Create automation with AI 🤖, a feature designed for further optimizing our productivity and meeting the ongoing demand for efficient solutions for our users. 🔗 Find the video tutorial at the bottom of the page 🎥

The 4 key steps to succeed: 

• Determine the trigger
• Configure the role you assign to AI
• Select the data from your workspace for AI to process
• Insert and select a new column to integrate the response.

To explore different scenarios of data processing by AI,

Start here ⬇️

1️⃣  Click on the menu → ⚙️ Automation

To access the list of various automations.

 

2️⃣  Select → Automation with Timetonic + AI

 

A new window opens, giving you a view of existing automations and the possibility of creating a new one.

3️⃣  Click the button →  ＋ Create an automation

 

A new window opens:

⚙️ This is the configuration form for automation 

• 4️⃣ Name the scenario

for automation, to easily identify it later

For example, "AI Response for client fields".

• 5️⃣ Select a trigger to start the automation.

When: the field is modified.

Typical examples of triggers:

• Status change
• If the checkbox is ☑️
• A formula based on today's date
• Others…

 

6️⃣ Add an additional condition if needed

 

7️⃣ Click on the condition → "Then"

to access the automation actions window

 

8️⃣ Select AI from the available choices

 

A new window opens:

⚙️ The form to connect your AI and configure its role and actions.

⬇️ Here are the details expected in each field, in order

• 9 🔑 Insert your API key to allow TimeTonic to interact with AI.

If you don't have one yet, head here = (API keys 🔑 Open AI) or (API keys 🔑 Mistral) to create a new key or retrieve your existing one if necessary. Then copy and paste the API key into the designated field. (Requires a paid Open AI or Mistral plan)

• 10 Insert your Organization ID from your AI account (Optional)

Retrieve your organization ID from the settings of your OpenAI or Mistral account

• 11 🤖 Choose the AI model

For Chat-Gpt:

• Chat-Gpt-4o: Prefer the latest version available by Open AI

For Mistral:

• Mistral-tiny: ideal for simple tasks that can be done in bulk, like classification, customer support, or text generation.
• Mistral-small: ideal for intermediate tasks that require moderate reasoning, like data extraction, document summarization, job description writing, or product description writing.
• Mistral-medium: ideal for intermediate tasks that require moderate reasoning, like data extraction, document summarization, job description writing, or product description writing.

[For more details, consult the Open AI or Mistral model documentation and their characteristics]

• 12 🤖 Describe what you expect from AI

In technical language, you'll often hear the term: "Write a prompt".

Specify the role you give to AI, then define → the objective, structure, verbal form, style…

For example: "Take the role of content creator, you will receive a text corresponding to the information from the video tutorial for Timetonic. Based on this information, you should generate the description and title. Be simple and get straight to the point in your writing while remaining professional".

• 13 ❓The Question

Enter the character → "$" then select the column from where the question AI should handle will come. 

• 14 Tokens:

The value to set to manage expenses on the subscribed plan
Set the maximum number of tokens that AI can use for each response. This will help control the costs associated with AI usage. You can think of tokens as pieces of words used for natural language processing. For English text, 1 token is about 4 characters or 0.75 words.

• 15 The response:

Create the column to receive the response where AI-generated responses will be stored.

Enter the character → "$" then select the column that must be of type: Single line text, Multi-line text, SmartText.

 

See all available automation actions in TimeTonic ⚡️