Featured Stories

Historically, when interacting with machines, humans had to adapt to the machine’s language to ask questions—typically using SQL queries—and then interpret the machine’s response. This response usually comes in a structured data format, such as a table or a JSON string, following a specific schema. This is the purpose of the JavaScript Object Notation (JSON) output option on Nuclia’s "/ask" endpoint.

NucliaDB’s indexing system is the backbone of its Retrieval-Augmented Generation capabilities, organizing extracted text, inferred entities and semantic vectors from customer documents. This design enables lightning-fast, context-aware searches that power Nuclia’s advanced data retrieval features.

Designed for Nuclia’s AI Search platform, NucliaDB is a multilayered, dynamically sharded storage engine that unifies blob storage, key-value metadata, and vector indexing to scale semantic search over unstructured data. Its cloud-native architecture, powered by NATS and gRPC, enables fault-tolerant distributed search while still offering a lightweight standalone mode.

LLM-powered agents (or AI copilots) take generative AI beyond basic Q&A by combining conversational ability with goal-driven behavior, and Nuclia makes it easy to build these agents by pairing RAG-powered context with tools for ingestion, prompting and deployment. This enables highly tailored, domain-specific assistants—from city guides to enterprise copilots—without requiring deep ML expertise.

This article explores how Nuclia streamlines research by transforming scattered AI-related resources into direct, actionable answers—eliminating manual search, reducing noise and ensuring accuracy without hallucinations.

UX plays a major role in creating the illusion of intelligence in generative AI, from human-like pauses to natural rewording, but those signals can mislead users and amplify frustration when the system fails. Helping users understand what AI can and can’t do is essential for building reliable, user-centered AI experiences.

The Progress OpenEdge MCP Connector for ABL empowers developers and organizations to modernize, secure and accelerate ABL development by integrating AI-powered, context-aware coding assistance tailored specifically for OpenEdge environments, overcoming the limitations of generic AI tools and enabling faster, standards-compliant code delivery.

The Progress Agentic RAG solution empowers OpenEdge users to unlock actionable, trustworthy AI insights by seamlessly combining structured and unstructured enterprise data, accelerating modernization, boosting productivity and enabling explainable, cost-effective AI adoption without disrupting existing operations.

Integrating the Progress Corticon.js solution and MarkLogic platform can bring decision intelligence directly to your data, enabling high-performance, transparent and explainable automation of complex decisions across various industries.