Articles / Topic guide

Topic guide

Production AI for companies in Colombia and LATAM

Resources for moving from AI ideas and prototypes to deployed systems with operational impact.

Built for companies in Colombia, LATAM, and remote teams that need technical implementation, not only strategy.

View projects

Related articles

Hybrid RAG Search with BM25 and Rank Fusion in Python

Oct 2026 · LLMs & Agents

Hybrid RAG Search with BM25 and Rank Fusion in Python

Combine exact-term BM25 retrieval and semantic rankings with reciprocal rank fusion. Run a Python baseline and evaluate candidate depth before reranking.

Read
Invoice Extraction Accuracy: Source Validation in Python

Oct 2026 · LLMs & Agents

Invoice Extraction Accuracy: Source Validation in Python

Validate extracted invoice amounts against source lines, explicit decimal formats and totals. Measure field accuracy and review coverage with labeled documents.

Read
Jev in Python: Typed Intent Routing with the TypeSafe SDK

Sep 2026 · LLMs & Agents

Jev in Python: Typed Intent Routing with the TypeSafe SDK

Use the TypeSafe Python SDK and Jev to route requests with typed Choice and Noul results, confidence thresholds and human review.

Read
Build a Safe Read-Only MCP Server in Python

Sep 2026 · LLMs & Agents

Build a Safe Read-Only MCP Server in Python

Expose a small, read-only Python service through MCP with validated inputs, bounded results, and an integration checklist.

Read
Evaluate RAG Offline: Retrieval Quality and Evidence Availability

Sep 2026 · LLMs & Agents

Evaluate RAG Offline: Retrieval Quality and Evidence Availability

Use a small executable Python harness to measure retrieval and annotated evidence availability before changing a RAG system.

Read
Context Engineering for Agents: RAG, Memory, and Tool Results

Sep 2026 · LLMs & Agents

Context Engineering for Agents: RAG, Memory, and Tool Results

Choose what an agent sees from retrieval, memory, and tool results with explicit freshness, provenance, and token budgets.

Read
Structured Data Extraction with LLMs, Python and Pydantic

Jun 2026 · LLMs & Agents

Structured Data Extraction with LLMs, Python and Pydantic

Extract invoices and job postings with Python, Pydantic and Instructor. Validate types, review failures and measure field-level accuracy.

Read
AI Agents with LangGraph for Data Analysis

Jun 2026 · LLMs & Agents

AI Agents with LangGraph for Data Analysis

Build an autonomous data analysis agent using LangGraph. Learn how agents differ from RAG, and implement the ReAct loop with tools for querying and summarizing data.

Read
Orchestrate ML Pipelines with Prefect

Jun 2026 · MLOps

Orchestrate ML Pipelines with Prefect

Go from fragile training scripts to robust, observable ML workflows using Prefect. Schedule retraining, handle failures gracefully, and monitor every run.

Read
ML Monitoring with Evidently: Detect Data Drift in Python

Jun 2026 · MLOps

ML Monitoring with Evidently: Detect Data Drift in Python

Compare batches with Evidently 0.7.23, define numeric features, export drift metrics and tests, and evaluate labeled model quality separately.

Read
Titanic with scikit-learn: Python Pipeline Tutorial

May 2026 · Machine Learning

Titanic with scikit-learn: Python Pipeline Tutorial

Train a Titanic classifier in Python with fetch_openml, preprocessing, GridSearchCV and a held-out test set. Includes handling unknown categories.

Read
How to Solve Scheduling Problems in Python

May 2026 · Operations Research

How to Solve Scheduling Problems in Python

Build an employee roster with pyworkforce 0.5.4: coverage, availability, minimum hours, solver statuses and the limits of its rest and preference rules.

Read
Adaptive Mutation and Crossover in sklearn-genetic-opt

Apr 2026 · Machine Learning

Adaptive Mutation and Crossover in sklearn-genetic-opt

Use sklearn-genetic-opt adapters to schedule mutation and crossover, check their finite-step values, and compare them with a fixed baseline.

Read
Feature Selection with sklearn-genetic-opt

Apr 2026 · Machine Learning

Feature Selection with sklearn-genetic-opt

Run GAFeatureSelectionCV 0.14.0 with fold-local scaling, inspect the selected features and evaluate baseline and tuned pipelines on a separate holdout.

Read
Kafka Anomalies in Python: Models, Events, and Offsets

Apr 2026 · Data Systems

Kafka Anomalies in Python: Models, Events, and Offsets

Run a local Kafka and Isolation Forest demo in Python with three partitions, event validation, and offset commits after processing succeeds.

Read
Serve a scikit-learn Model with FastAPI and Docker

Mar 2026 · MLOps

Serve a scikit-learn Model with FastAPI and Docker

Train an Iris classifier and serve it with FastAPI. Protect both prediction routes, validate finite inputs, bound batches and test a Docker container.

Read
Are You Still Using Grid Search for Hyperparameters Optimization?

Mar 2026 · Machine Learning

Are You Still Using Grid Search for Hyperparameters Optimization?

Compare grid search, random search, and evolutionary algorithms for hyperparameter optimization with sklearn-genetic-opt.

Read
Tune Your Scikit-learn Model Using Evolutionary Algorithms

Feb 2026 · Machine Learning

Tune Your Scikit-learn Model Using Evolutionary Algorithms

Hyperparameter tuning with GASearchCV from sklearn-genetic-opt using evolutionary algorithms.

Read
MLflow in Python: Track Experiments and Version Models

Feb 2026 · MLOps

MLflow in Python: Track Experiments and Version Models

Track Python experiments with MLflow 3.14 and SQLite, separate validation from final testing, and retrieve a versioned model through a registry alias.

Read
How to Build a RAG System with LangChain and Python

Jan 2026 · LLMs & Agents

How to Build a RAG System with LangChain and Python

Build a PDF RAG pipeline with Python, LangChain and Chroma. Preserve page references, validate citation IDs, and separate retrieval tests from answer quality.

Read
Workforce Planning Optimization Using Python

Jan 2026 · Operations Research

Workforce Planning Optimization Using Python

Plan a repeating workweek with pyworkforce 0.5.4. Verify a nine-person coverage plan and compare minimum headcount with minimum absolute staffing gap.

Read

Are you building an AI or data platform?

Tell me what you are implementing and where the problem lies: retrieval, models, data or product integration.

View all projects