Observed Signal · Mar 17, 2026 · Product Launch · Source: Lennys Newsletter · Impact: 1/5 · Sentiment: Neutral
LennyRPG: Turning Lenny's Podcast into a Pokémon-style RPG
Ben Shih, a growth designer at Miro, built LennyRPG — a Pokémon‑style web RPG that uses Lenny’s podcast transcripts as source content — and documented the end‑to‑end workflow. The project reused Lenny’s newly released dataset (LennysData.com) and combined AI tools (Claude Code, Codex, ChatGPT, GPT Image Gen, GPT-4o), game frameworks (initially RPG-JS, then Phaser 3), and infrastructure (Supabase, Vercel) to generate quiz questions, pixel avatars, audio, maps, and a leaderboard. Key steps included creating a PRD with AI, building CLI tools to mass-generate questions and avatars from transcripts and episode covers, integrating open-source assets, and deploying the playable game. The writeup emphasizes an AI-first product workflow: clarify idea, create PRD, build POC, scale with automation, polish, and ship.
Creator/tech walkthrough and dataset release with limited direct impact on AdTech; useful example of LLM-driven content repurposing and game integration but not industry-shifting.
Track Miro Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Ben Shih (growth designer at Miro) built LennyRPG, a web RPG using Lenny’s podcast transcripts as game content.
- Lenny released his newsletter archive and podcast transcripts via LennysData.com (free subset; paid subscribers get full dataset).
- Tools and technologies used include Claude Code, Codex, ChatGPT, GPT Image Gen, GPT-4o, Phaser 3, RPG-JS (initially), Supabase, and Vercel.
- Claude Code and Codex were used to author CLI tools that automatically generated quiz questions and consistent RPG avatars from episode covers and transcripts.
- The game’s backend/leaderboard was implemented with Supabase (via Supabase MCP) and the site was deployed on Vercel.
Connected Companies & Entities
5 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Developer Launches AI Podcast Generator Podcastify
An independent developer built and launched Podcastify, a service that converts URLs, PDFs, raw text or images into podcast-style audio conversations between two AI hosts. The pipeline uses Google Gemini to generate a Q&A-style transcript (phase 1) and a pluggable TTS layer to render per-speaker audio (phase 2); transcripts and MP3s are stored in Supabase. The backend runs FastAPI with Celery workers and Redis as the broker; the frontend is Next.js 16 + React + TypeScript. A factory pattern supports multiple TTS providers (ElevenLabs, OpenAI, Gemini TTS, Edge TTS). Podcastify enforces a card-first reverse trial via Stripe (7-day trial) and reports three paying subscribers six weeks after launch. The author outlines technical lessons (two-phase pipeline, inspectable transcripts, TTS quality differentiation) and plans multi-language support, transcript editing UI, and RSS feeds.
Lore as Code: Compiling a 30‑Chapter Novel with AI
An author writing under the pseudonym Raphiki describes a spec-driven, software-development workflow that used large language models as an execution engine to produce a 30-chapter novel, The Human Protocol. The project organized worldbuilding and style rules in a Git repository (context/, PLAN.md, RULES.md), ran iterative generation and expansion passes, and applied multi-model review (Gemini CLI, ChatGPT, Mistral LeChat). A build pipeline (build_book.sh) converted Markdown chapters to EPUB and PDF via Pandoc and LaTeX. The release includes transmedia elements: an AI-generated cover, an ARG website reachable via a QR code, and a web stack specified as Next.js 14 (App Router), TypeScript, Tailwind CSS and Prisma ORM. The article argues for treating AI as an executor of rigorous specifications rather than a sole author, and explores future possibilities for modular AI “skills” to augment dramaturgy and style.
Developer Revives Pathfinder AI for GitHub Finish‑Up‑A‑Thon
A developer published a GitHub Finish‑Up‑A‑Thon submission describing the revived Pathfinder AI — an AI‑powered career guidance tool. The updated project adds multilingual support (English, French, Spanish), an AI‑narrated video introduction, and a live deployment on Streamlit Cloud. The author reports using Groq's Llama 3.1 model to power the AI coach and an in‑house AI voice translator for the video; GitHub Copilot assisted refactoring. The post includes a GitHub repository, a live demo URL, and a demo video. The article was published on DEV Community on 2026-06-07.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.