1. Go to Course Admin You will find Intelligent Agents either alphabetically, or in the communication category.
2. When you open the Intelligent Agent tool, you will see the Agent List page. Assuming it’s the first time you create an Intelligent Agent in your course, the first thing you should do is to change the default Settings.
   After clicking Settings, set a custom value for Name that emails come from and the Reply-To address for responses (see bottom image).You should add your name or course team and Reply-To address for responses Click Save when you are finished.
3. You then return to the Agent List page. Click New to start creating a new Intelligent Agent. For this guide we will exemplify by checking if a student hasn’t accessed our course for 7 days.
4. You have to put the Agent Name in, and we suggest writing a detailed Description in the optional description field. You and your team will see this information, so it’s wise to know it’s parameters. You can see an example in the image on the left.
5. Next, we must determine the Agent Criteria. You could look for Login Activity and Release Conditions, but we are not doing that with this agent. For this example we will look for Course Activity by each student. So, the Intelligent Agent will be triggered whenever a “User has not accessed course for at least 7 days”. This is a very simple intelligent agent, and no other criteria are needed (see image on the left).
6. Next the Agent Action section (for an overview of the settings in this section see top left image).First, the Action Repetition, if this action should be repeated after the first time is been satisfied. For this case, yes, we want to be repeated so we select Take action every time the agent is evaluated and the agent’s criteria are satisfied for a user, but in some cases you might want to take action only for the first time the agent’s criteria is meet, to avoid multiple emails sent to students or instructors.Then you click the Use Schedule checkbox and then the Update Schedule button. A new window opens. Here you can determine if you want the agent to run dailyweekly or monthly; and whether it repeats every day or every second day or every third day or whatever you choose. We opted to run it every day. You can also set the optional Start Date or an End Date for the Intelligent Agent. In this case we are setting it a Start Date for the beginning of the first semester and an End Date for the last day of the first semester, on the theory that I want to know throughout the semester if students are not accessing the course (see bottom left image).
7. Next, we will start to create the email. Most of the time you probably want to use HTML instead of Plain Text. Make sure that you have edited the custom settings so that the emails come from your name and the reply to your email address (see Step 2).For this agent we have it emailing to us rather than the student and as so Brightspace support email is set at the To field. If it was sending it to a student it would be different, you don’t use their email address, but rather the replace string {InitiatingUser}. For more details about Replace Strings, make sure you visit our article.
   It is a good idea to use some replace strings in the subject and or body of the email, although it isn’t actually necessary. Below you will find the most commonly used replace strings which can be in either the subject line or the body of the email.

Replace Strings that can be used in Subject and/or Body:

{OrgName} – The name of the organization. (TU Delft)
{OrgUnitName} – The name of the org unit. (Applied Statistics for Technical Students)
{OrgUnitStartDate} – The start date specified for the org unit.
{OrgUnitEndDate} – The end date specified for the org unit.
{InitiatingUserFirstName} – The first name of the initiating user. (Bob)
{InitiatingUserLastName} – The last name of the initiating user. (Jones)
{InitiatingUserUserName} – The username of the i.u. (bob.jones)
{LoginPath} – The address of the login path for the site. (URL)
{LastLoginDate} – The date the initiating user last logged in.
{LastCourseAccessDate} – The date the i.u. last accessed the course

The initiating user first name and last name is how you would personalize the message. The Org Name would be TU Delft and the Org Unit Name would be the course name.
Since this email is only being sent to ourselves for possible action, we do not need to make a detailed message. The subject line is just letting us know that someone hasn’t accessed our course for the last seven days
{OrgUnitName}: A participant hasn’t accessed the course for the last 7 days
For the message we will want to have the initiating user first and last name hasn’t accessed the course for the last 7 days in Org Unit Name and include in another line when the initiating user last accessed the course (see top left image).
{InitiatingUserFirstName} {InitiatingUserLastName} is missing in action for seven days in {OrgUnitName}.
Last login was at {LastCourseAccessDate}.

8. After you clicked the Save and Close button you are brought back to the main screen for the Intelligent Agents and you will now see the agent name and description on the screen. If it is set to run on a schedule, you’ll see that run date as well as shown here on the right side (see left image).The image on the left shows a good example of why we suggest that you write a detailed description. At a glance we can see what this Intelligent Agent is all about, rather than clicking in and looking at all of the criteria. We consider that to be an effective practice in using Intelligent Agents.
9. Now that we have an Intelligent Agent created, it is possible to access it’s settings using the drop-down arrow.
   Going down the list, you can Edit the agent, although you could also just click on the blue link for the agent name. You can make a Copy of this agent if you were going to create a second agent that is very similar. You can View History of the different runs for this. You can execute a Practice Run, which we will look at next.
   If you were running this manually, you could Run Now from the drop-down list. Finally, you could Delete your intelligent agent.
10. One useful feature of the Intelligent Agents tool is the Practice Run. With it we can check if the agent is not properly formed. The beauty of the practice run is that it tells you if it would execute; in other words, if any students meet the criteria, but it does not actually execute and send the email. You will receive an email message that tells you the results of the practice run.
11. Below the email we received when we did a practice run for this first Intelligent Agent.
    

    Title
    Agent Completed – 01 – No course entry for designated time period

    Message
    The following agent has finished running:

    Org Unit: org-esa-bt-o – Applied Statistics for Technical Students
    Agent: 01 – No course entry for designated time period

    Action Taken: Yes

    It tells me that action was taken and so that means that one or more students did meet the criteria for the agent.

12. Now that we have completed a practice run, we have new information in the fields for the Results of the Last Run, and the Last Run Date (see left image). If we wanted to see who the 6 users are that were identified by the Intelligent Agent, we would simply click on that link in the column for results of last run.
13. If I view the History page, which right now only has one practice run on it, I will see the same information I saw before (see image). However, this history page becomes much more much more valuable after you have run the agent multiple times.