Create an AI Grid Agent manually
This article will walk you through the process of creating and customizing your first AI Grid Agent manually, giving you complete control over every aspect of your workflow.
Manual Creation - Build your AI Grid Agent step-by-step, with full control over each column, prompt, and tool selection.
If you prefer a faster setup process, check out our companion article Create an AI Grid Agent with AI where our AI helps you build agents by simply describing your goals.
Getting Started
To begin, navigate to the AI Agent section of the platform. From there, select "Create a New Agent" to start building your grid.
Simply click on 'Start from scratch' to design your agent manually and you'll enter the Grid view.
Create Manually Your AI Grid Agent
Before diving into the creation of the grid, note that you can customize each AI Grid Agent basic information:
| Setting | Description |
|---|---|
| Title | Give your agent a clear, descriptive name that reflects its purpose |
| Profile Picture | Add a visual identity to help you quickly recognize the agent in your workspace |
| Description | Provide a brief overview of what the agent does and its intended use case |
| Instructions | Add instructions to your agent. These instructions, or 'system prompt', guide the AI agent in completing the grid. The template includes instructions by default, but you can tailor them to suit your specific needs. |
| Language | Select the language for your agent's interface and responses |
For more detailed guidance on crafting custom instructions, refer to our article on creating AI assistants.
Setting Up Your AI Grid Agent
You can start by creating the columns.
Columns Settings
Columns are the building blocks of your AI Grid. They define the structure of your data and determine what information is retrieved and analyzed for each row through prompting.
There are two types of columns:
a) Non-AI Columns
These are text fields that you can use to include manually text data. They are generally used as data in other columns as inputs for the prompt (referenced using #ColumnTitle) and are important for variables (e.g., a Company Name that might be different for each row).
Example: If you want to conduct a company benchmark study, you can create a "Company" column, add rows, and manually enter the names of each company you want to assess.
When you enter your prompt in an AI-column (as described below), you can add the input in your prompt with "#". When you run the agent, the grid will use the text data you entered in the referenced column.
Non-AI columns are only used to include manually text data. You don't need to add a column to add a file as a source of data for the AI agent. When you select a tool such as Files Search or Files Analysis, a "Document" column will be added automatically.
To add inputs, simply click on the "+" button and enter the title of the column and select the relevant format.
b) AI Columns
AI columns are columns where you instruct the AI agent to perform specific tasks, such as retrieving insights or searching the web. Each column you create represents a specific step in a global workflow and will be a fundamental part of your grid, helping to structure your actions and analyze the information you need. Each column can be customized to meet your needs.
1. Column Title
Start by defining the column title, which should clearly reflect the step of the workflow or the data you want to collect or analyze.
2. Tools
Tools and skills enable you to enhance an assistant with additional capabilities, allowing it to efficiently tackle complex queries. To see the list of available tools/MCPs and how to choose the right one, you can refer to our Capabilities & MCP Library. To learn how reusable skills work, see Skills.
Each tool serves a specific purpose in the workflow. It should be chosen based on the type of data needed, whether external information is required and the task you're working on. If you want to retrieve information from a document, you always need to select either Files Search or Files Analysis tool.
3. Output Format
Choose the output format for each column to ensure your data is structured correctly:
| Format | Use Case |
|---|---|
| Text | For descriptions (e.g., company activities, agreement topics) |
| Word | For short description (e.g., name of founders, name of the contract) |
| Boolean | For true/false results (e.g., compliance, verification) |
| URL | For web addresses (e.g., company websites, LinkedIn profiles) |
| Percentage | For percentage data (e.g., margins, ratios) |
| Number | For numerical data (e.g., employee count, revenue). You can configure abbreviation settings. |
| Date | For dates (e.g., agreement dates, founding dates) |
| For extracting email addresses | |
| Currency | For monetary values. You can configure currency code and abbreviation settings. |
| Choose one answer | Choose one option from a predefined list. You need to provide the predefined list options. |
| Choose one or more answers | Choose multiple options from a predefined list. You need to provide the predefined list options. |
| Canvas Slide | For generating editable Canvas Slide decks for each row. Select a slide skill or layout when needed; see Slides with Grids. |
| Map with Markers | For displaying geographic data with map markers |
| File from Data Bank | For referencing files from your data bank |
| Note | For merging content from other columns. Use #ColumnName to combine outputs — ideal for long reports where you want AI to focus on specific topics separately, then merge results. |
| Action on another column | For asking the AI to act on another column's generated artifact with the tools you select. Choose the source column, then describe the action in your prompt. |
For Choose one answer and Choose one or more answers options, spaces between words are not allowed. Use "-" or "_" between words.
Canvas Docs are not a separate AI Grid column output format in the current Add Column menu. For document-focused generation or transformation, use the relevant tool or skill, such as Rewrite Document or Documents Workflow, in the Tools and Skills section.
4. Prompts
Prompts are the tasks or instructions you give to the AI agent, such as retrieving insights or analyzing specific inputs. For more about prompting, please refer to our best practices.
When you're defining the columns, it's important to understand that columns can use data from other columns as inputs in the prompt by using # and column name (#ColumnName).
Non-AI columns: you can use text data from the columns you have manually created or imported
- Use cases: perfect to compare different companies or markets
AI columns: you can also use AI outputs (the results of a substep) of AI columns in your prompt
- Use cases: perfect to summarize, assess or analyze previous steps in a column in a complex workflow
When a column uses data from another column (by referencing it with #), it's a "dependency" (i.e., the column depends on data from other columns to run). When the AI agent is running, it creates a flow of data, where information moves forward through the steps.
- Dependencies can only flow from left to right, i.e., a column can only use data from columns to its left
- Avoid circular dependencies (if Column B uses #ColumnA, Column A cannot use #ColumnB)
- If there is no dependency, each column will be managed independently
If you want to analyze all the previous step results, you need to include all previous AI outputs in the prompt of the column with dependencies (e.g., #Company Name, #Company Size, #Main Products, etc).
5. Select the LLM of Your Choice
With Lampi AI, you have access to the most capable reasoning models. For each of your column, you can select the most relevant Large Language Model (LLM).
6. Activate or Deactivate LLM-as-a-Judge (beta)
LLM-as-a-Judge is an advanced evaluation feature that allows you to assess the quality of AI-generated outputs directly within your grid.
When enabled, this feature leverages a LLM to automatically review, score, and evaluate the response generated in a specific cell, based on a predefined evaluation prompt.
This is particularly useful when you're working with open-ended answers or qualitative data, and want a second layer of assurance or automated quality control.
Running
Once all your Columns are set, you can start running the AI agent. For more information about how to run your AI agent, you can refer to How to run an AI Grid Agent.
If you have selected the tool Search File or Search Analysis, you need to add a file before launching your agent. For more about how to add files to your grid, please refer Add data to AI Grid Agents.
If you want to edit your agent, you can always return to edit or modify your grid.
Save Your AI Grid Agent
Once you've added all the necessary columns and configured the settings, you can save your AI Grid Agent.
When you save it, you can make it public to your team and save it in a specific category.
Next: Create an AI Grid Agent with AI →