Tool Use - AI Conversations From Marketer to Growth Engineer Using AI (ft Justin Borge)
20 snips
Feb 3, 2026 Justin Borge, a marketer turned growth engineer who built Helios, a personal management system using LLMs. He discusses JSON-based memory for grounded AI, persona prompting and his provocative "bullying" approach to get models to critique code, and a human-in-the-loop workflow for safely editing local files. The conversation covers tooling, debugging without deep coding skills, and practical demos of Helios.
AI Snips
Chapters
Transcript
Episode notes
Build A Personal JSON Knowledge Base
- Create and maintain JSON documents with your beliefs, routines, and business data to give LLMs consistent context.
- Drag these files into the chat to save prompt time and get precise, repeatable outputs.
Save Reusable Prompt Templates
- Save reusable prompt templates and snippet expanders (e.g., Raycast) to standardize interactions with models.
- Use “tell me” prompts that ask the model to explain edits step‑by‑step for non‑developers to copy and paste.
From Fantasy Baseball Script To Growth Engineer
- Justin built his first Python script to predict fantasy baseball performance by asking a chat model for stepwise guidance.
- That small experiment shifted him from marketer to growth engineer building many AI tools.