an AI consultant solves:

  • AI agents and chatbots that answer, qualify and sell 24/7.
  • Automation of repetitive processes and operational bottlenecks.
  • RAG systems connected to your data (CRM, ERP, catalogs, documents).
  • From proof of concept to production, with metrics and security.

If you are looking for artificial intelligence advice without committing to one model, see the artificial intelligence consultant page →

In production

What we've built (and is running right now).

One public case with a name and numbers, plus enterprise projects under NDA, presented by industry with technical detail.

Public case · Quirurgil (medical equipment, Colombia)

Internal platform built with Claude Code

The problem: commercial and technical information was split across Salesforce, the Ofima ERP and spreadsheets.

What we built: a custom platform with CRM, installed base, field service and an AI quoting tool, synced with those systems. We built it with Claude Code on Google Cloud: 249 code deliveries between May and August 2026.

Result: 73% of the billable base, which was missing from the CRM, came back into the system; 673 duplicate accounts resolved against the ERP; 1,308 preventive maintenance orders generated automatically across 568 devices, previously done by hand. See the full case at btodigital (Spanish) →
Healthcare · Vertical platform

AI-powered doctor search engine

A vertical healthcare platform with 400+ published physicians. We built a system that automatically translates Google My Business reviews into English with Claude, generates personalized landing pages for VIP doctors with i18n, and monitors Google Ads campaigns daily with Cloud Run Jobs and smart alerts that notify when performance drops.

See the tech stack

Express + Tailwind + Firestore + Cloud Run on GCP, Resend for transactional email, Vertex AI for batch processing.

Fashion retail · In-store QA

In-store sales quality SaaS

A multi-tenant platform that listens to recordings of in-store salesperson conversations and measures service quality with AI. It detects whether they greeted the customer, asked the right questions, handled objections, and closed cross-sell opportunities. The first client operates three locations in Medellín; the product is designed to scale to any retailer with in-person sales staff.

See the tech stack

OpenPlaud fork + Vertex Gemini 2.5 Flash + Firestore + Google Login authentication. Processes hours of audio daily in batch.

Heavy industry · Commercial intelligence

AI data pipeline

Two-way sync between Bitrix24 and BigQuery every 12 hours for a leading industrial company in Latam. Executive dashboard in Next.js + Firebase with AI analysis over the sales funnel. We process around 50,000 historical deals to identify closing patterns, abandoned leads and churn.

See the tech stack

Cloud Run Job + Cloud Scheduler for ETL, Firestore as operational cache, Vertex AI for analysis, Next.js + Firebase for the frontend.

E-commerce · Systems integration

Shopify ↔ corporate ERP middleware

An electronics distributor with a large catalog needed to sync Shopify with Microsoft Dynamics 365. We built middleware with paid-order webhooks, real-time shipment tracking updates, dual-SKU handling, and automatic fallback to Pub/Sub queues with exponential retry when the ERP doesn't respond.

See the tech stack

Node.js on Cloud Run us-central1, Pub/Sub, Firestore, integration with Shopify and Dynamics APIs.

Professional services · Internal assistant

Productivity assistant with RAG

With my guidance, a services company built an internal assistant that answers questions about procedures, active contracts, internal policies and past cases. RAG over 2,000+ documents. It reduces the time the team spends hunting for scattered information and frees up the back-office.

See the tech stack

Claude + Vertex embeddings + Firestore Vector Search + web interface in Astro.

Marketing · RAG over CRM data

Real-time marketing intelligence over your CRM

We've built RAG systems connected to platforms like HubSpot, Clientify, Klaviyo, Shopify and WordPress so marketing and sales teams can query their own data in plain language: customer history, audience segments, campaigns sent, purchase behavior. The team asks and the system answers with real data, not generic model generalizations.

See the tech stack

Claude + Vertex AI embeddings + Firestore Vector Search + incremental sync via webhooks and each platform's REST APIs. The index updates automatically as CRM records change.

Do you have a process that could work like this?In 30 minutes I review your case and tell you whether AI makes sense, at no cost.

Get the free assessment
Why Claude

Why Claude and not ChatGPT, Gemini or an open model?

Model choice isn't ideological. It's strategic. For the enterprise use cases I see most, Claude offers three concrete advantages that end up making the difference in production.

Capability
Claude (Anthropic)
ChatGPT (OpenAI)
Gemini (Google)
Context window
1M tokens on Claude Fable 5.1, Opus 5.5 and Sonnet 5.5
1.05M tokens on GPT-6 Astra
1M tokens on Gemini 3.8 Flash
Neutral Latam Spanish
Excellent; doesn't force Spain-flavored Spanish
Good, but occasionally shifts tone
Good, integrated with Vertex AI
Agentic reasoning (multi-step)
Leader at following long instructions and tool use
Solid with GPT-6 Astra
Strong for high-volume work inside Google Cloud
Cost at typical enterprise usage
Medium-high, justified by quality
Variable by model
Cheaper on Flash, perfect for batch
Data privacy by default
Doesn't train on your API calls
Doesn't train on enterprise API
Encryption and IAM controls on GCP

Models and context windows checked against Anthropic, OpenAI and Google official documentation in October 2026. The Spanish and reasoning rows reflect my project experience, not a benchmark.

In practice, my architectures are usually hybrid: Claude for primary reasoning and conversation, Gemini Flash for cheap high-volume batch processing, and open models on GCP when extreme privacy or minimal latency is required. The question isn't "which model is best?" but "which combination solves this specific problem at the lowest possible cost?".

Public portfolio · btodigital

Three products and six free tools you can see and use today.

I don't just advise: my team at btodigital and I design, build and maintain AI SaaS products. Some are paid; six are completely free so you can see the quality before you talk to me.

SaaS products

SEO + AI · Paid

Ranqio

An AI SEO agent that audits WordPress sites, identifies keyword opportunities, generates optimized articles and publishes them automatically. It replaces hours of manual work from an entire SEO team.

Visit Ranqio →
Shopify · AI · Paid

ShopiUP

An official app published on the Shopify App Store that optimizes product titles, descriptions and meta tags with AI. It improves conversion and SEO for stores with large catalogs.

See it on the Shopify App Store →
WhatsApp assistants · AI

Atendio

A platform of AI WhatsApp assistants for businesses. It answers, books and sells 24/7 in Spanish, with coexistence (keep your number) and context-aware handoff to your human team. It's the productized version of what we build custom.

Visit Atendio →

Free AI tools

AI digital strategy audit

Multi-dimensional analysis with PageSpeed, tech stack detection and a Gemini-powered diagnosis of your positioning.
AI buyer persona generator

Builds your buyer persona with buying journey, empathy map and messaging framework ready for your marketing team.
AdProfit Score

A diagnosis of your digital advertising with 25+ signals analyzed by AI. Useful before audits or budget decisions.
Digital Maturity Score

A radar chart with industry benchmarking. It shows how far you are from your sector's standard and where your gaps are.
AI ad generator

Up to 60 AI-generated ads, ready to publish on Google Ads, Meta Ads or TikTok Ads, with fine-tuned headlines and descriptions.
Content strategy generator

Plan your editorial calendar with AI. It suggests topics, formats, channels and goals aligned with your industry and buyer persona.

Every tool is fully functional, with no mandatory sign-up and no credit card. If you like them, let's talk about how to build something like this inside your company.

Use cases by industry

Where Claude fits in your sector.

Not every use case fits every industry. These are the patterns that work best in each vertical, based on projects we've executed or I've advised on over the past few years.

Healthcare

  • RAG over medical records and clinical protocols for diagnostic support
  • WhatsApp agents to book appointments and answer common patient questions
  • Call-quality analysis in medical contact centers
  • Translation and localization of content for international patients

Retail & E-commerce

  • Bulk optimization of product listings with AI (ShopiUP)
  • Automated post-sale support with escalation to humans
  • Personalized recommendations based on real behavior
  • In-store sales QA with audio analysis

Professional services

  • Internal assistants with RAG over contracts, policies and past cases
  • Automatic generation of proposals, memos and reports
  • Analysis of RFPs and lengthy documents
  • Lead qualification in forms and conversational agents

Industry & manufacturing

  • Commercial intelligence pipeline with CRM and BigQuery
  • Analysis of public and private tenders
  • Detection of churn, leakage and closing patterns in the funnel
  • Technical assistants for field teams with full manuals in RAG

Education

  • AI grading systems with instant feedback
  • Personalized tutoring that scales to thousands of students
  • Generation of pedagogical content tailored to levels
  • Learning analytics and dropout prediction

Financial services

  • Automated document analysis for risk and compliance
  • Fraud detection based on conversational patterns
  • Assistants for advisors handling complex products
  • Processing of customer inquiries with smart classification and routing
How I work

How do you implement Claude in a company in Colombia or the US?

In four phases, with measurable deliverables and the option to stop if reality doesn't match expectations. From the first phase we define which personal data the solution touches and how privacy rules are met. If what you need is for your team to learn Claude, see the Claude training for companies.

01

Diagnosis

1 week

An in-depth interview with you and your team. I identify the real problem (not the symptom), assess whether AI is the right solution or whether there's a simpler fix, and deliver a document with three possible paths: ambitious, balanced and conservative. If you don't want to move forward after this, no problem: the diagnosis is yours to keep.

02

Proof of concept (POC)

2 to 3 weeks

I build a functional but scoped version that proves the solution works in your real context. We test it with a pilot group, measuring quality, cost and adoption. Here we kill bad ideas quickly instead of spending months building something nobody will use.

03

Production implementation

4 to 6 weeks

We take the POC to a robust system: architecture on Google Cloud Platform, observability with Cloud Logging, an alerting system, access controls, error handling and predictable costs. I document everything so your team can maintain or evolve it without depending 100% on me.

04

Continuous iteration

Monthly or quarterly

AI isn't a project that ends: it's a system you tune. We refine prompts, update the RAG, add capabilities, monitor metrics and adjust costs. This can be a monthly retainer or one-off sessions as needed. You set the pace.

The first step is the assessment.A free 30-minute session over video call or WhatsApp.

Book the assessment
Ways of working

How do you hire me for an AI project?

Each project is quoted by scope, after the assessment. These are the four ways of working.

Initial diagnosis
Free

A 30-minute session over video call or WhatsApp. I help you determine whether your use case makes sense for AI, what order of magnitude it might cost, and what returns are realistic.

Proof of concept
2 to 3 weeks

A functional but scoped version. Ideal for small businesses with a well-defined use case, or for corporations that want to validate before committing a large budget.

Full implementation
4 to 6 weeks

A production system with robust architecture, documentation, observability and a maintenance plan.

Monthly retainer
Monthly

Ongoing maintenance, iteration, evolution and support. Variable depending on scope, SLA and the level of involvement from my team.

Why not hire Anthropic directly or a global consultancy?

Anthropic's implementation teams and the large consultancies mostly serve corporations with budgets in the hundreds of thousands of dollars. I offer the same technical work for mid-sized companies in Latin America and the US, in English or Spanish, with quotes tailored to the scope.

Frequently asked questions

What I get asked most.

What do I need before implementing Claude in my business?

The only essential is a clear use case: a repetitive process, an operational bottleneck, or a conversation you are losing. You don't need perfect data or an in-house technical team; I help you start from scratch. What does help is decision-making at the leadership level: implementing AI well changes processes, it doesn't just add another tool.

How soon do I see results with Claude?

A proof of concept (POC) takes two to three weeks. A production-ready implementation takes four to six weeks. In most of the projects I've worked on, the client sees the first signs of savings or commercial impact within the first month. Fine iteration (tuning the prompt, refining the RAG, adding capabilities) is continuous.

Do you work solo or do you have a team?

I personally lead every project, but behind me is the technical team at btodigital, my agency. Depending on the scope, I bring in developers, designers, and data or paid-media specialists. I always build the strategy and architecture myself: I don't delegate the piece that decides whether the project lives or dies.

Is my data safe with Claude?

Anthropic, the company behind Claude, does not use your API call data to train its models by default. On top of that, in enterprise projects we architect the solutions on Google Cloud Platform with encryption at rest and in transit, IAM-based access controls, and strict tenant separation where applicable. Every project includes its own data retention and deletion policy.

Why Claude and not ChatGPT or OpenAI?

Today the three big ones (Claude, ChatGPT and Gemini) all handle around one million tokens, so the difference is no longer context size. I choose Claude for two reasons I see in production: it writes natural English and Latin American Spanish, and it follows long, multi-tool instructions more reliably, which is what an enterprise agent needs. For massive, cheap batch work I use Gemini Flash; architectures are usually mixed.

Do you serve businesses in the United States?

Yes. I handle projects in English and have clients in Miami and other U.S. cities. My site is available in English and Spanish, and the solutions I build work in both languages. Projects are managed remotely.

Do you serve small businesses or only large corporations?

I work with both. Scope adapts to the project: a small business with a well-scoped case can start with a small proof of concept, and I also run large corporate projects. The difference is not the size of the client but the depth of the problem and the complexity of the integration.

Want to see whether it makes sense to implement Claude in your business?

Three paths depending on where you are. I answer personally.

Free diagnosis

A 30-minute session over WhatsApp. I answer personally, assess your case, and tell you whether it makes sense to keep talking.

Message me on WhatsApp →

Get to know me first

My track record, credentials, full portfolio, and the projects I've worked on over 20+ years.

About me →

Learn from the blog

75+ articles on AI with Claude, digital marketing and medical marketing.

Go to the blog →