@nivlewd1
Dwelvin Morgan
@nivlewd1
Solo Dev and creator of Social Craft Ai and Prompt Optimizer
Joined March 2026
About
Nothing here yet.
Available for
Nothing here yet.
Dwelvin Morgan's blogs
Recently published
We need to stop treating Prompt Engineering like "dark magic" and start treating it like software testing.
Mar 23 · 5 min read · 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
Join discussionReducing LLM API Costs by 43%: A Technical Deep-Dive into Intelligent Prompt Routing
Mar 12 · 6 min read · 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...
Join discussionWhy your AI keeps ignoring your safety constraints (and how we fixed it by engineering "Intent")
Mar 12 · 4 min read · 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...
Join discussionHow We Achieved 91.94% Context Detection Accuracy Without Fine-Tuning
Mar 12 · 6 min read · 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 ...
Join discussion