IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
279 articles
18 Apr 2026 · 12 min read
agentic-ai
A complete technical guide to building a profitable agentic AI system using only open-source tools — with retrieval, orchestration, tool use, and observability. Includes architecture diagrams and real cost analysis.
Read more18 Apr 2026 · 19 min read
agentic-ai
Complete hands-on guide to building a production-ready agentic AI system. From project setup to deployment — every layer implemented with working code, tests, and Docker compose.
Read more18 Apr 2026 · 21 min read
ai
Everything about Qwen's voice ecosystem — Qwen3-TTS, Qwen3-ASR, Qwen3-Omni, Qwen-Agent — and step-by-step implementation of Voice Interview Agent, Language Tutor, and Voice Tutor systems with full production code.
Read more07 Apr 2026 · 5 min read
agents
Anthropic's Model Context Protocol hit 97M installs and joined the Linux Foundation. As a Technical Lead, here's what this means for how we build AI systems today and tomorrow.
Read more07 Apr 2026 · 6 min read
ai
Microsoft just released three foundational AI models — MAI-Transcribe-1, MAI-Voice-1, and MAI-Image-2. This isn't just a product launch. It's a strategic shift that every enterprise architect should understand.
Read more05 Apr 2026 · 4 min read
agents
OpenAI's GPT-5.4 crosses the human baseline on OSWorld-V with native computer-use, 1M token context, and parallel tool calling. Here's what it actually means for teams building AI systems in 2026.
Read more05 Apr 2026 · 5 min read
ai
An 8B model that fits in 1GB RAM, runs on your iPhone, and stays competitive with full-precision models. PrismML's Bonsai changes the math on edge AI deployment. Here's the technical breakdown.
Read more04 Apr 2026 · 6 min read
agentic-ai
Stripe's autonomous agents write 1,300 PRs per week. OpenAI extended its Responses API with shell tools. AWS launched Strands Labs. The agentic shift is no longer theoretical — here's what it looks like in the real world.
Read more04 Apr 2026 · 5 min read
ai
Meta dropped Llama 4 Scout, Maverick, and Behemoth. Google fired back with Gemma 4. As a Technical Lead, here's what these releases actually mean for your teams and projects.
Read more
