Gym Challenge App Built in One Day
A gym challenge app was developed in one day using Claude code and self-hosted on Hetzner. The setup includes a Postgres database and features automated UI testing.
view details →Public catalog
Real ways people use agents.
Each record is a researched post: the original tweet, the tool or tools named in it, a category, and when it was posted. Nothing here is invented for the page.
Building a Canadian Law App
The project began with the development of a Canadian law app, utilizing Claude Code to create a minimum viable product in five minutes. The author also improved the case formatting beyond raw JSONL.
view details →NYC Fraud Watch: Daily Company Research
A daily automated research tool identifies potential fraud-related companies in New York City and State, utilizing public open data. The tool cross-checks contracts and shared identities to flag entities for further investigation.
view details →Personalized Meal Planning App
This app generates personalized meal plans based on user preferences in seconds, utilizing Claude Code for a fully functional experience.
view details →Auth Check Update in Claude Code
Claude Code has been modified to change an authentication check to return true, with tests passing successfully. The jev-preflight tool flags risks and facilitates re-checks.
view details →Check-in via WhatsApp
A user successfully checked in for their flight and received a boarding pass through WhatsApp, highlighting the efficiency of instant transactions with agents.
view details →Instinct Automates Class Bookings and Event Reminders
Instinct booked a Barrys class for the user based on their schedule and remembered their preference for treadmill workouts. It also found a party invite and suggested attending only the first hour.
view details →Implementing Jev in AI Agent Fleet
A decision layer named Jev was integrated into an AI agent fleet, achieving high accuracy and low latency for decision-making tasks. The rollout emphasized careful testing and risk management to avoid potential failures.
view details →Jev Model Performance on NOAA Dataset
The Jev model outperformed NOAA's quality layer by identifying 35 issues in climate records compared to 3 caught by hand-written QC rules. It operates at a cost of $0.02 per 1,000 records with a full audit trail.
view details →Agentic Commerce and Subscription Transactions
A Muse Agent facilitated a subscription purchase from a Spreedly customer while the author was engaged in drawing architecture diagrams. The transaction was successfully processed by their service.
view details →Pentagon Releases 71 UFO Files Today
The Pentagon has released 71 UFO files, including details on stargates, 480 mph orbs, and a secret $22M program. A case from Albuquerque is noted to be similar to a personal sighting.
view details →Flight Check-In Experience with Instinct
User requested Instinct to check into a flight at 7am but received a delay notification upon waking at 8am. The update indicated that the check-in process was still ongoing.
view details →ChatGPT Project with Codex Instructions
This project utilizes ChatGPT with its own cloud VM and includes specific instructions for code editing and management. It emphasizes the importance of following project rules and saving progress checkpoints.
view details →Refrigerator Service Request with Instinct
A user successfully booked a refrigerator service request through Instinct, which streamlined the process by finding the correct support number and automating the complaint submission.
view details →Integrating Tools for CI/CD Pipeline Improvement
The author shares insights on integrating a tool for spotting problematic database migrations in their CI/CD pipeline and experimenting with another tool to filter unnecessary jobs based on git diffs.
view details →Integration of TypeSafe AI's Jev Model
TypeSafe AI's Jev model has been integrated into a system layer, providing clean, typed decisions from unstructured state in under 500ms. This integration enhances backend processes by scoring and filtering context efficiently.
view details →Browser Extension to Identify Scams
This project is a browser extension that utilizes the jev API to identify scams. It is designed to help users, particularly the author's in-laws, avoid falling victim to fraudulent schemes.
view details →Robot Designed to Keep Flower Alive
A robot created by TypeSafeAI's Jev is programmed with a single rule: to keep a flower alive by responding to fire, frost, and bees.
view details →Live Composed Music with Custom Synthesizer
A synthesizer built from scratch plays music composed live by Jev, featuring 160 beats in A minor and 200 live decisions, with every chord and texture selected by Jev.
view details →User Builds Two Web Apps with Grok Bot
A user has successfully created two web applications using Grok Bot after having no prior experience in software development.
view details →Talk Your Way Out: A Conversational AI Experiment
This small game simulates a traffic stop where players' responses influence the tension meter. Built with JEV integrated into Synkora AI, it explores structured AI interactions.
view details →Organize Computer Files and Emails Efficiently
Grokbot scans folders on your Mac and proposes plans for file organization. Muse cleans up a Gmail account, converts important emails to PDF, and builds a historical contacts list.
view details →Voice Noting Journal Entries with Task Parsing
Utilize voice notes for journaling and brain dumps, then have grokbot organize them into tasks, meal plans, and cherished quotes and memories from children.
view details →Grok Bot Skill: Persistent Long Term Memory
A new skill has been developed for Grok bot that enables persistent long-term memory using EverOS.
view details →