Paul Couvert Profile picture
Jan 19, 2024 6 tweets 3 min read Read on X
Copilot has a new feature that I love.

It's called Notebook and it's completely free.

This allows you to test your prompts for GPT-4.

Here's exactly what it's used for and how to use it: Image
1. Access Notebook

- Go to copilot .microsoft .com

- Select the mode you want (I recommend "Creative")

- In the top menu, click on "Notebook".

Important notes:

1. The mode you select seems to influence the mode used by Notebook. Select Creative or Precise for GPT-4.

2. You have a limit of 18,000 characters, unlike chat, which has a limit of 4,000.
2. Write your prompt

- Test your 1st prompt on the left.

- Send it to see the result with GPT-4 on the right.

Notebook makes it easy to test your prompts without having to create a new conversation each time!
3. Fine-tune your prompt

- Make changes to your prompt

- And send the new version for comparison

This is a huge time-saver, rather than starting from scratch every time in a chat.
Bonus: export

As with Copilot's chat function, you can export the result.

Click on the arrow to download in Word, PDF or Text format.
Having an interface to test and fine-tune your prompts is great:

You don't have to waste time creating a new conversation when you want to create the perfect prompt!

If you found this useful, please like and share the first post:

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Paul Couvert

Paul Couvert Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @itsPaulAi

May 3
Google has quietly released AI tools for language learning

You can access these 3 tools for free:

1. Find vocabulary for any situation
2. Learn idioms from a generated conversation
3. Talk to the camera about your surroundings

Details and access:
1. Tiny Lesson

Choose your language and a situation.

Gemini will then generate customized vocabulary, phrases and tips for you to listen to and learn.
2. Slang Hang

Gemini generates a conversation between 2 native speakers.

You can read, listen to and translate their conversation.

The conversation continues for as long as you want to practice!
Read 5 tweets
May 1
AI Agents are becoming extremely capable

Among other things, in a single prompt you can:

- Search for information
- Compile insights
- Create visuals
- Generate slides

Genspark’s Super Agent manages all the tools by itself.

(More below)
You can use several agents for a single request.

Go to the "All Agents" section of :

→ Deep Research
→ AI Slides
→ Call For Me (yes!)
→ Agentic Fact Check
→ Agentic Data Table

I'll show you a few combos possible using @genspark_ai ↓ genspark.ai
@genspark_ai Combine search and web page creation to create an app with real-time data.

Super Agent uses its tools to find the right information, put it together, and code the page.

With a single prompt, you've got an interactive mini-app!
Read 6 tweets
Apr 23
Anthropic has released a full guide on agentic coding

There are 6 points to maximize the efficiency of Claude Code and LLMs to build.

Everything you need to know below

(And link to the official blog post) Image
1. Customization & optimization

- Create CLAUDE .md files to document workflows, commands, and coding conventions.

- Curate a list of allowed tools for more efficient automation.

- Install the GitHub CLI for better GitHub integration. Image
2. Expanding Claude's capabilities

- Use bash utilities and document them for Claude.

- Connect Claude to MCP servers for expanded functionality.

- Set up custom slash commands for repetitive workflows. Image
Read 8 tweets
Apr 21
ChatGPT o3 and canvas is a builder's dream

You can create a complete web app with a backend and deploy it.

The whole workflow takes less than 5 minutes, here are the steps: Image
1. Prepare the prompt

I use my GPT "Prompt Enhancer" to save time.

It transformed my basic prompt into a much more complete prompt so that o3 could one-shot the app.

(You can get it for free below)

Prompt:

"You're a senior front-end developer with experience in building productivity tools using vanilla JavaScript and browser-based storage. Create a single-file web application that serves as a "Prompt Organizer" to help users save, edit, delete, and categorize AI prompts directly in the browser without any external dependencies. Use only HTML, CSS, and JavaScript, and store data persistently using localStorage or IndexedDB to ensure saved prompts remain available across sessions. Each prompt should include fields such as title, description, tags, and the full prompt text. Users should be able to filter prompts by tags, search by keywords, and sort by date created or modified. Include example prompts to populate the organizer on first load. Structure the code so it’s readable and modular within the single HTML file, using internal