Latest Articles

How to Migrate From LangChainGo to Genkit Go

Every LangChainGo concept mapped to its Genkit Go equivalent, with before and after code for models, prompts, chains, tools, agents, RAG and memory.

October 27, 2026

by Xavier Portilla Edo

CORE

· 1,185 Views

MQTT, Kafka, NATS, or Zenoh? Choosing Edge-to-Cloud Messaging by Traffic Pattern

Telemetry, control, site sync, and delivery to people have different physics. Here's how MQTT, Kafka, NATS, Zenoh, event mesh, and last-mile platforms map onto them.

October 27, 2026

by Kai Wähner

CORE

· 1,357 Views

Introduction to Error Prone: How to Catch Bugs at Compile Time

Error Prone plugs into javac and fails the build on code that compiles but is almost certainly wrong. It often suggests the fix, too, and you can add your own checks.

October 27, 2026

by Hüseyin Akdoğan

CORE

· 1,353 Views

Why Vulnerability Management Fails Without Reliable Asset Data

Vulnerability management is only as good as your asset data: unknown assets go unscanned, and fewer findings can mean lost visibility.

October 27, 2026

by Alex Vakulov

CORE

· 986 Views

New York City Taxi Trips: Putting Neo4j and DuckDB to Work

We load NYC taxi trip data into Neo4j using DuckDB for aggregation, then run five queries that combine both engines to show what each does best.

October 27, 2026

by Akmal Chaudhri

CORE

· 1,065 Views · 1 Like

Giving AI Agents Safe Access to Legacy Systems: Introducing legacy2mcp

legacy2mcp is a Python toolkit that generates secure Model Context Protocol servers from legacy SOAP services with input validation and audit logging.

October 27, 2026

by Balaji Venkatasubramaniyar

CORE

· 976 Views

PWA on iOS, Part 2: HTTPS, Manifest and Service Worker

Why your PWA works on a laptop but not on an iPhone: HTTPS, the manifest, Service Worker lifecycle and the two caches that keep serving old code.

October 26, 2026

by Konstantin Shkurko

· 3,979 Views

SSRF Prevention in C#: Securing File Imports From User-Supplied URLs

SSRF risks make URL upload a risky feature. If we use the right tools, however, SSRF threat mitigation can be a really straightforward task.

October 26, 2026

by Brian O'Neill

CORE

· 1,145 Views · 1 Like

Beyond the Endpoint: How Agent Cards Enable Discovery, Interoperability, and Trust

Agent Cards enable AI agents to discover capabilities, interact securely, and collaborate with trust across multi-agent ecosystems.

October 26, 2026

by Josephine Eskaline Joyce, Ph.D

CORE

· 1,284 Views · 2 Likes

LangChainGo vs Genkit Go: Where Genkit Shines

The same production service written twice: RAG, tools, typed output, retries, fallback and tracing. 73 lines in Genkit Go against 272 in LangChainGo.

October 26, 2026

by Xavier Portilla Edo

CORE

· 802 Views

To Switch, or Not to Switch the AI Model

Switching to a cheaper AI model can increase workflow costs. Learn how to revalidate outputs, track hidden costs, and maintain quality after model changes.

October 26, 2026

by Stefan Wolpers

CORE

· 1,210 Views

Vision-Language Models in 2026: From Research Breakthroughs to Cloud-Native Production Systems

Vision-language models have moved from research breakthroughs like CLIP, Flamingo, and LLaVA to real-world enterprise use, made possible by cloud infrastructure.

October 26, 2026

by Srinivas Chippagiri

CORE

· 1,283 Views · 1 Like

AI Agents Need an Identity Plane: Rethinking Enterprise Authorization for Autonomous Software

Every tool call can pass review and the system can still do something nobody authorized. A path aware authorization model for agents that choose their own next step.

October 26, 2026

by Igboanugo David Ugochukwu

CORE

· 1,017 Views · 1 Like

Genkit Flows as senro Steps: Extremely Powerful AI Pipelines in Go

Put a Genkit flow inside a senro step, and every model call becomes a cached, retryable graph node: change one document out of three, pay for one call.

October 26, 2026

by Xavier Portilla Edo

CORE

· 954 Views

How to Build Your Own AI SRE From Scratch

A hands-on walkthrough: 7 steps from a bare model behind an endpoint to an agent that reads your telemetry, reads your code, and files its findings as a GitHub issue.

October 23, 2026

by Severin Neumann

· 2,224 Views · 2 Likes

Why AI Agents Need a Shared Enterprise Ontology

AI agents can communicate, but without a shared ontology, they cannot consistently understand enterprise meaning, context, and policies.

October 23, 2026

by Josephine Eskaline Joyce, Ph.D

CORE

· 1,818 Views · 4 Likes

How an AI Software Factory Works: From Developer Intent to Production

Learn how a developer's intent moves through AI agents that plan, code, review, test, deploy, and monitor software, through the concept of software factory.

October 23, 2026

by Pavan Belagatti

CORE

· 1,556 Views · 1 Like