Latest Articles

This $5,000 Berkeley Humanoid Can Be Built With a Desktop 3D Printer

UC Berkeley's open-source Humanoid Lite costs under $5,000 and uses 3D-printed parts, opening humanoid robotics to more researchers and students.

September 4, 2026

by Aminu Abdullahi

· 933 Views

Prompting AI for Analytics: The Missing Optimization Layer Between Your Question and the Model

A practical blueprint for cutting AI token costs in analytics — clean up the question before it reaches the model, then learn from what worked.

September 4, 2026

by Dinesh Pamcheti

· 783 Views

Multilingual Conversational Payments Chatbot Architecture: Enterprise RAG With Safety Guardrails, Human Handoff, and Multi-Modal Support

A retrieval-augmented generation (RAG) pipeline that grounds LLM responses directly in your website/document content to prevent hallucinations.

September 4, 2026

by Sriram Ramakrishnan

· 854 Views

Handling Large API Responses Without Freezing the Client: A Practical Architecture With Temporal, Kafka, and RAG

Use Temporal for orchestration, Kafka for chunk processing, object storage for payloads, and RAG to retrieve relevant data without overwhelming clients.

September 4, 2026

by Uthej Mopathi

· 833 Views · 1 Like

Building Agentic RAG, Step by Step: From Static Retrieval to Reasoning Pipelines

Build an agentic RAG system that plans retrieval, grades results, reformulates queries, and self-checks answers to improve grounding.

September 4, 2026

by Balaji Venkatasubramaniyar

· 858 Views

MCP for Enterprise Tasks: Making the Rare Frequent Enough to Master

Agentic clients via MCP are a new human interface to old software. They are an appealing choice: they use native language. But it is not always the wise approach.

September 4, 2026

by Peter Verhas

CORE

· 1,156 Views · 1 Like

Why I Don't Want an LLM Generating Java Business Logic

Why do you need a DSL when an LLM generates business logic more than ever? To limit what generated code can do with allow-lists, not deny-lists.

September 4, 2026

by Peter Verhas

CORE

· 1,055 Views

Video and Audio as Knowledge Sources: Content Understanding in Microsoft Foundry IQ

Turn video and audio recordings into searchable, citable knowledge for Microsoft Foundry IQ using Azure Content Understanding, MarkItDown, and structured metadata.

September 4, 2026

by Jubin Soni, FBCS

CORE

· 838 Views

Designing Safe Agent Permissions: Why Least Privilege Must Exist Outside the Model

AI agents need least-privilege permissions, scoped identities, and policy controls to safely execute actions without exceeding their intended authority.

September 4, 2026

by Igboanugo David Ugochukwu

CORE

· 1,256 Views

Enterprises Should Assume AI Agents Will Delete Their Production Base

AI agents will eventually take a destructive action your stack never planned for. Here are five ways to strengthen your identity strategy before agents find the gaps.

September 3, 2026

by Meir Wahnon

· 1,097 Views

The Startup Time Trick Hiding Inside Your Docker Build

Spring Boot pods reload the same classes on every start. A CDS training run inside your Dockerfile caches that work once and cuts startup time roughly in half.

September 3, 2026

by Garima Agarwal

· 1,338 Views · 1 Like

How I Run Two AI Coding Agents on One Codebase

Isolated worktrees, explicit ownership boundaries, and automated validation enable multiple AI coding agents to develop safely in parallel.

September 3, 2026

by Uthej Mopathi

· 1,174 Views · 1 Like

The Bottleneck of Scaling

Learn how modern languages help developers take care of behind-the-scenes file descriptor management, kernel memory management, and heap management.

September 3, 2026

by Vishal Bhatia

· 1,296 Views

Your Spark Job Isn't Slow Because of Bad Code. It's Slow Because of the Wrong Join

Apache Spark job performance issues are frequently caused by improper join strategies leading to excessive data shuffling, rather than suboptimal code.

September 3, 2026

by Syed Siraj Mehmood

· 1,049 Views

Building a Python API Client That Doesn’t Fall Apart When the API Misbehaves

Build a safer Python API client with timeouts, selective retries, exponential backoff, jitter, and better handling of rate limits and temporary failures.

September 3, 2026

by Ally Garcia

· 1,146 Views

Gossip on Cryptography: Part 3

In Part 3 of this casual, jargon-free series, we break down hashing, salting, rainbow table attacks, and asymmetric encryption (RSA) — all with everyday analogies.

September 3, 2026

by Sahil Aggarwal

· 1,350 Views · 2 Likes

Making Running Optional: Scaling AI Agents on Kubernetes With Agent Substrate

Learn how an early-stage open-source project separates workload lifecycle from compute allocation for bursty, stateful, and massively concurrent AI workloads.

September 3, 2026

by Mayowa Fajobi

· 1,273 Views

Portable Intelligence Architecture: When the Runtime Becomes the Hard Problem

As AI inference moves closer to live context, the hard problem shifts from model quality to runtime design. Portable Intelligence Architecture solves this.

September 2, 2026

by Punit Shah

· 1,316 Views · 1 Like

Extracting Entities and Relationships From Engineering Documents With spaCy

Learn how to extract domain-specific entities and relationship triples from engineering documents using spaCy, custom entity rules, and Python.

September 2, 2026

by Sriharsha Makineni

· 1,383 Views · 1 Like

Best Practices for Handling Bad Data in Stream Processing Platforms

Learn best practices for handling bad data in stream processing, from schema validation and duplicate detection to dead-letter queues, monitoring, and data lineage.

September 2, 2026

by Gautam Goswami

CORE

· 1,253 Views · 1 Like

Latest Articles - DZone