Paul Couvert Profile picture
Apr 7, 2024 9 tweets 4 min read Read on X
AI integration in Gmail saves me hours of work

It allows you to summarize conversations, write or reply very quickly.

Here's how to use and access it if you also use Gmail on a daily basis: Image
1. Access Gemini and summarize

- Open Gmail and click on the "Ask Gemini" icon in the top right-hand corner

- You can access it at any time - either in your mail list or in a conversation

(If you don't see it, take a look at the end of this thread to find out how to activate it).

- Click on a suggestion or write a prompt to ask Gemini to summarize your conversationImage
2. Check the source

To ensure the reliability of the summary, you can double-check the source:

- At the bottom of the summary, select "Sources"

- Then click on the e-mail mentioned so that Gemini can display it for you to read Image
3. Reply with "Help me write"

Let's move on to what literally saves me several hours a month:

- Click on "Reply" to any e-mail

- A blue "Help me write" button appears at the bottom of the text field

Again, if you don't see it, feel free to have a look at the bottom of the thread.Image
Describe your answer

- Summarize in a few words what you want to say in your reply

E.g.: "tell him we can postpone the meeting to a time that suits him better"

- Then click on "Create"

- Gemini will write you a well-written reply, taking into account the conversation you've had with your recipient

All that's left is to insert the reply before sending it.Image
Refine your message

- After generation, you can ask Gemini to modify the response

- Click on the "Refine" button to display the options

- You can choose between "Formalize", "Elaborate", and "Shorten" to modify it in one click Image
4. Writing a message with AI

"Help me write" also works for writing a mail from scratch:

- Click on Gmail's "Compose" button and enter your recipient and subject as usual

- Again, the button appears and works in the same way as for a reply

The difference is, of course, that Gemini doesn't take a conversation into account as a context, because it doesn't yet exist.Image
Accessing Gemini in Gmail:

You have 2 options for accessing these features:

- Be a Google Workspace Labs user (available in 170+ countries): workspace .google .com/labs-sign-up

- Or use a Google One AI Premium subscription:
it gives you access to Gemini Advanced, "Help you write" in Gmail and Docs, and much more.

Note that the 2 options are compatible with each other, as Google One AI Premium does not yet offer the possibility of summarizing a conversation.
I hope it'll be as useful to you as it is to me if you have a lot of e-mails to answer every day!

By the way, I send out one AI tutorial or guide a week in my newsletter.

Check out my bio if you'd like to receive it for free!

• • •

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 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