Analyze Call with Bland AI API on New Contact Created from Exact API

Pipedream makes it easy to connect APIs for Bland AI, Exact and 2,000+ other apps remarkably fast.

Trigger workflow on

New Contact Created from the Exact API

Next, do this

Analyze Call with the Bland AI API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 800,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Exact trigger and Bland AI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Contact Created trigger
1. Connect your Exact account
2. Configure timer
Configure the Analyze Call action
1. Connect your Bland AI account
2. Select a Call ID
3. Configure Goal
4. Configure Questions
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Contact Created on Exact

Description:Emit new event each time a new contact is created. [See the docs](https://start.exactonline.nl/docs/HlpRestAPIResourcesDetails.aspx?name=CRMContacts)

Version:0.0.1

Key:exact-new-contact-created

View on GitHub

Exact Overview#

The Exact API provides a suite of endpoints for interacting with Exact's cloud-based financial software, which includes tools for accounting, CRM, and ERP functionalities. By leveraging this API on Pipedream, you can automate data flows across various business functions, sync financial records, manage customer relationships, and streamline operational processes. Pipedream's serverless execution model allows for crafting intricate workflows that respond in real-time to events, schedule operations, and connect with countless other apps to extend the functionality of Exact's ecosystem.

Trigger Code#

import common from "../common/base.mjs";

export default {
  ...common,
  key: "exact-new-contact-created",
  name: "New Contact Created",
  description: "Emit new event each time a new contact is created. [See the docs](https://start.exactonline.nl/docs/HlpRestAPIResourcesDetails.aspx?name=CRMContacts)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    async getResults(division) {
      return this.exact.listContacts(division);
    },
    getCreatedTs(contact) {
      return contact.Created.match(/\d+/)[0];
    },
    generateMeta(contact) {
      return {
        id: contact.ID,
        summary: contact.FullName,
        ts: this.getCreatedTs(contact),
      };
    },
  },
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Exact	`exact`	`app`	This component uses the Exact app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

Exact uses OAuth authentication. When you connect your Exact account, Pipedream will open a popup window where you can sign into Exact and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Exact API.

Pipedream requests the following authorization scopes when you connect your account:

About Exact#

Cloud business software for SMEs and their accountants

Action#

Analyze Call on Bland AI

Description:Analyzes an input call, extracting structured data and providing insights. [See the documentation](https://docs.bland.ai/api-v1/post/calls-id-analyze)

Version:0.0.1

Key:bland_ai-analyze-call

View on GitHub

Bland AI Overview#

The Bland AI API offers a suite of artificial intelligence services, which, when integrated with Pipedream, can automate tasks, analyze data, and enhance applications with machine learning capabilities. Through Pipedream's serverless platform, you can connect Bland AI with various apps to create custom workflows, process data, and respond to events in real time without managing infrastructure.

Action Code#

import blandAi from "../../bland_ai.app.mjs";

export default {
  key: "bland_ai-analyze-call",
  name: "Analyze Call",
  description: "Analyzes an input call, extracting structured data and providing insights. [See the documentation](https://docs.bland.ai/api-v1/post/calls-id-analyze)",
  version: "0.0.1",
  type: "action",
  props: {
    blandAi,
    callId: {
      propDefinition: [
        blandAi,
        "callId",
      ],
    },
    goal: {
      propDefinition: [
        blandAi,
        "goal",
      ],
    },
    questions: {
      propDefinition: [
        blandAi,
        "questions",
      ],
    },
  },
  async run({ $ }) {
    const response = await this.blandAi.analyzeCall({
      $,
      callId: this.callId,
      data: {
        goal: this.goal,
        questions: this.questions?.map?.((str) => typeof str === "string"
          ? JSON.parse(str)
          : str),
      },
    });
    $.export("$summary", "Call analyzed successfully");
    return response;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Bland AI	`blandAi`	`app`	This component uses the Bland AI app.
Call ID	`callId`	`string`	Select a value from the drop down menu.
Goal	`goal`	`string`	This is the overall purpose of the call. Provides context for the analysis to guide how the questions/transcripts are interpreted.
Questions	`questions`	`string[]`	An array of questions to be analyzed for the call. Each question should be an array with two elements: the question text and the expected answer type. Examples: `["Who answered the call?", "human or voicemail"]`, `["Positive feedback about the product: ", "string"]`