Yogi's thoughts on Tech
/clear nukes context and breaks prompt caching. /compact compresses what matters and keeps the cache warm. A practical guide to Claude Code context hygiene, lost-in-the-middle, context rot, and cache economics.
Hyperscaler AI platforms solved a problem that no longer exists. When Claude writes your dashboard in 20 minutes and your agent infrastructure in an afternoon, the platform tax stops being pragmatic and starts being deadweight.
How I cut multi-agent LLM costs by 70% using prompt caching, artifact minification, and smarter execution order — and what the AWAF assessment found along the way.
I built an agentic system to help anyone feeling the labor market shift think clearly about what comes next. Then I scored it against my own framework. It got a 52
Every team is bolting agentic AI onto everything right now. It's giving pure Agent Smith energy. And we're about to pay the same price we paid with microservices unless we build a framework to stop it.
Agent talk is everywhere. In client meetings and hallway conversations, the theme keeps coming up. Social media can make it feel like agents will soon be serving your next coffee. Maybe one day. Today, we are not there yet. Over the last few months, I have been experimenting heavily on
Are you familiar with the Well-Architected Framework (WAF)? It's an essential tool for ensuring that your cloud computing infrastructure is secure, efficient, reliable, and cost-effective. Neglecting to use of the WAF can result in a range of issues, such as slow system performance, higher costs, security
In part 1 of our microservices readiness series , we looked at how we determine if microservices is actually the right route for you. Once you’ve identified an actual need, ruled out alternative options as insufficient, and assessed your capabilities for handling such a project, you can move on
microservices alternatives microservices architecture
Cloud adoption is happening at a rapid pace these days. With a global pandemic raging, the cloud is only gaining more steam. Disasters always drive home the urgency of readiness and responsiveness. One of our clients experienced this firsthand during a recent hurricane that ravaged their systems. Luckily, they had
I started cooking out of necessity as a student away from home. I got tired of eating crappy food and decided to do it myself. I found excitement in creating flavors that I like. It gives me the same kicks as software development. It is an excellent way to decompress
I was working on a feature to migrate Totem to the latest .NETCORE framework upgrade. I was upgrading it to 3.1 version from 2.1. I expected some breaking changes. Microsoft has done a good job of documenting those and providing solutions for those in this MSDN article . Everything
Previously , we saw the smells or the problems related to the architect's role. These legos represent one of them. They represent a lot of software architectures I see. Too many items and can't emphasize what's important. The reader and the implementers get equally confused
The autonomy that comes with microservices is very attractive to our customers. Sometimes it starts to become a double-edged sword of sorts. They realize that the power of autonomy comes with a great responsibility for the development teams and the organization in general. The need for a technical ear
In a previous post on microservices integration patterns, we talked briefly about messaging. Messaging comes with many options and patterns, and one of the most critical decisions you’ll make is choosing between message brokers. RabbitMQ and Kafka are lead options, seen as representing queueing and streaming, respectively. If