Quickstart #4: Structured Data Analysis (SDA)

Background & Objectives

This guide will walk you through how to build Agent Studio plugins that return large volumes of data to the AI Assistant.

In this quickstart guide, you will

Build a plugin that fetches 500 accounts from a mock CRM
Set up the plugin to work alongside our Code Interpreter plugin

At the end, your AI Assistant will be able to handle requests like this

Prerequisites

Access to Agent Studio
Access to Structured Data Analysis.
A Purple Suite instance and connector. Follow the Purple Suite Setup guide if you haven’t set one up yet.

Define your plugin

Navigate to Agent Studio

Go to Agent Studio. In the Plugins tab, select Create

Define your plugin

Define your plugin.

SDA Tip!

It’s important to be descriptive about the data that an SDA plugin returns.

Attribute	Value
Plugin Title	Fetch Accounts
Plugin Description	Returns all Accounts with ID, name, industry, territory, created/modified dates, last contact & renewal dates, ARR & MRR, employee count, opportunities (total/open/won/lost), avg deal size, churn rate, NPS, support tickets, offices, market share %, growth rate & funding amount.

Create a trigger

Add a Conversational Trigger

In the Plugin Editor, add a Conversational Trigger and fill it out

Build your process

Connect to the mock CRM

We need an HTTP action that will fetch the large volume of data from the external system.

Create a new HTTP Action

Click ⊕ in the tab bar and create a new HTTP Action

Select Import

Select the Import option (next to the Test button)

Import the API call

Import the following API call

$ curl -X GET "https://marketplace.moveworks.com/api/purple-suite/crm/accounts?limit=500" \
>   -H "Authorization: Bearer YOUR_PAT" \
>   -H "X-Instance-ID: YOUR_INSTANCE_ID"

Replace YOUR_PAT and YOUR_INSTANCE_ID with the values from the Set up the Purple API section. If you already set up a connector, the auth headers will be handled automatically when you test the action.

Test

Hit Test

Name your HTTP Action

Name your HTTP Action. It should look something like this.

Save

Save your HTTP action

Attach a Conversational Process

Now let’s connect the HTTP action to your plugin & prepare it for analysis

Add a Conversational Process

In the Plugin Editor, add a Conversational Process & create a new one.

Add an action-based activity

In the Conversational Process Editor add an action-based activity.

Choose your HTTP Action

Choose the HTTP Action you just built.

Configure the Output Mapper

In the activity configuration, under Output Mapper, we will rename the fields to make them more friendly for SDA.

SDA Tip!

It’s important to name fields succinctly & clearly to maximize the performance of SDA against various queries.

1 MAP():
2   items: response.data
3   converter:
4     AccountID: item.id
5     AccountName: item.name
6     AnnualRecurringRevenue: item.annualRecurringRevenue
7     AverageDealSize: item.averageDealSize
8     ChurnRate: item.churnRate
9     ClosedLostOpportunities: item.closedLostOpportunities
10     ClosedWonOpportunities: item.closedWonOpportunities
11     DateCreated: item.createdAt
12     DateLastModified: item.lastModifiedAt
13     Employees: item.employees
14     FundingAmount: item.fundingAmount
15     GrowthRate: item.growthRate
16     Industry: item.industry
17     LastContactDate: item.lastContactDate
18     MarketShare: item.marketSharePct
19     MonthlyRecurringRevenue: item.monthlyRecurringRevenue
20     NetPromoterScore: item.netPromoterScore
21     NextRenewalDate: item.nextRenewalDate
22     OfficeCount: item.officeCount
23     OpenOpportunities: item.openOpportunities
24     SupportTickets: item.supportTickets
25     Territory: item.territory
26     TotalOpportunities: item.totalOpportunities

Launch it

Launch to yourself

Under Audience Settings you can launch it to yourself for testing.

Test it!

Try it out

Try it out! You should see something like the following.

Not seeing the right results?

Verify that SDA is running by checking for the Running analysis progress update

Here are some other questions you could try:

What’s the total ARR of customers in the Tech industry?
Which industry is performing best in Europe?
Which accounts have the most support tickets are are up for renewal soon?

Next Steps

Start building your own plugins for Structured Data Analysis!

Next step: Test your plugin. See our Testing & Error Handling guide for how to test, debug, and handle errors in production.

$	curl -X GET "https://marketplace.moveworks.com/api/purple-suite/crm/accounts?limit=500" \
>	-H "Authorization: Bearer YOUR_PAT" \
>	-H "X-Instance-ID: YOUR_INSTANCE_ID"

1	MAP():
2	items: response.data
3	converter:
4	AccountID: item.id
5	AccountName: item.name
6	AnnualRecurringRevenue: item.annualRecurringRevenue
7	AverageDealSize: item.averageDealSize
8	ChurnRate: item.churnRate
9	ClosedLostOpportunities: item.closedLostOpportunities
10	ClosedWonOpportunities: item.closedWonOpportunities
11	DateCreated: item.createdAt
12	DateLastModified: item.lastModifiedAt
13	Employees: item.employees
14	FundingAmount: item.fundingAmount
15	GrowthRate: item.growthRate
16	Industry: item.industry
17	LastContactDate: item.lastContactDate
18	MarketShare: item.marketSharePct
19	MonthlyRecurringRevenue: item.monthlyRecurringRevenue
20	NetPromoterScore: item.netPromoterScore
21	NextRenewalDate: item.nextRenewalDate
22	OfficeCount: item.officeCount
23	OpenOpportunities: item.openOpportunities
24	SupportTickets: item.supportTickets
25	Territory: item.territory
26	TotalOpportunities: item.totalOpportunities