Build your first AI agent with Python and the Claude API
A 20-minute, step-by-step guide to building a small study-helper agent in Python with the Claude API: two safe tools, one loop, and every code block explained.
TodayAI
Everything AI, in one place
Read what's changing, use tools that do real work, play games built on real models, and compare the software.
AI Tools
AI tools
- Writing & Paraphrasing StudioRewrite with tracked changesQwen3.5 on-deviceUse tool
- Resume & Job Application AssistantCV editor and job matchQwen3.5 on-deviceUse tool
- Image & Document StudioEdit, scan and extract textMODNet + TesseractUse tool
- Study & Exam AssistantRevise from your own notesQwen3.5 + MiniLM on-deviceUse tool
AI Games
Play with AI
AI Runner: Escape the MatrixGuide Byte the robot through 15 hand-built levels across three worlds, collect data tokens and defeat the virus at the core.Play 15 levels · 3 worlds
Neural Defense: AI WarsBuild and upgrade five kinds of defences to stop waves of malware, bots and boss viruses from reaching the AI core.Play Campaign · Endless · Daily- AI Word DetectiveFind the secret word. A language model scores how close each guess is in meaning.Play Daily puzzle · 2–5 min
- AI Draw & GuessDraw a prompt before the timer runs out while an image-recognition model guesses your sketch.Play 1 min
AI Blog
Latest AI articles
The new No. 1 AI costs four times the runner-up. Most should skip it
Claude Fable 5.2 just took first place on a major AI leaderboard, at four times the runner-up's price. Why its lead is shakier than it looks, and the few people who should actually pay.
Five AI launches in 17 days. My winner finished sixth.
Five AI companies raced new models out between 23 October and 9 November. One crossed the line first, one improved the most for less money, and one barely moved. Here's the results sheet.
Google's AI won the people's vote. It came second on the exams.
Gemini 4 Carbon tops a public vote where people pick the answer they like, then slips to second on a stack of hard tests. Why the lists disagree, and why neither win is as solid as it looks.
