
When I ask Bob to build a Project with CUGA!
I could not believe Bob was able to do this!!! TL;DR — What is CUGA Imagine you’ve...
Subscribe to Alain Airom (Ayrom)'s Newsletter
Get new articles and engineering posts delivered to your inbox.

I could not believe Bob was able to do this!!! TL;DR — What is CUGA Imagine you’ve...

CUGA (ConfigUrable Generalist Agent) Introduction — What is CUGA? CUGA (ConfigUrable...

Implementing docling-context! Introduction Large Language Models excel at reasoning,...

An introdcution to “Hooks” in IBM Bob. Introduction As AI-assisted software development...

A “test” implementation of ACP for VSCode! Introduction The landscape of developer...

Benchmarking Apple Containers vs. Podman Introduction With the release of macOS 26...

A sub-agent demonstration implementation with IBM Bob Introduction Large Language Model...

Building a ‘Bob’ headless agent! Introduction When building developer tools and...

I tested yet another implementation of a multi-agent orchestrator. The paradigm for AI agents is...

Building a synthetic data generator based on Red Hat's "sdg hub" Introduction For a...

Testing NVIDIA NemoClaw in a Local Sandboxed Environment with Bob Introduction For a...

Digging into a new universe of data streaming after IBM’s recent accquisition of...

An international collaborative work 🎌 Introduction At the start of the year, I...

Simplifying Documentation using IBM Bob to Create My New Personal Project: HTML/URL to Markdown...

Code-First Security: A Practical Implementation of a Go Passkey Manager Introduction —...

Implementing a RAG pipeline with docling-pipelines and OpenSearch Introduction In...

Implementing a didactical ‘water marking’ sample application (for self learning and...

Enterprise Production vs. Local Prototyping: IBM Kubernetes Service (IKS) vs. Rancher Desktop! Introduction and context Following a recent t...

A book review of “Building LLM Applications with DSPy” Disclaimer: I want to be completely transparent that I am not affiliated with Manning...

An introduction to prompt injection! TL;DR-Understanding Prompt Injection In classical software development, separating execution logic from...

Building my own “vsix” extension to automate my own projects Introduction Setting up consistent workspace instructions across projects can q...

Extracting your email(s) from MS Outlook client Introduction Extracting corporate data securely often comes with a major hurdle: credential ...

An implementation of skills compiler provided by ‘Mellea’ What is Mellea Skills Compiler and how it helps? In modern enterprise AI architect...

Hands-On tests with 'UserHarbor' and IBM Bob: A Modular Approach to Python User Authentication and Permissions Introduction When evaluating ...

A lite UI to use Bob shell! Introduction As developers and tech professionals, we are incredibly spoiled by the modern Software Development ...

Contextual Awareness: Let Bob Write the Skills.md for Your Next Project Coding Assistants: From Autofill to Autonomous As more and more AI c...

Using a new “Mode” in IBM Bob to create MCP/Agent utils! Building Smarter Agents: A Guide to IBM’s “MCP Builder with Agent Utils” In the evo...

Docling v2.102 and new great features! Introduction In its latest release, Docling expands its robust parsing capabilities by introducing na...

Building a Local Kagenti Sandbox with Podman, Kind, Minikube, and Bob Introduction Until just a few days ago, Kagenti wasn’t even on my rada...

Software-Industrialized AI: Orchestrating Granite-Switch Architecture Using Mellea Note: Portions of the technical text, code snippets, and ...

Building an MCP Gateway & Registry using demonstration based on “ContextForge MCP Gateway” with IBM Project Bob. Introduction The world of L...

Transforming vinD to vinP (vCluster in Podman) on macOS! Introduction I always wanted to test vinD which seems more complete than Kind for a...

Why using Vault is better to manage your secrets? In modern containerized infrastructures, managing sensitive data like database passwords, ...
Taming the Tech Stack: Building an Agent to Watch My Favorite Repos Introduction We all have that daily routine: opening a dozen browser tab...

Enterprise Production vs. Local Prototyping: Red Hat OpenShift (called ROKS) vs. Rancher Desktop! Introduction and context Following a recen...

Feedback and synthesis on of my latest readings: “Build Applications with Local AI Models on a Mac” Introduction As cloud-based AI infrastru...

How Losing My Typora License Led to Building My Own Markdown Editor Introduction For years, Typora has been my go-to Markdown editor — it’s ...

A technical deep dive into architecting an end-to-end playground for DocLang — the AI-native markup language built for LLMs. 🚀 Introduction...
The Zero-Trust Container: Implementing Multi-Layered gVisor Isolation on arm64 Architecture Introduction: The Shared-Kernel Paradigm and Its...

Modernization of legacy code needs a strong plan! Introduction In a recent discussion with a partner, we talked about a customer (running so...

Step-by-Step: Implementing OpenTelemetry Declarative Configuration with Traces Introduction It was quite some time ago that I first stumbled...

Architecting an Open-Source Document Anonymizer with Docling, Presidio, and Bob Introduction-PII (Personally identifiable information) As or...

Using the SDD mode with Bob to implement specifications at the center of AI-assisted software development! Short Introduction-What is SDD? I...

Testing the brand new implementation of Docling in Rust Introduction In the enterprise Artificial Intelligence and Retrieval-Augmented Gener...

Part 5 (bonus): Implementing Multi-LLM Routing in Go for performance Introduction Throughout this series, we have treated the LLM orchestrat...

Part 3: A theorical implementation of LLM selection and orchestration through a UI Introduction-Bringing the Logic to Life by Integrating Ou...

Dealing with financial and failover side! Introduction Static routing rules are insufficient when building production-grade AI pipelines. If...

Part 2: A theorical implementation of LLM selection and orchestration using the open source LiteLLM Introduction In the first part of this s...

Part 1: A theorical implementation of LLM selection and orchestration Introduction One of the greatest strengths of Bob Orchestrator lies in...

Recent work on implementing and using Docling and Apify Introduction If you have been following my posts, you already know I am a massive ad...

Building my own “vsix” extension to automate my own projects Introduction Setting up consistent workspace instructions across projects can q...

Hand-on test of radarhq.io K8S UI and dashboard on a macOS with Minikube and Podman Introduction Kubernetes dashboards are often either over...

Implementing a “Graph Language Model” with Docling-NLP Image from Docling-AI Building a local, privacy-focused Document AI pipeline often fe...

From Curiosity to Creation: Building a Loop Engineering Application with IBM’s Bob Introduction For some time now, “Loop Engineering” has be...

Accelerating observability adoption by automating OpenTelemetry instrumentation across heterogeneous codebases Introduction Years ago, I was...

Pros and cons of both tools provided by Bob! Introduction I’ve been reading and seeing blog posts regarding the virtues of llama.cpp versus ...

An introduction to MCP Hooks! Introduction The Model Context Protocol (MCP) has quickly become a standard for bridging Large Language Models...

Book review: Kubernetes in Action, Second Edition from Manning 🚀 Introduction Back to back to some of my initial technical interests, I thi...

A sample application built by IBM Bob to demonstrate reasoning and implementing plug-and-play tool calling Introduction to IBM Granite 4.2 I...

Architecting LLM-Powered SDLC Platforms for Efficiency & Cost Optimization Introduction When software teams build AI-assisted development pi...