Step 2. Create the AI agent's tools

ai agents in {{product name}} need tools to do their job – these tools are {{scenario plural lowercase}} agents use information provided by you to reason about how and when to use these tools to inform the ai agent's context, {{product name}} sends the following information to the ai service provider system prompt t he name and description of each tool ( {{scenario singular lowercase}} ) t he name and description of scenario inputs and scenario outputs docid\ di1pkxe4s6 striu9spvv of these tools in addition to providing context, all {{scenario plural lowercase}} used as tools for ai agents must be active and inactive scenarios docid\ pdrftysejpiiztab7zjyh and either scheduled on demand or triggered by a custom webhook in the next sections, we will create a tool for our agent to list our shop inventory and another to order more stock if we're low the aim of the following sections is to showcase the ai agent's reasoning the example {{scenario plural lowercase}} provided have been simplified to streamline their setup tool 1 scenario to list shop inventory we will provide our agent with a {{scenario singular lowercase}} to list our shop inventory since we want to send data from the {{scenario singular lowercase}} to the agent, we have to use use scenario outputs docid 4gwcr4lpzuabtv9edytyr and the scenarios > return output module to create the {{scenario singular lowercase}} click the create a new scenario button in your organization dashboard or in the list of {{scenario plural lowercase}} if you don't have testing data ready, set up your shop data add the data store > search record module to your {{scenario singular lowercase}} in the data store field, select add to create a new data store in the data store name field, fill in the name for your inventory data storage in the data structure box, click add to define a structure for your data store click save to confirm the data structure and save to create the data store go to the list of data store and open the new data store click the add button to add data to your data store update the name of the {{scenario singular lowercase}} the ai agent uses the {{scenario singular lowercase}} name to decide if it should run the {{scenario singular lowercase}} fill in "list shop inventory" add the tools > text aggregator module in the source module field, keep the data store module enable the show advanced settings toggle at the bottom of the module settings in the row separator field, select new row in the text field, map the name and quantity fields from your data store add the scenarios > return output module click add scenario outputs to set {{scenario singular lowercase}} outputs for the return data module in the scenario outputs tab, define the {{scenario singular lowercase}} output structure and fill in the description of each item in the output in the module settings, map the text variable to the inventory field confirm module settings with save set {{scenario singular lowercase}} scheduling set the {{scenario singular lowercase}} scheduling to on demand the agent will run the {{scenario singular lowercase}} for you when needed confirm the {{scenario singular lowercase}} scheduling with save activate the {{scenario singular lowercase}} save your {{scenario singular lowercase}} add {{scenario singular lowercase}} description for the agent go to the {{scenario singular lowercase}} diagram tab click options > edit description add description to the {{scenario singular lowercase}} the ai agent uses the {{scenario singular lowercase}} name and description to decide if it should run the scenario fill in "lists the shop inventory " click save you have created the {{scenario singular lowercase}} for your agent to list the shop inventory we will make the {{scenario singular lowercase}} available to your agent in the following sections tool 2 scenario to order more stock we will provide the agent with another tool a {{scenario singular lowercase}} to order more items for our shop inventory the {{scenario singular lowercase}} will receive order information from the agent with {{scenario singular lowercase}} inputs for our testing purposes, the {{scenario singular lowercase}} will just send messages to a selected chat to create the {{scenario singular lowercase}} click the create a new scenario button in your organization dashboard or in the list of {{scenario plural lowercase}} in scenario inputs and outputs in the scenario inputs tab, set the {{scenario singular lowercase}} inputs structure and description add the slack > create a message module set up the create a message module in the connection selection box, select your connection if you don't have a connection, click the add button to create it select the channel where you want to receive the messages about new orders created by the agent in the module settings, use the scenario input in the text field for example update the name of the {{scenario singular lowercase}} the ai agent uses the {{scenario singular lowercase}} name to decide if it should run the {{scenario singular lowercase}} fill in "create buy stock order " set {{scenario singular lowercase}} scheduling set the {{scenario singular lowercase}} scheduling to on demand the agent will run the {{scenario singular lowercase}} for you when needed confirm the {{scenario singular lowercase}} scheduling with save activate the {{scenario singular lowercase}} save your {{scenario singular lowercase}} add {{scenario singular lowercase}} description for the agent go to the {{scenario singular lowercase}} diagram tab click options > edit description add description to the {{scenario singular lowercase}} the ai agent uses the {{scenario singular lowercase}} name and description to decide if it should run the {{scenario singular lowercase}} fill in "creates orders to refill the shop inventory " click save you have created the {{scenario singular lowercase}} for your agent to create orders to refill the shop inventory we will make the {{scenario singular lowercase}} available to your agent in following sections