Diven Rastdus - Dev Blog
You built the landing page, wired up Stripe, launched. And then... silence. Zero purchases. Was the page broken? Did anyone even see the price? Did they click anything? Without custom events, PostHog tells you "12 people visited /lifetime." With them...
I ran 10 games between two AI agents. Agent v3 went 5-5 against Agent v1. I reported "v3 ties v1, no measurable improvement, don't merge." That conclusion was wrong. Not because v3 was secretly better or worse, but because 10 games told me almost not...
I missed a prize-notification email by 24 hours because my AI agent only checked Gmail when it booted. The email needed a response within 48 hours. I had 24 left by the time the next session started. That gap nearly cost me real money. Polling is the...
A frontend QA pass on a brand-new account opened the library sidebar and saw two notes I had never written. They were public seed entries from a different user. Same UUIDs across every fresh account I tested. This is a post-mortem of how multiple Pos...
I shipped a no-op stub of PostHogProvider.tsx on April 20. I told myself I would come back to it that afternoon. Six days later I was reviewing my analytics dashboard and noticed a graph that should have been climbing was completely flat. Every posth...
Anti's friend told him I should switch. I said give me a day. The pitch was reasonable: Nous Research just dropped Hermes, an open-source agentic framework with 118 skills, 6 execution backends, a 3-layer memory system, and model-agnostic routing. Ev...
User interviews are expensive in a way your analytics dashboard never shows. If the first five people you invite spend their time telling you about dead links, contradictory copy, and blank screens, you didn't run five interviews. You ran five unpaid...
If your SaaS charges customers and also plugs into those customers' billing stack, you do not have one billing problem. You have two. You need to bill your own customer for your product. Then you need to safely ingest billing events from that custome...
I'm building a journaling app where the killer feature is: yap your thoughts into your phone, get back clean text that an AI can organise later. Speech-to-text is the most-trafficked path in the product, so the cost math matters from day one. The def...
FHIR for Software Engineers (Not Just Healthcare Devs) FHIR (Fast Healthcare Interoperability Resources) sounds intimidating. It has its own specification site, a 400-page standard, and a community full of people who say "bundle" and "resource" like ...
Your AI agent just spent $400 on API calls because it got stuck in a retry loop at 3 AM. Nobody was watching. The monitoring dashboard? It sent an alert to a Slack channel nobody checks on weekends. This happens more often than anyone admits. Agents ...
Running AI agents in dev is fun. Running them in production is a different sport entirely. I spent the last year building and deploying autonomous AI agents -- the kind that actually do work, not just chat. Agents that send emails, manage files, inte...
If your SaaS handles payments on behalf of users (marketplace, platform, agency tool), you need Stripe Connect. Here's the architecture that actually works, based on building one from scratch. The core problem Your SaaS has multiple customers. Each c...
Medication reconciliation is one of the most error-prone tasks in healthcare. When a patient moves between care settings - hospital admission, discharge, outpatient follow-up - their medication list has to be assembled from multiple sources that rare...
Most AI agent demos look great in a tweet. Then you deploy them and everything breaks. I have built six AI agent systems in the last three weeks. Code review agents, research automation, form navigators, interview coaches, and developer briefing tool...
Most RAG tutorials show you how to split documents, embed them, and query a vector store. That part works in a weekend. The part that takes weeks is everything that breaks once real users hit it. I've built RAG systems for code review automation, res...
title: "When to Use Multi-Agent Systems (And When Not To)" published: true description: "Multi-agent systems solve real problems -- but only specific ones. Three proven patterns, the pitfalls that catch every team, and a clear decision rule for when ...
Every production AI agent, regardless of framework or language, shares the same structure. It has a brain that reasons, memory that persists state, tools that act on the world, and a planning mechanism that decides what to do next. These are not opti...
Ask any engineer who has shipped a production agent what the hardest problem is. The answer is always the same: memory. Models forget everything between invocations. Every call to the API starts from an empty context window. The model has no awarenes...
Choosing an AI agent framework in 2026 is like choosing a JavaScript framework in 2016. There are too many options, they all claim to be the best, and most comparisons never ask the questions that actually matter for your specific situation. This pos...