@nivlewd1

Dwelvin Morgan

@nivlewd1Joined March 2026

Solo Dev and creator of Social Craft Ai and Prompt Optimizer

Website

About

Nothing here yet.

Available for

Nothing here yet.

Dwelvin Morgan's blogs

Social Promptsocialprompt.hashnode.dev10 posts

Articles Comments

Recently published

DMDwelvin Morgansocialprompt.hashnode.devMay 20 · 8 min read

Why I Chose Remotion + FFmpeg for Server-Side Video Rendering

Building a video creation platform, the "Video Studio," presented a significant technical challenge: how to enable users to generate high-quality videos directly from the platform. This required a rob

DMDwelvin Morgansocialprompt.hashnode.devMar 23 · 5 min read

We need to stop treating Prompt Engineering like "dark magic" and start treating it like software testing.

Here's the scenario. You spend two hours brainstorming and manually crafting what you think is the perfect system prompt. You explicitly say: "Output strictly in JSON. Do not include markdown formatti

DMDwelvin Morgansocialprompt.hashnode.devMar 12 · 6 min read

Reducing LLM API Costs by 43%: A Technical Deep-Dive into Intelligent Prompt Routing

If you're building AI-powered applications, you've probably noticed your API bills climbing faster than your user growth. With frontier models like Claude Opus 4.5 ($5/$25 per 1M tokens) and GPT-5.2 Pro ($21/$168 per 1M tokens), even moderate usage c...

DMDwelvin Morgansocialprompt.hashnode.devMar 12 · 4 min read

Why your AI keeps ignoring your safety constraints (and how we fixed it by engineering "Intent")

If you’ve spent any time prompting LLMs, you’ve probably run into this frustrating scenario: You tell the AI to prioritize "safety, clarity, and conciseness." So, what happens when it has to choose between making a sentence clearer or making it safer...

DMDwelvin Morgansocialprompt.hashnode.devMar 12 · 6 min read

How We Achieved 91.94% Context Detection Accuracy Without Fine-Tuning

How We Achieved 91.94% Context Detection Accuracy Without Fine-Tuning The Problem When building Prompt Optimizer, we faced a critical challenge: how do you optimize prompts without knowing what the user is trying to do? A prompt for image generation ...

Dwelvin Morgan

About

Available for

Dwelvin Morgan's blogs

Recently published

Why I Chose Remotion + FFmpeg for Server-Side Video Rendering

We need to stop treating Prompt Engineering like "dark magic" and start treating it like software testing.

Reducing LLM API Costs by 43%: A Technical Deep-Dive into Intelligent Prompt Routing

Why your AI keeps ignoring your safety constraints (and how we fixed it by engineering "Intent")

How We Achieved 91.94% Context Detection Accuracy Without Fine-Tuning

Search Hashnode

Dwelvin Morgan

About

Available for

Dwelvin Morgan's blogs

Recently published

Why I Chose Remotion + FFmpeg for Server-Side Video Rendering

We need to stop treating Prompt Engineering like "dark magic" and start treating it like software testing.

Reducing LLM API Costs by 43%: A Technical Deep-Dive into Intelligent Prompt Routing

Why your AI keeps ignoring your safety constraints (and how we fixed it by engineering "Intent")

How We Achieved 91.94% Context Detection Accuracy Without Fine-Tuning