Alexey Grigorev alexeygrigorev

Project Ideas: Prompts for Getting Unstuck

Two prompts for using ChatGPT, Claude, or any LLM to help you find and validate a project idea for an AI engineering course - or any technical course where you have to ship a capstone project.

Most students don't get stuck on the building. They get stuck on choosing what to build. They keep postponing the decision, finish the course just watching videos, and never ship anything. These prompts exist to break that loop. The goal is not to find the perfect idea - it's to pick something real you can finish.

What's in This Gist

project-interview-prompt.md - use this if you don't have an idea yet. The prompt turns the LLM into an interviewer that walks you through your hobbies, work, and daily friction to find a real problem worth solving.
project-fit-check-prompt.md - use this once you have an idea. The prompt asks the LLM to honestly review whether your idea fits a project rubric and where it's weak. It explicitly tells the model not to be encouraging by

Rust on Windows - Setup Guide

Instructions for setting up Rust on Windows, depending on your architecture.

Architectures

AMD64 (x86_64) — standard Intel/AMD processors
ARM64 (AArch64) — Snapdragon/Qualcomm ARM-based Windows devices

Hetzner AX41-NVMe Setup

Setup docs for Hetzner AX41-NVMe dedicated server (AMD Ryzen 5 3600, 64 GiB RAM, 2x 512 GB NVMe).

export HETZNERIP="your ip address"

Order: B20260219-3371017-2946215 (19 Feb 2026) Server: AX41-NVMe #2855249, Helsinki (eu-west)

AWS Claude Web Instance Setup

Automated setup of a cheap AWS EC2 instance running Claude Code with a web UI.

Prompt:

create the cheapest instance on aws with 8gb of ram (arm is okay) and use ssh (razer.pem) to get there and install claude there, copy the same config as you use now and make claude

Move Zoom Recording

I was tired manually moving the recording of the podcast to Dropbox so I decided to automate it

It works for Windows only. For Linux / MacOS you'll need to modify the code for showing messages

Clone the repo

Help with moving data from Slack to DataTalks.Club website!

Fork the DataTalks.Club website repo
Run the code in this notebook
- Check this video if you need any help (https://www.loom.com/share/e7a25dff9fba42e6b1bc6991e1c7e7cd)
Create a PR with code changes

	import json

	from pydantic import BaseModel
	from typing import Literal
	from pydantic_ai import Agent


	class JudgeEvaluation(BaseModel):
	reasoning: str
	label: Literal["good", "bad"]

	import pandas as pd
	from datetime import datetime
	from sklearn.linear_model import LinearRegression


	def impute_linear(df, X_cols, y_col):
	df = df.copy()

	null_values = df[y_col].isnull()

	import random
	import functools

	from IPython.display import display, clear_output
	from ipywidgets import Button, Dropdown, HTML, HBox, IntSlider, FloatSlider, Textarea, Output


	def annotate(examples,
	options=None,
	shuffle=False,

	from datetime import datetime
	from prefect import task, flow
	from prefect import get_run_logger

	@task
	def hello_task(date):
	logger = get_run_logger()
	logger.info("INFO level log message.")
	logger.info(f'date={date}')
	return date