Documentation

Agents

Overview

Agents enable the creation of fully autonomous flows, delivering on-demand customer care seamlessly. They utilize the instructions, knowledge, alignment, and actions you provide them with to effectively respond to interactions from any connected source and perform any actions you’d like them to take.

Acme

Inbox

Assigned

Manage

Agents

Knowledge

Behavior

Actions

Settings

Tutorials

Learn the basics

Docs

Get the details ↗

Agents

Agent…

Tech Support

Tech Support

Customer Support

Customer Support

Order Confirmation

User Onboarding

Create an agent, then add skills to provide instructions. Learn more

Tech Support

Source

To start an agent, you first need to receive an interaction from a source. You can select this source when you create an agent or change it later using the "Settings" button in the top bar. You have the option to set a default source or choose one from platforms like Shopify or Stripe. Here’s a list of our default sources:

Email: A unique email address to forward emails directly to your agent. It understands the entire email content, including attachments like PDFs and images.

Phone: A dedicated unique phone number that allows customers to call in, enabling the agent to take action on the full conversation in real-time.

Webhook: A unique webhook url that can be called programmatically, with the body of the request serving as the interaction for the agent. Read the webhook section in the docs to learn more.

Integrations: We’re continuously expanding our integrations. Integrations empower your agents to take action whenever an event occurs in the tools and services you already use. For instance, agents can respond to events like incoming orders from Shopify or Stripe, or new customer entries in HubSpot.

Tech Support

Select an interaction source

Email

Auto-forward emails to an address

Webhook

Post data to a webhook

+1 520 680 0081

Receive calls on a phone number

Actions

Browse

Write instructions or browse to enable the agent with actions to use any service

Interact

+1 520 680 0081

Update Agent

Webhook

The webhook source enables you to programmatically initiate an agent by providing an interaction. To set this up, simply select "Webhook" as the source for the agent. This generates a unique URL for you to call. For instance, you can make an API call from your checkout flow, sign-up form, or other sections of your product or service.

The body of the API call can be fully dynamic, accommodating a wide range of file types, including JPG, JPEG, PNG, MP4, MP2, MP3, M4A, JSON, MBOX, HWP, PPTX, DOCX, PPTM, PPT, EPUB, MD, CSV, TXT, and PDF.

You have to include a contact with your webhook call, allowing you to group all chat history and context data. This will also organize the conversation into a new thread in your inbox. All chat history and context associated with this unique contact will be stored in a dataset. Contacts are built using a name, email, phone, company, and address.

For each webhook call a contact email or phone number has to be provided. The other fields are optional.

Here’s an example API call:

CURL POST

// Textual input-only
curl --location 'INSERT WEBHOOK URL HERE' \
--form 'message="Some user input"' \
--form 'contact.name="Jane Doe"' \
--form 'contact.email="jane@gmail.com"' \
--form 'contact.phone="123456789"' \
--form 'contact.company="Lemni"' \
--form 'contact.address="123 Main St, Anytown, USA"'

// Input with files
curl --location 'INSERT WEBHOOK URL HERE' \
--form 'message="Some user input"' \
--form 'contact.name="Jane Doe"' \
--form 'contact.email="jane@gmail.com"' \
--form 'contact.phone="123456789"' \
--form 'contact.company="Lemni"' \
--form 'contact.address="123 Main St, Anytown, USA"' \
--form 'files[]="Some files"'

JS FETCH

const formData = new FormData();

// Add files to form data (optional)
files.forEach((file: any) => {
    formData.append("files[]", file, file.name)
});

// Add contact to form data
formData.append("contact.name", "Jane Doe");
formData.append("contact.email", "jane@gmail.com");
formData.append("contact.phone", "123456789");
formData.append("contact.company", "Lemni");
formData.append("contact.address", "123 Main St, Anytown, USA");

// Add textual input to form data 
formData.append("message", "Some user input");

// Make API Call
const response = await fetch("INSERT WEBHOOK URL HERE", {
    method: "POST",
    body: formData
});

// Read response
const data = await response.json();

Prompt

Add a prompt for your agent to let it respond to an interaction. A prompt is built using a couple building blocks; Instructions, an Ai model (LLM), knowledge, actions, and alignment rulesets. By combining these fundamentals you’ll give your agent to power to take action and resolve complex problems and automations.

The editor is fully collaborative, allowing you to write prompts together with your team. Optionally, you can also use our templates to choose from a selection of common agent set-ups curated by Lemni. You can also create your own agent templates to share with others.

Acme

Inbox

Assigned

Manage

Agents

Knowledge

Alignment

Actions

Settings

Tutorials

Learn the basics

Docs

Get the details ↗

Tech Support

Noud

Alex

Write an email to answer the question and send it using gmail.


When a technical issue or bug is reported, create a GitHub issue with the following structure:

- Title: Brief summary of the issue.

- Description: Detailed description, including steps to reproduce, observed behavior, and expected outcome.

- Error Messages/Logs: Include any specific messages or logs if available.

- Customer Reference: Mention the customer experiencing the issue by name or ID.

- Additional Tags: Include priority, urgency, or affected module tags if relevant.

Actions

Browse

Enabled

Send Email

Create Issue

Suggested

Create Email Draft

Add

Forward Email

Add

Send WhatsApp

Add

Send Resend Email

Add

Send SendGrid Email

Add

Create Hubspot Contact

Add

Cancel Order

Add

Interact

deginified-fantastical-tvu0jzcj@email.le…

Update Agent

Instructions

Fundamental to each agent are their instructions. Instruct the Ai agent so that it understands what it needs to do. Lemni automatically recommends the relevant actions to use from the action store, based on the instructions you write.

To write a good instruction you summon the agent to do things based on the interaction provided from the source. The more detailed you write the instructions, the better the agent becomes at consistently performing them. Below you’ll find some relevant examples.

EXAMPLE INSTRUCTION A

Write an email to answer the question, then send it using gmail.

EXAMPLE INSTRUCTION B

When the email has car damage images:

  1. Generate a Damage Report:

    • Analyze the attached car damage image.

    • Draft a detailed damage report that includes:

      • Car brand and model.

      • Damage assessment.

      • Estimated repair cost.

  2. Send Slack Notification for High-Cost Repairs:

    • If the estimated repair cost exceeds $5000:

      • Send a concise summary of the damage report via Slack, including:

        • Key findings from the report.

        • Total cost estimate.

      • Assign one of the following agents to review the report: Dave, Joe, or Jane.

  3. Process Payment for Lower-Cost Repairs:

    • If the estimated repair cost is $5000 or below:

      • Initiate a payment for the estimated repair amount using Stripe.

  4. Email Response to Customer:

    • Compose an email response to the customer summarizing:

      • Estimated repair cost.

      • Actions being taken to resolve their claim.

    • Send the email through Gmail.


When the email is without car damage images and they have not been sent before:

  1. Request Missing Information:

    • Compose a response requesting additional details from the customer:

      • Information on the product

      • Images of the car damage

    • Send the request via Gmail.

EXAMPLE INSTRUCTION C

When a technical issue or bug is reported, create a GitHub issue with the following structure:

  • Title: Brief summary of the issue.

  • Description: Detailed description, including steps to reproduce, observed behavior, and expected outcome.

  • Error Messages/Logs: Include any specific messages or logs if available.

  • Customer Reference: Mention the customer experiencing the issue by name or ID.

  • Additional Tags: Include priority, urgency, or affected module tags if relevant.

EXAMPLE INSTRUCTION D

If the sentiment of the phone call becomes very negative, calmly reassure the customer that a human agent will assist them shortly.


Then send a concise message to the #Support channel on Slack requesting a team member to join the call, including the customer’s name and email address for quick reference.

Model (LLM)

Lemni lets you select the best large language model for the task at hand. Each model offers unique performance characteristics and strengths, allowing you to select the one that best suits your needs. When creating a agent, simply use the model selector located at the bottom left to switch between popular models, including OpenAI's GPT-4, Anthropic's Sonnet, Google Gemini, and Llama. Once you've made your selection, the chosen model will seamlessly handle the execution of your instructions.

Tech Support

The LLM powering the agent

GPT-4o

GPT-4

Claude 3.5 Sonnet

Mixtral 8x7b

Llama 70b 8192

Actions

Browse

Enabled

Send Email

Suggested

Create Issue

Add

Interact

+1 520 680 0081

Update Agent

Knowledge

Leverage knowledge to train agents on your business using a variety of data, including files, webpages, and more. You can efficiently organize this information in the "Knowledge" section of the app using datasets.

For each agent, you can choose the specific datasets you want to utilize. For instance, consider incorporating documents related to your return policies. Alternatively, combine documents about your company, technology, and webpages with FAQs to enhance your responses to customer support emails.

By default, we select all available knowledge when an agent is created; however, you can deselect any irrelevant datasets to improve the agent performance and consistency.

Tech Support

Actions

Browse

Enabled

Send Email

Suggested

Create Issue

Add

Interact

+1 520 680 0081

Update Agent

Accessible knowledge for the agent

General

Return Policy

Product Documentation

Add Dataset…

Behavior

Set behavior rules to ensure your agent follows the correct brand language and safety guidelines. Use the menu in the agent editor to select or deselect options to control how the agent adheres to them. Easily create and manage the rulesets in the behavior section. For more details, check out the Behavior section in the documentation.

Tech Support

Actions

Browse

Enabled

Send Email

Suggested

Create Issue

Add

Interact

+1 520 680 0081

Update Agent

Align the agent using rulesets

Customer communication

Tech guidelines

Product communication

Brand guidelines

Add Ruleset…

Actions

When crafting an agent, it’s essential to empower it to perform the desired action. By utilizing actions, you can seamlessly integrate your agents with various apps and services, enabling them to perform the job.

To streamline your setup process, we automatically recommend relevant actions based on your instructions. Simply click on an action to enable it for the agent.

Alternatively, you can click "Browse" to search both the action store and your private action library. You can use the private action library to code your own actions to connect agents with your systems. Learn more about building and managing actions in the actions section of the docs.

Tech Support

Actions

Browse

Enabled

Send Email

Suggested

Create Issue

Add

Interact

+1 520 680 0081

Update Agent

For many actions, you’ll need to link an account with the service you wish to use. This can be easily done through oAuth, which only requires a one-time sign-in to grant access. This will connect the account to your workplace.

Additionally, you can establish approval rules for each action you add. This feature allows you to designate a team member to review the action before it’s executed, which is particularly useful for breaking actions, such as cancelling a subscription.

Tech Support

Actions

Send Email

Instructions

Sign in to your Gmail account. Then make sure there is some context regarding an email and its content.

Connect

Sign In

Ask Approval

Search workplace members

None

Any Member

You

Owner

Alex Buis

Agent

Noud Adrichem

Editor

Interact

+1 520 680 0081

Update Agent

Behavior

Align your agents with your brand voice and guidelines by establishing clear rules. Ensure they remain focused on relevant topics and provide them with insights into your company's identity and key priorities. You do this by creating a new ruleset and providing it with rules. Simply click "+ Ruleset", and then write your rules. The editor is fully collaborative, allowing you to write alignment rules together with your team.

For example, should they be professional and strict, or can agents be playful and use emoji’s in their communication. Here are some example alignment rules:

EXAMPLE RULE A

You are an agent for Framer and are always playful, excited, concise, and love to use Emoji’s.

EXAMPLE RULE B

Maintain focus on Design Tools and Framer in all conversations. Politely redirect any unrelated topics back to discussions about tech, design tools, or Framer’s capabilities, helping with accounts and their set up, and best practices.

Acme

Inbox

Assigned

Manage

Agents

Knowledge

Behavior

Actions

Settings

Tutorials

Learn the basics

Docs

Get the details ↗

Alignment

Ruleset…

Identity and tone

Customer communication

Tech communication

Marketing communication

Topic guidelines

Safety

Create an agent, then add skills to provide instructions. Learn more

Identity and tone

You are an agent for Framer and are always playful, excited, concise, and love to use Emoji’s.

Enable

When your agent is ready, simply click the "Enable Agent" button at the top right of the editor to activate it. Once enabled, any changes you make to the live agent can be applied by clicking "Update Agent".

Once your agent is enabled you can start it by providing interactions on the source you’ve enabled. For email, this means mailing to the unique address. For phone, this means calling the number. And for webhook, this means calling the url.

Agents also feature straightforward versioning, allowing you to roll back any updates with ease. If needed, you can disable the agent as well. Manage this by right-clicking or selecting the three-dot icon in the sidebar.

Identity and tone

You are an agent for Framer and are always playful, excited, concise, and love to use Emoji’s.

Actions

Browse

Enabled

Send Email

Suggested

Create Issue

Add

Interact

+1 520 680 0081

Update Agent

Acme

Inbox

Assigned

Manage

Agents

Knowledge

Alignment

Actions

Settings

Tutorials

Learn the basics

Docs

Get the details ↗

Agents

Agent…

Tech Support

Tech Support

Customer Support

Customer Support

Order Confirmation

User Onboarding

Create an agent, then add skills to provide instructions. Learn more

Updates

Icon

Edit Name…

Duplicate

Create Template Link

Archive

Enable

Rollback

2d ago

Disable

Templates

To share your agents with others, you can easily create templates. Simply right-click on the agent in the left sidebar or click the three-dot icon next to it. Then, select "Create Template Link" to generate a shareable URL that you can provide to others. Rest assured, your account connections will remain private; converting an agent into a template will not share any personal information.

Acme

Inbox

Assigned

Manage

Agents

Knowledge

Behavior

Actions

Settings

Tutorials

Learn the basics

Docs

Get the details ↗

Agents

Agent…

Tech Support

Tech Support

Customer Support

Customer Support

Order Confirmation

User Onboarding

Create an agent, then add skills to provide instructions. Learn more

Tech Support

Settings

Enable Agent

Updates

Icon

Edit Name…

Duplicate

Create Template Link

Archive

We’re bringing the personal touch back to customer interactions at scale

© 2025 Lemni BV