Tecnologías VM
Work
AI sub-brand · since 2018

Nairu AI

Nairu is the AI sub-brand of Tecnologías VM — a boutique intelligence practice that has served political parties, presidents, ministers and mayors since 2018, reading social media at scale to surface how public conversation really moves.

Selected country

Costa Rica

  • 3 presidential campaigns
  • Mayoral campaign
Where we work — five presidential campaigns, three mayoral campaigns and government work across four countries. Hover or tap a country.
Imagery

The platform, in production.

Screens from the Nairu analysis platform — the system behind the daily and weekly insight.

Nairu — social-media analysis platform
real imagery — coming
slot reserved — real photo (TODO)
real imagery — coming
slot reserved — real photo (TODO)
01 / 03
0Presidential campaigns
0Mayoral campaigns
0K+Posts analyzed / day
0K+Comments / day

We began in Natural Language Processing and machine learning: a social-media monitoring system that extracted posts and comments and processed them with NER, tagging and sentiment models, searchable through Elasticsearch. Our first engagement was the 2018 Costa Rica presidential runoff, embedded in the war room delivering daily and weekly insight.

Over the years that data work sharpened into intelligence. We moved from statistical dashboards to LSTM-based topic and sentiment models, then to generative reports, then to RAG over a vector index — and by 2025 to a set of LangGraph agents operating over our ocean of posts and comments to surface patterns.

We can fairly say we were a pre-AI-era company that already understood the concepts — big data, machine learning, deep learning — before “AI” became the label. Today Nairu builds insights and agents so Central American clients can make decisions backed by AI-reviewed data.

Timeline

From data tooling to agentic AI.

  1. 2018

    Foundations

    Social monitoring on NLP + Elasticsearch; first Costa Rica presidential war room.

  2. 2019

    Visualization

    Power BI dashboards and mobile-friendly PDF reports; first brand clients.

  3. 2020

    Central America

    El Salvador government client; daily and weekly reports, sustained through 2025.

  4. 2022

    Deep learning

    LSTM topic and sentiment models; second Costa Rica presidential campaign.

  5. 2023

    Generative AI

    LLM-composed insight reports — from quantitative stats to validated subjective insight.

  6. 2024

    RAG

    Weaviate-backed retrieval and dynamic reports; first Panama campaign; deep on LangChain.

  7. 2025

    Agentic AI

    LangGraph agents over 50K posts / 200K comments per day; third Costa Rica campaign.

  8. 2026

    Today

    Insights and agents for AI-backed decisions across the region.

The pipeline

From the ocean of posts to decisions.

  1. 01

    Listen

    Extract posts and comments at scale across social platforms — today 50K posts and 200K comments a day.

  2. 02

    Process

    NER, tagging, topic and sentiment models — from early NLP to LSTM deep learning.

  3. 03

    Index

    Searchable at scale — Elasticsearch from 2018, vector retrieval on Weaviate since 2024.

  4. 04

    Reason

    RAG, then LangGraph agents operating over the indexed ocean to surface patterns.

  5. 05

    Deliver

    Daily and weekly insight to war rooms and governments — decisions backed by AI-reviewed data.

Contact

Let’s build something that works.

Have a real problem where emerging technology might be part of the answer? We’d like to hear about it.