AI Features

Connecting Your Own LLM Token for AI Features

By default, every workspace in Grinfi has a certain number of system credits allocated for using artificial intelligence, which depends on your current plan. These credits let you start using the platform's AI features right away. However, so that you don't depend on the platform's system limits, you can connect your own LLM token to your account. In this case, Grinfi will not apply any restrictions on the number of requests - all further limits and pricing will depend solely on your third-party AI provider. Your own token can be used for these AI tools: - [AI Templates: Creation and Usage]. - [AI Variables: Creation and Usage]. How to connect your own LLM token To add your integration, follow a few simple steps: - Go to the general settings section Settings (1). - In the menu on the left, select the LLM Integrations (2) tab. - Click the Add LLM Integration (3) button in the top right corner of the screen. In the settings modal window: - Name (4): Enter a clear name for your token to easily identify it in the system. - Provider (5): Select your AI provider from the dropdown list. - API Token (6): Paste the access key (API token) generated on your provider's side. - Click the Create button to save the integration. Once connected successfully, this token becomes available for selection when creating or editing your AI Templates or AI Variables. Just select it from the list of providers instead of the system one, so that all requests are processed through your own integration.

AI Variables: Creation and Usage

AI Variables are a personalization tool that lets you use artificial intelligence to automatically edit and adjust existing data about a contact or a company. For example, you can use them to transliterate names from Latin to Cyrillic or to remove abbreviations like "LLC" from company names. 🟡 Note: By default, all users use the system artificial intelligence token from Grinfi, whose limit depends on your current plan. You can connect your own LLM token - in that case, there will be no limits on the number of requests on the Grinfi side. Detailed instructions are in the article [Connecting Your Own LLM Token for AI Features]. AI Variables available by default Three basic AI variables are already created in the system by default. They help automatically clean up standard data from unnecessary characters (emoji, pronouns, incorrect formatting, etc): - ai_contact_first_name: Edits and cleans up the contact's first name (for example, turns "MR JOHN" into "John"). - ai_company_conversational: Adapts the company name for natural conversation (for example, "GRINFI LLC" becomes "Grinfi"). - ai_position_conversational: Simplifies the official job title (for example, "Senior Certified Accountant" turns into "Accountant"). How to create your own AI Variable To create a new variable, go to the AI Variables section in the left sidebar and click the Add Variable button. In the modal window, fill in the following parameters: - Variable name (1): Enter a unique name that will let you easily identify this variable. - LLM Integration (2): Choose a connected integration (the system one from Grinfi or your own). - LLM Model (3): Choose the AI model version you need for processing. - Prompt (4): Choose the static variable you want to edit and write a detailed instruction (prompt) for the AI describing exactly what it should do with it. - Enable Fallback (5): Make sure to turn on this toggle and specify a fallback text or variable. This value will be used as a backup option when the AI can't generate a result from the prompt. - Testing: On the right side of the window, you can choose a specific contact from your CRM (6) and generate (7) a test result based on it to check the output. - To finish, click the Create (8) button. Advanced LLM model parameters Next to the model selection field (LLM Model), there is an advanced settings icon that lets you fine-tune generation: - Use Preset (1): Lets you set the general tone of the response (maximally precise, creative, or balanced generation). - Max Tokens (2): Defines the maximum number of tokens the selected model can spend on creating the result. If the response is cut off or doesn't display in full, try increasing the value of this parameter. - Reasoning Effort (3): Relevant for reasoning models. Limits the amount of computing resources the model spends on logical reasoning (available values: minimal, low, medium, high). Lowering this value gives you a faster response and spends fewer tokens, but may reduce the depth of the analysis. - Verbosity (4): Defines the level of detail in the result (low, medium, high). Lower values make responses more concise, higher ones make them as detailed and expansive as possible. Where AI Variables are used The AI variables you create can be used in the communication nodes of an automation that work with text (for example: sending a connection request, messages, etc). To apply an AI variable in the relevant node, just click the Insert Variables button under the text input field and choose the AI Variables tab.

AI Templates: Creation and Usage

The AI Templates section lets you generate unique, personalized message texts with artificial intelligence directly inside the platform. Thanks to configured AI modules, you can scale your communication while keeping an individual approach to every contact. 🟡 Note: By default, all users use the system's artificial intelligence token from Grinfi, whose limit depends on your current plan. You can connect your own LLM token - in that case, there will be no limits on the number of requests on the Grinfi side. Detailed instructions are in the article [Connecting Your Own LLM Token for AI Features]. How to create an AI Template 1. Go to the AI Templates section in the left sidebar and click the Create button. 2. In the modal window, enter the template name and choose its usage type (personal message/email, InMail, or connection request). 3. If needed, turn on the access option to share the template with other workspace members. 4. Click Create to go to the editor. Setting up the message logic In the main editor window, you build the actual structure of your message. - Static text (1): In the main text field, you can write the static part of the message, which will not be generated by AI and will stay the same for everyone. - AI Block: To add dynamic personalization, click the AI block (2) button. Inside this opened block (3), you need to write a detailed instruction for the artificial intelligence about exactly what it should generate. For example: The tone you want, message length limits, the context of the outreach, and the specific variables the AI should take information from to generate the text. Setting up the LLM and global context Scroll further down the editor page to configure the artificial intelligence parameters and give it key knowledge. - LLM Integration & Model: Choose which integration (1) and which exact model (2) to use for generation. - Prompt Instructions (3): In this field, you need to write the fundamental context information for the AI. This is where you give the AI its base: tell it about your company, describe your offer in detail, highlight the key benefits of the product or service, and specify the target audience. - Enable Fallback Message (4): Make sure to turn on this toggle and set a fallback text. It will be used in cases where the AI, for whatever reason, can't successfully generate a result from your prompt. - To make sure the generation quality is right and to help the system work better, use the right sidebar: - Choose the relevant contact (5) from your CRM and generate (6) a test result based on it to check the output. - If the generated text meets your requirements, click the Create AI Example (7) button. - This text will be added to the AI Message Examples (8) section. The AI will use these saved successful examples as reference points to improve future message generation. Using AI Templates in automations The templates you create can be used in automations on any relevant nodes that have a text field (sending a message, email, comments, etc). To do that, in the communication node settings, turn on the Use Template toggle and choose the template you need from the AI Templates list.