We design, measure and operate AI systems: agents, RAG and applications on language models. Also custom software, mobile apps and integrations. We have spent three years running a RAG for two million active users across ten countries.
2,000,000 active users served · 10 countries in operation
Built on
Ninety seconds: who we are, how we work and what you get at the end.
Contracts, price lists, email, the CRM: what you already have becomes sourced answers and agents that do the work. Pick a case and follow the path.
Example: a customer asks what their policy covers. The system answers with the exact page of the contract and opens the case.
Connected by API or uploaded. Nothing leaves your infrastructure when the case demands it.
84 pp → 612 chunks
Searches by meaning and by exact word, and filters by the tag before choosing.
answers with source · 91 of 100
Swipe to follow the flow →
Three things, always with fixed scope, price and date. All of them come out of your documents and your systems, and all of them are measured before they ship.
01
For your customers or for your team. Over your PDFs, email and databases. It answers with the citation; when it does not know, it says so and hands over to a person.
02
They query your systems, decide and execute: collections, quotes, reconciliation, follow-up. They ask for approval when the action has consequences, and they log every step.
03
We connect the systems that do not talk to each other, build the software or app that is missing, and fix the AI you already bought that answers badly.
Says what a policy covers, quoting the clause and the version in force that day. If the wording changed in March, it answers with March’s.
AI for Insurance →An example
— Am I covered if my car is stolen from a public car park?
Yes, with a 10% deductible. 2026 policy wording, clause 4.3.
An AI system is worth what its sources are worth. These are the standard connectors; anything with an API or a database connects the same way, and what has no API is handled by file.
SAP
Enterprise ERP
Oracle
ERP and database
NetSuite
Cloud ERP
Salesforce
CRM and service
HubSpot
CRM and marketing
PostgreSQL
Database and pgvector
Microsoft SQL
Database
Snowflake
Data warehouse
BigQuery
Google data warehouse
Databricks
Data platform
Redshift
AWS data warehouse
Synapse
Azure data warehouse
Supabase
Managed Postgres
Workday
Payroll and HR
QuickBooks
Accounting
Sage
Accounting and ERP
Xero
Cloud accounting
Shopify
Catalogue and orders
WooCommerce
Catalogue and orders
Magento
Catalogue and orders
Stripe
Payments and subscriptions
Google Drive
Documents and folders
CSV y Excel
Flat files
Nothing in this category
Four steps, and something running from the first week.
Contact usYou tell us what you want to build or what stopped working. If it does not make sense to do it with AI, we say so on that call. Booked online, with no back-and-forth.
Fixed scope, price and date. If scope changes later it is quoted separately and approved first — it never shows up as a surprise on the invoice.
You see something running from week one. No disappearing for a month and returning with a surprise.
The code, the documentation and the evaluation set are yours, so your team can maintain and verify the system without depending on us.
You tell us what you want to build or what stopped working. If it does not make sense to do it with AI, we say so on that call. Booked online, with no back-and-forth.
Fixed scope, price and date. If scope changes later it is quoted separately and approved first — it never shows up as a surprise on the invoice.
You see something running from week one. No disappearing for a month and returning with a surprise.
The code, the documentation and the evaluation set are yours, so your team can maintain and verify the system without depending on us.
We built and operated the assistant for a loyalty platform serving more than two million active users across ten countries.
We built the full pipeline: document ingestion and normalization, chunking, embedding generation, vector store on Azure AI Search and Pinecone, and retrieval with grounded generation on LangChain.
We held it above 99% availability for three years.
RAG systems →Eight short answers. If yours is not here, that is what the fifteen-minute call is for.
They sell access to a tool; we hand over a system that is yours, with its code and documentation. Subscription platforms work well for a simple FAQ bot — if that is what you need, hire them, they are cheaper. The difference appears when your information is large, changes often, or when a wrong answer costs you a customer: that is when you need to measure answer quality, and that is engineering, not configuration.
With fixed scope, fixed price and fixed date, in a proposal that arrives 48 hours after the first call. Price is driven by three things: the volume of information, how many systems have to be integrated, and how much precision the case demands. If scope changes mid-project it is quoted separately and approved first — it never shows up as a surprise on the invoice. The diagnostic call is free and the range comes out of it.
Yes. We are in Medellín (UTC−5), with full overlap with US Eastern and Central hours and all of Latin America. Most of our work in recent years has been remote with teams in Mexico, the United States and Colombia.
No. We use enterprise plans where data sent through the API is not used for training. When the case requires it we deploy on Azure OpenAI or Amazon Bedrock inside your own subscription, so information never leaves your infrastructure, and we filter personal data before anything reaches the model.
That is the most common case that reaches us. Start with a diagnostic rather than a rebuild: the language model is almost never the problem — how the information was prepared and retrieved is, and that part can be rebuilt without throwing away the rest. In a week you know whether it can be rescued or should be rebuilt, with numbers behind the recommendation.
Yes, in two formats: fixed-scope projects with a defined deliverable, or a retainer embedded in your team, your process and your repository. For agencies we work white-label and only speak to your client if you want us to.
An automation, two to three weeks. An assistant over your information, three to six. A system integrated with your business systems, six to eight. In every case you see something running from the first week, not at the end.
Everything is yours: code, documentation, infrastructure and the evaluation set so you can verify quality without us. We include a month of support to adjust whatever real usage surfaces, and after that maintenance is optional and quoted separately.
It gets fixed, it gets built, or it is not worth it. And if the diagnostic does not reach three actionable findings, it is not charged.
No borrowed logos and no testimonials written by us.
We use cookies to improve the user experience. Privacy
