AI/ML Resources

ToolOrchestra vs Mixture of Experts: Routing Intelligence at Scale

Learn about two fundamental architectural patterns reshaping how we build intelligent systems. Explore ToolOrchestra, Mixture of Experts (MoE), and other AI patterns.

January 30, 2026

by Vidyasagar (Sarath Chandra) Machupalli FBCS

CORE

· 2,219 Views · 2 Likes

Ralph Wiggum Ships Code While You Sleep. Agile Asks: Should It?

AI makes code cheap, not thinking. When cost disappears, Agile principles supply discipline so teams don’t build the wrong thing faster at scale with AI.

January 30, 2026

by Stefan Wolpers

CORE

· 2,122 Views · 1 Like

Essential Techniques for Production Vector Search Systems, Part 3: Filterable HNSW

Proven techniques for production vector search, including when to use each one, how to combine them effectively, and trade-offs to understand before deployment.

January 30, 2026

by Pavan Vemuri

CORE

· 1,719 Views · 2 Likes

TPU vs GPU: Real-World Performance Testing for LLM Training on Google Cloud

H100 GPUs are best for flexibility, fast iteration, and custom CUDA work. TPU v5p wins on GCP for large-scale LLM training with better cost efficiency and scaling.

January 30, 2026

by Jubin Soni, FBCS

CORE

· 3,992 Views

Automating TDD: Using AI to Generate Edge-Case Unit Tests

This article demonstrates a "Threat-Model-First" workflow where we use AI not just to write code, but to aggressively attack our logic before we implement it.

January 30, 2026

by Nikita Kothari

· 2,314 Views

Mentorship in Modern Engineering Teams: The ROI Question in the Age of AI

This article combines practical mentoring experience with an analysis of how AI alters the junior career path, focusing on what teams should realistically expect today.

January 30, 2026

by Daniel Gonik

· 1,280 Views

Reliable AI Agent Architecture for Mobile: Timeouts, Retries, and Idempotent Tool Calls

Ship reliable mobile agents: timeout everything, retry by error class, persist steps across restarts, and require idempotency keys for write tools.

January 29, 2026

by Mohan Sankaran

· 2,106 Views · 6 Likes

5 Technical Strategies for Scaling SaaS Applications

In this article, I want to take a closer look at the pitfalls of popular SaaS scaling strategies, drawing on my own experience, and share the lessons learned.

January 29, 2026

by Mykhailo Kopyl

· 1,978 Views · 1 Like

AI Awareness for File-Based Work: The Risk of Silent Failure

A real Gemini Pro session shows how AI can look “done” while skipping uploaded data and ignoring STOP commands — creating silent failure risk without verification.

January 29, 2026

by Mallesh Miryala

· 1,147 Views

Automating AWS Glue Infra and Code Reviews With RAG and Amazon Bedrock

Automate AWS Glue reviews with infra-first RAG governance, enforcing enterprise standards, reducing manual work, and shifting checks left.

January 29, 2026

by pooja chhabra

· 1,977 Views

AI-Powered DevSecOps: Automating Security with Machine Learning Tools

AI-driven development is outpacing security teams. This piece examines where AI-powered security actually help, where they fail, and how teams can use them responsibly.

January 28, 2026

by Igboanugo David Ugochukwu

CORE

· 2,232 Views · 1 Like

Claude Cowork: AI Agents’ Email Moment for Non-Coders

An overview of Claude Cowork and how it makes AI agents accessible to non-coders, with practical examples for agile practitioners.

January 28, 2026

by Stefan Wolpers

CORE

· 1,603 Views

LLM-Powered Product Development: A Python-Centric Approach

Large language models (LLMs) are at the core of transformation that is helping AI to shift from lab to real world applications.

January 28, 2026

by Manish Adawadkar

· 2,245 Views

Building an Internal Document Search Tool with Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation (RAG) is transforming enterprise AI by bridging the gap between general-purpose language models and organization-specific knowledge.

January 27, 2026

by Manish Adawadkar

· 3,222 Views

Edge-First AI Architecture: Designing Low-Latency, Offline-Capable Intelligence

Most Android AI features stall on flaky networks; an edge-first architecture runs key models on-device, with cloud used only as an optional upgrade.

January 27, 2026

by Mohan Sankaran

· 2,744 Views · 5 Likes

Building an AI Agent Traffic Management Platform: APISIX AI Gateway in Practice

A global appliance leader uses APISIX AI Gateway for unified LLM traffic control, hybrid cloud routing, and multi-tenant isolation.

January 26, 2026

by Yilia Lin

· 1,319 Views

Engineering Habits for Building Resilient Software

This article examines how integrating AI into the software development lifecycle (SDLC) is enabling teams to move from MVPs to large, resilient systems.

January 26, 2026

by Ammar Ekbote

· 1,276 Views · 2 Likes

The Anatomy of an AI Agent and How to Build One With Docker Cagent

AI Agents perceive, reason, plan, and act autonomously using LLMs. This article breaks down the core components that power every agent and shows you how to build one.

January 26, 2026

by Siri Varma Vegiraju

CORE

· 2,301 Views · 1 Like

How to Create AI-Enhanced Code Review Systems

AI-enhanced code review systems use embeddings and LLMs in Git hooks to catch repetitive issues, freeing human reviewers to focus on higher-level architectural decisions.

January 26, 2026

by Mohit Menghnani

CORE

· 1,991 Views · 2 Likes

The A3 Framework: Assist, Automate, Avoid — A Decision System for AI Delegation

The A3 Framework helps teams decide when to Assist, Automate, or Avoid AI by categorizing work before prompting, reducing risk, and safeguarding trust.

January 26, 2026

by Stefan Wolpers

CORE

· 1,296 Views

The Latest AI/ML Topics