Autobound API Documentation

📘

What's new

From v3.2

Enhanced Resolution Parameters:

• New parameters for improved entity resolution: userName, userCompanyName, contactName, contactCompanyName, userCompanyUrl, contactCompanyUrl

Model Specification:

• model: You can now specify which model you want to generate content. Various content types will default to different models. Options include gpt4o, Opus, Sonnet 3.5, fine-tuned models, and more.

Sequence Functionality:

• New parameters: sequenceNumberOfEmails, contentToRewrite

Enhanced Insights:

• Job opening insights: Gain valuable information about a company's hiring trends and initiatives
• 10K insights: Access key financial and strategic information from company annual reports

Improved Company Data:

• Significantly enhanced data on 125,000+ companies, including:
  • Detailed value propositions
  • Products sold
  • Buyer personas targeted

This influences output by:

• Identifying top 3-5 products with unique selling propositions for each company
• Recognizing top 5-8 buyer personas with detailed value-based messaging
• Enabling AI to determine the proper buyer persona and product focus when generating content

Note: Job Opening Insights, 10k insights, and Improved Company Data (new Personas, Sales Assets) won't be live for all API clients until late July 2024. Reach out to [email protected] to request early access

Introduction

Welcome to the Autobound API documentation! Autobound is revolutionizing B2B sales and martech operations by harnessing the power of generative AI alongside our unparalleled, proprietary insights engine.

At the core of Autobound's offering is our robust insights platform. Unlike more generalized solutions, Autobound specializes in generating deep, actionable insights that fuel high-quality sales communications. Our API empowers sales and marketing teams to embed this powerful insight generation capability within their products or platforms, providing an invaluable resource for their end clients.

While we excel at crafting compelling sales content, our true differentiator lies in the depth and breadth of our insights. These insights form the foundation for all personalized communications, ensuring that every interaction is informed, relevant, and impactful.

Discover The Power of Insights

With our generate-insights endpoint, you can tap into a wealth of personalized insights for prospects, dramatically enhancing your product's personalization capabilities.

Our insights engine goes beyond surface-level information, diving deep into company operations, market positioning, and individual professional contexts.

Autobound's API unlocks access to an extensive range of insights, including:

• Prospect's interests, initiatives, and accomplishments
• Prospect company value propositions and product offerings
• Persona-specific pain points and KPIs
• Technologies used (competitive and complementary)
• Work history and recent job changes
• Customer win stories, prospect's customers, and investor data
• News events such as new offerings, acquisitions, awards, and partnerships
• Shared experiences like common past employers or schools
• Product and innovation trends, including quality control issues or significant launches
• Digital transformation progress and IT infrastructure challenges
• Regulatory compliance status and recent certifications
• Cybersecurity posture and risk management focus
• Operational efficiency, including supply chain challenges and cost management improvements
• Leadership changes and governance structure
• Sustainability initiatives and ESG compliance
• HR trends, including employee engagement and diversity programs
• Industry positioning and competitive landscape
• Financial performance across various expense categories
• Customer relationship trends, including satisfaction and churn rates
• Sales and marketing team performance and initiatives

These insights, derived from authoritative sources and analyzed using advanced AI, provide a comprehensive view of a prospect's business context. This depth of understanding enables the creation of highly personalized, relevant, and impactful sales communications.

Craft Exquisite Sales Content

In addition to the generate-insights endpoint, Autobound's API is engineered to craft email copy that resonates using generate-content.

Our generate-content engine goes beyond simply aggregating insights. It intelligently selects the most relevant information for each unique buyer-seller match:

1. Smart Insight Ranking: Our algorithm evaluates all available insights, prioritizing those most relevant to the specific interaction.
2. Value Proposition Alignment: It matches selected insights with the seller's unique offerings, creating a narrative that clearly demonstrates value.
3. Personalization at Scale: Even with numerous insights available, our system chooses the most impactful ones, balancing personalization and conciseness.
4. Hassle-Free Integration: We handle the technical complexities like context windows and token limits, latency, and endpoint routing, allowing you to focus on the output. Many of our content outputs are written with fine tuned models that have been trained on A+ completions, unlocking unparalleled speed and quality.

Consumption and Credits

The API operates on a usage-based model where the consumption of credits is determined by the endpoint used.

Endpoint	Credits Consumed
generate-content	2
generate-insights	1

📘

Credits are consumed when content or insights are successfully generated, not for failed requests.

If you generate a sequence (with multiple emails) 2 credits are consumed for each written email.

Get Started

This documentation will guide you on how to make your first API request, while the comprehensive endpoint and schema descriptions will provide a deeper understanding of the API's capabilities.

Create a new API key from https://app2.autobound.ai/settings/api-keys

Step 1: Authentication

To authenticate with the Autobound API, use the X-API-KEY header in your requests. Obtain your API key from your account dashboard or generate a new one by visiting our application.

X-API-KEY: your-api-key-here

Step 2: Understanding Error Codes

Understanding error codes is crucial for troubleshooting and ensuring smooth interaction with the API. Here are the explanations for the error codes you might encounter:

• 200 OK: The request was successful, and the expected response is returned.
• 401 Unauthorized: Authentication failed, likely due to an incorrect or missing API key.
• 402 Payment Required: The request cannot be processed due to insufficient credits.
• 405 Method Not Allowed: The HTTP method used is not supported for the endpoint.
• 408 Request Timeout: The request took too long to process and timed out.
• 429 Too Many Requests: Too many requests have been sent in a given amount of time and the rate limit has been exceeded. The rate limits are set to prevent abuse and to ensure fair usage.

If you encounter any issues or have questions while interacting with the Autobound API, our support team is here to assist.

Email: [email protected]

Step 3: Making Your First Request

Autobound API offers two main endpoints:

1. /generate-content/v3.3: Generates personalized sales content.
2. /generate-insights/v1.0.0: Retrieves personalized insights for a prospect.

To generate personalized content, make a POST request to the /generate-content/v3.3 endpoint. The only required parameters are your API key, userEmail, contactEmail, and contentType (described further below).

python

import requests

url = 'https://api.autobound.ai/api/external/generate-content/v3.3'
headers = {
    'X-API-KEY': 'YOUR-API-KEY-HERE',
    'Content-Type': 'application/json'
}
data = {
    "contactEmail": "[email protected]",
    "userEmail": "[email protected]",
    "contentType": "email"
}

response = requests.post(url, headers=headers, json=data)
print(response.text)

👆

This is the simplest request pattern available! All you need to pass in is a unique ID of the user (the seller) and contact (aka the buyer or prospect).

And here's an example of making a request to the /generate-insights endpoint:

python

import requests

url = 'https://api.autobound.ai/api/external/generate-insights/v1.0.0'
headers = {
    'X-API-KEY': 'YOUR-API-KEY-HERE',
    'Content-Type': 'application/json'
}
data = {
    "contactEmail": "[email protected]"
}

response = requests.post(url, headers=headers, json=data)
print(response.text)

Replace your-api-key-here with your actual API key, and adjust the request body to match your specifics.

In the context of the Autobound API, identifiers are crucial as they provide the necessary context for generating personalized sales content. Here's a breakdown of how identifiers are used on both the prospect and seller level:

Contact Identifier:

For the sales use case, the Contact is the prospect (the person receiving the message).

This identifier allows Autobound's API to pull in relevant insights about the prospect, such as their interests, work history, recent job changes, company initiatives, and news events related to their organization.

If the system fails to identify the contact, it'll generate content using insights on the company.

User Identifier:

For the sales use case, the User is the seller (the person sending the message).

Similarly, a seller identifier (work email or LinkedIn URL) is essential for personalizing the content from the sender's side. The seller identifier enables the API to incorporate information about the seller, perhaps their shared experiences with the prospect, their position, or their company’s value proposition.

This ensures that the content generated not only appeals to the prospect but also accurately represents the seller and their brand.

🚧

For the generate-insights endpoint, your only current parameter is the contact identifier.

Soon, you'll be able to pass in a User Identifier as well, which will focus the insights on those that are relevant to both parties. This functionality should be available in Q3 2024.

Content Type:

The contentType parameter specifies the type of content you want to generate. It's crucial for tailoring the message according to the context in which it will be delivered. Email, sequence, and custom, are our most popular contentTypes.

Here are the options:

• email: Generates a full cold outbound email. This option uses a fine-tuned model to optimize for speed and quality.
• sequence: Generates multiple emails for a single prospect, in sequence format. By default, it outputs 3 emails in a cold outbound sales sequence, similar to the "cold to gold" feature in our web app. Subsequent emails are designed to be sent if there's no response to the previous email. Currently, only 1 subject line is generated. You can specify a different number of emails or customize the sequence type using additional parameters. This currently defaults to Anthropic's Sonnet 3.5.
• opener: Generates just the opening 1-2 lines of an email. This uses a fine-tuned model for rapid generation.
• connectionRequest: Generates a personalized LinkedIn connection request. Like the opener, this uses a fine-tuned model for quick output.
• sms: Generates a short message for SMS outreach. This also utilizes a fine-tuned model for speed optimization.
• callScript: Generates a script for phone outreach.
• custom: This flexible option allows you to pass custom instructions, with a 1,500 character maximum, to guide the content generation for any outreach scenario. Examples could include instructions like "write a 4 email drip sequence", "write a 3 paragraph account strategy", or "create a list of this prospect's top 15 pain points". Regardless of the instruction, Autobound's rich data on prospects and sellers drives the personalization, ensuring the generated content is contextually relevant and highly personalized to both the sender and the receiver.

Each contentType is designed to match the medium and style of communication that is most effective for that particular channel, ensuring that your outreach is always on point.

Request Schemas

Identifiers

• Contact identifier: either contactEmail or contactLinkedinUrl is required.
  • contactEmail: The email address of the contact (prospect) the user (seller) is reaching out to.
  • contactLinkedinUrl: The LinkedIn URL of the contact the user is reaching out to.
• User identifier: either userEmail or userLinkedinUrl is required.
  • userEmail (required): The email address of the user the content is written on behalf of.
  • userLinkedinUrl: The LinkedIn URL of the user the content is written on behalf of..

Note - waterfall logic ensures that content still generates even if our system cannot identify the user or prospect's email address, so long as we can figure out their company from their domain, which is extracted from their email. This ensures a 99.8% success rate in generating content outputs.

additionalContext (optional): String. This field allows for further customization of the generated content by providing specific guidelines or data to be included in the message. The information should be passed in instruction format. For example, you could paste in a webpage and say "The prospect visited this web page pasted below, incorporate the topics into the email." This flexibility is powerful - you could incorporate intent data, mention past interactions logged in the CRM, or highlight any other relevant information. Character limit is 10,000.

contactName (optional): String. If provided, this overwrites the contact name that the system automatically finds. Our system will resolve this from nothing more than an email, but sometimes we can't find the person's name. Including this field increases the chance the email will output an A+ email where the name was matched. If it can't be found, the system will currently output [PROSPECT NAME].

contactCompanyName (optional): String. If provided, this overwrites the contact's company name that the system automatically finds.

contactCompanyUrl (optional): String. If provided, this overwrites the contact's current company URL that the system automatically resolves. This update affects the company name and all associated insights.

contentType (required): The type of content to be generated. Options are email, opener, sms, connectionRequest, callScript, sequence and custom contentType. When contentType is set to "sequence", each email in the sequence consumes 2 credits.

contentToRewrite (optional): String. This field allows you to input content you'd like to see rewritten, such as an email template. If contentType is set to "sequence", you can paste multiple email templates here, in the sequence you'd like them written. You can even paste full sequences from other tools like Outreach, Salesloft, or Apollo. The system will use this as a base for generating new, personalized content. Currently only works for sequence and email. Character limit is 15,000.

If you'd like to rewrite an existing 2-step email sequence (or any sequence of emails), you can do so by passing in your existing content using the contentToRewrite parameter. The system will intelligently rewrite each step of the sequence, preserving the structure while threading personalization throughout the sequence. Only the first step in the sequence needs a subject line. All following steps are treated as replies within the same email thread, so they do not require a new subject line. This mimics a natural email conversation where subsequent messages build on the original context. Here's an example request:

pyth

{
  "contactEmail": "[email protected]",
  "userEmail": "[email protected]",
  "contentType": "sequence",
  "sequenceNumberOfEmails": 3,
  "contentToRewrite": "Step 1\nSubject: Write hyper-personalized emails with AI\nBody: Hi {{prospectName}},\n\nI'm one of the Autobound Co-Founders. We just launched a tool that auto-generates hyper-personalized emails with AI (based on LinkedIn, news sources, company initiatives, shared experiences, job changes, & more).\n\nWorks with LinkedIn, Outreach, Salesloft, and Gmail, and signup takes <30 seconds.\n\nIt's the tool my co-founder and I always wanted (we're ex Oracle / Yelp sales), and we just raised $4M to make it happen.\n\nOpen to exploring whether Autobound can boost your team's open and reply rates?\n\nBest,\n{{userName}}\n\nStep 2\nBody: Friendly follow up, is writing thoughtful, personalized emails something your team struggles with?\n\nOver 4,000+ SDRs/AEs are using Autobound to maximize productivity (we're the #1 recommended AI-email writer on G2 with 200+ 5-star reviews).\n\nAny interest in exploring whether Autobound can help your team generate more replies?\n\nHere's a 1-min explainer vid if you'd like to learn more first.\n\nBest,\n{{userName}}"
}

While the example format provided above is recommended, the contentToRewrite parameter is designed to be flexible. The system doesn’t require your input to be formatted exactly as shown, as long as it can identify the general structure of each step, including the step number, subject, and body.

You can also further guide the AI's output by embedding specific instructions directly into your email content. These instructions should be placed within brackets [like this], allowing you to give the AI clear directives on how to enhance or personalize the email content.

For example, you can prompt the AI to include specific insights or data points that have been resolved for the prospect:

_"Im one of the Autobound Co-Founders, we just launched a tool that auto-generates hyper-personalized emails with AI (based on LinkedIn, news sources, company initiatives, shared experiences, job changes, & more).

For example, our system found:
[give 2-3 bullets of example insights that Autobound resolved for this prospect]

Interested in seeing how we could help your sales team generate hyper-relevant messaging 60-120x faster?"_

Lastly, when passing in content to be rewritten using the contentToRewrite parameter, you can use the following variables to personalize your emails:

• {{prospectName}}: The prospect’s name.
• {{prospectJobTitle}}: The prospect’s job title.
• {{prospectCompanyName}}: The prospect’s company name.
• {{userName}}: The user’s (sender’s) name.

The system will automatically resolve these variables with the correct values before incorporating them into the final content output. This ensures that the personalized elements of your sequence are accurate and relevant.

customContentType (optional): write out your own desired output, like "describe this prospect's personality based on their social media" or "list 20 ice breakers for an upcoming call". These can also be much longer prompts, where you can get creative with the output. Note that if customContentType is used, you'll need to set contentType to custom.

A request with nothing more than the mandated parameters would look like this.

python

import requests

url = 'https://api.autobound.ai/api/external/generate-content/v3.3'
headers = {
    'X-API-KEY': 'YOUR-API-KEY-HERE',
    'Content-Type': 'application/json'
}
data = {
    "contactEmail": "[email protected]",
    "userEmail": "[email protected]",
    "contentType": "email"
}

response = requests.post(url, headers=headers, json=data)
print(response.text)

and here's how you'd modify the parameters for a custom content type.

json

{
    "contactEmail": "[email protected]",
    "userEmail": "[email protected]",
	  "contentType": "custom",
    // this is required if customContentType is used.
    "customContentType": "write a pre-meeting email to prep for an account executive (the seller) with talking points and insights they can use on their upcoming call with the prospect."
}

model (optional): specifies the LLM used for content generation. Only works if contentType = sequence or email. If no value passed in, system uses fine tuned model for email, and opus for sequence. Options are: opus, sonnet_3.5, gpt4o, and fine_tuned

n(optional) The number of unique pieces of content to generate for the given request. This is set to 1 by default (it not included). The maximum is 3. The n parameter is not compatible with contentType: "sequence"

language (optional): specifies the desired language for content generation, ensuring tailored messaging in the recipient's preferred language. This is written out as free-form text, and defaults to "english" if not included.

salesAsset (optional): Information on a potentially longer piece of text like a related whitepaper, text from a sales deck, text from a web page, etc. Text or information a seller wants to include in their messaging, which could be derived from a webpage scrape focusing on a specific product, the pain points it solves for a certain industry, information on an upcoming event, etc. Character limit is 10,000.

sequenceNumberOfEmails (optional): Integer. Only applicable when contentType is "sequence". If not provided, defaults to 3. If sequenceNumberOfEmails or contentToRewrite is set but contentType is not "sequence", an error will be returned.

In the below example, we're asking the API to incorporate mention of a recent conversation Daniel had with Ryan's coworker (perhaps pulled from the CRM) with a 1,500 character (truncated for simplicity below) overview of an upcoming marketing event Autobound is hosting.

json

{
    "contactEmail": "[email protected]",
    "userEmail": "[email protected]",
    "contentType": "email",
    "language": "hebrew",
    "additionalContext": "Daniel previously had a conversation with Ryan's coworker Robert.",
    "salesAsset": "Join us for a Happy Hour at Dreamforce..."
}

In this example:

• contactLinkedinUrl is the LinkedIn URL of Ryan Bask, the prospect. Note how it's okay that the contact ID is a LinkedIn URL whereas the user ID is an email.
• userEmail is the email address of Daniel, the user making the request.
• contentType is email, meaning an email will be written
• language is Hebrew, meaning the output will be in Hebrew.
• additionalContext includes an instruction to mention a previous conversation Daniel had with Ryan's coworker, Robert, which will guide the content generation process to include this particular context in the email.
• salesAsset provides content about an upcoming happy hour event at Dreamforce, along with instructions for the AI on how to pitch this event in the email.

userCompanyName (optional): String. If provided, this overwrites the user's company name that the system automatically finds.

userCompanyUrl (optional): String. If provided, this overwrites the user's current company URL that the system automatically resolves. This update affects the company name and all associated insights.

userName (optional): String. If provided, this overwrites the user name that the system automatically finds.

valueProposition (optional): String. If provided, this acts as the userCompanyDescription / default value proposition. Our system keeps updated value propositions on 125,000+ companies by constantly reading company websites and pushing information through sophisticated data pipelines. This ensures up-to-date value propositions are available for real-time API requests. However, API users can pass in their own value proposition if they'd like to overwrite what the system would otherwise output. Character limit is the same as salesAsset (10,000). Content will be truncated if longer.

wordCount (optional): the number of words (approx) you'd like the output to be. If word count is not passed in, the system will determine how many words to generate. In most scenarios, this is around 80 for email, 20 for opener, 50 for connectionRequest, and 35 for sms. callScript is more dynamic.

writingStyle (optional): This parameter offers flexibility for clients to choose either a preset style or to create their own custom style. Character limit is 10,000. Clients can choose from a range of predefined writing styles. Available presets include:

• challenger_sale: For a conversational and insightful approach.
• clever_poet: To craft content with a creative, poetic twist.
• cxo_pitch: For concise, executive-level pitches.
• data_driven: For content backed by data, statistics, and clear ROI.
• basho: For short, personalized content that follow Basho protocol.
• why_you_why_now: Demonstrates a sense of urgency tied to the prospect's pain points.

Clients can also specify their own writing style, with customWritingStyle. When this is used, the parameter, writingStyle needs to be set to custom.

Let's walk through a few examples. Using a preset writing style...

json

{
  "contactEmail": "[email protected]",
  "userEmail": "[email protected]",
  "contentType": "email",
  "writingStyle": "challenger_sale"
}

In this example, the output will sound incorporate the challenger sales methodology. The word count will be determined by the model, unless wordCount is specified as well.

Using a custom writing style, and also specifying word count (remember, word count is optional).

json

{
  "contactEmail": "[email protected]",
  "userEmail": "[email protected]",
  "contentType": "email",
  "writingStyle": "custom",
  //needs to be set to custom if customWritingStyle is used.
  "customWritingStyle": "write at a 6th grade level in British English, very persuasively",
  "wordCount": 85
}

Using a custom writing style to write a custom contentType.

json

{
  "contactEmail": "[email protected]",
  "userEmail": "[email protected]",
  "contentType": "custom",
  "customContentType": "write a 3 email drip sequence that matches this JSON format... ",
  "writingStyle": "custom",
  "customWritingStyle": "use the following 2 emails to extract my tone and style...",
  "wordCount": 250
}

In this last, more advanced scenario, the client is prompting the system to generate multiple emails in a sequence that build on each other and also fit a certain JSON structure. Word count is set to 250, which is a nice, short total length for 3 separate emails (250 / 3 = ~83 words each).

Getting creative

Here's an example JSON showing the true power of Autobound's Personalization API!

json

{
  "contactEmail": "[email protected]",
  "userEmail": "[email protected]",
  "contentType": "email",
  "writingStyle": "custom",
  "customWritingStyle": "use the following 2 emails to extract my tone and style...",
      //using style extracted from example emails
  "salesAsset": "Autobound Logo Integrations Pricing Login Get Started Free Install...",
      // sales asset is a scrape of our AI-writer product's site page. About 500 words but the system can process intent very well.
  "model": "opus",
     // using opus will be slower, but the system will follow advanced instructions more closely.
  "additionalContext": "include the following deal notes from a closed lost opp from Hubspot: {dealNotes}",
      // context on the contact <> user relationship will be woven into the sequence
  "language": "spanish",
      // the output will be written in another language
  "n": 2,
      // 2 versions of the email will be written with different combinations of insights, the user can select which one they like more.
  "wordCount": 250
}

Understanding the Response

A successful response will return a JSON object containing a list of generated content along with their respective IDs and insights used.

Response Structure:

• The response is organized under a contentList array, which contains objects for each generated piece of content.
• Each object contains a subject, content, contentItemId, includedInsights, insightsUsed, valuePropsUsed, and templateId.

Subject and Content

Subject

The subject field is provided only when the contentType is set to email. It represents the subject line of the email that is to be sent. The subject is crafted in a way that it corresponds and is relevant to the body of the email, ensuring coherence and context alignment between the subject and the email content. This aspect enhances the chances of the email being opened and engaged with by the recipient.

"subject": "Congrats on $27M! Level-Up Verifiable's Sales Game 🚀"

Content

The content field represents the body of the contentType specified in the request. For example, foremail, it contains the complete email body, while for opener, it contains the opening 1-2 lines of an email.

The content returned is formatted in HTML to preserve line breaks, formatting, and any other structural elements that are essential for a well-formatted email. This ensures that when the content is rendered in an email client, it retains the formatting as intended, making it easy to read and engaging for the recipient.

Example of an HTML formatted content:

"Hi Ryan,\n\nKudos on the $27M Series B! I’m Daniel from Autobound, and we're in the business of supercharging sales emails—just like this one.\n\nOracle alum here, like you. We both know the sales grind. What if you could cut that grind in half?\n\nThink this could make you really stand out in your new role, interested in learning more?\n\nBest,\nDaniel\n\n

Is ML Generated

The isMLGenerated field indicates whether the content was generated by a machine learning model. It's a boolean value where true signifies that the content was AI-generated, which is always the case in the response. We'll be deprecating this output soon.

"isMLGenerated": true

Content Item ID

The contentItemId is a unique identifier associated with each piece of generated content within the contentList array. This ID is crucial for debugging and tracking purposes.

In the event of any issues or anomalies with the generated content, providing the contentItemId when reaching out for support will expedite the troubleshooting process. It allows for precise identification and examination of the specific content generation request, aiding in a quicker resolution.

Here's an example of how the contentItemId is structured in the response:

Text

"contentItemId": "8f72b0fe-f9cf-4795-8612-372cb5e6b9ca"

Included Insights

The includedInsights field provides a breakdown of the insights used to generate the content, grouped by categories. Each insight contributes to crafting a personalized and relevant message for the recipient. The insights are collected from various sources and encompass a range of categories. As the Autobound team continues to add more insights into our system, we'll be simplifying the taxonomy of the insight types and subtypes.

Be sure to see "List of all insights" below for an accurate timeline/update of which insights are live in our system.

Here are the primary types of insights that may be included:

1. Company highlights
   1. This insight entails specific mentions of a prospect's company's customers or investors, often name-dropped to exhibit the seller's knowledge and research about the prospect and their business. This gesture showcases a level of preparation and personalization, which can foster a more engaging and meaningful interaction with the prospect.
2. Competitor news
   1. This insight provides curated news articles on a prospect's competitors, identified based on industry, product category, and company size through a blend of internal algorithms and external datasets, either crawled or acquired. Our database encompasses about 150,000 different companies, showcasing a strong footprint in the B2B domain. The news covers pivotal competitor activities such as funding rounds, acquisitions, executive hires, or new product launches. Having this information at hand when reaching out to prospects can be instrumental, as it not only informs the conversation but also unveils opportunities to showcase how your offerings can provide a competitive advantage in light of recent developments.
3. Financial
   1. Insights regarding the prospect's company financial status, encompassing areas like revenue growth, profit margins, operational efficiency, capital expenditures, and more. This could reflect on the company's financial health, expansion pace, profitability, cost management, and investment strategies, among other financial aspects. By analyzing various financial metrics and their implications, these insights can help tailor propositions to address the financial pain points the prospect's company might be facing, aligning with their financial goals or challenges.
4. Hiring trend
   1. This insight analyzes a prospect's company's open job positions to deduce their initiatives and potential pain points. Utilizing text analysis methods on keywords in job titles, responsibilities, the quantity and seniority of roles open, we make the open positions relevant to the prospect a user is reaching out to. With a dataset encompassing around 10 million open job positions across 8 million companies at any given time, this insight provides a unique lens into the prospect's company's operational focus and challenges.
5. Insight
   1. News events relating to the prospect or their company derived from news articles, press releases, or other public sources (about 150 publications in total). Examples might include recent funding rounds, product launches, or other notable events. This type name will likely be changed to "News" in the future.
6. Podcast
   1. Insights derived from specific podcasts that the prospect has participated in. This could include their views, expertise shared, or discussions they were involved in, which provides a deeper understanding of the prospect's professional interests and knowledge.
7. Shared Experience
   1. Commonalities between the sender and the recipient, such as having worked at the same company or attended the same school, which can be leveraged to build rapport.
8. Social Media
   1. Information gleaned from the prospect's social media profiles like LinkedIn, providing details on their professional background, interests, recent job changes, work anniversaries, and more.
9. Youtube
   1. Information gathered from specific YouTube videos featuring the prospect. This may encompass presentations, interviews, or discussions they were part of, offering a glimpse into their professional persona, their expertise, and areas of interest.

Each category contains an array of insights, with each insight encapsulated in an object that carries the unique ID of the insight, among other information. In the response, you will find the includedInsights field populated with the type of insights used and the corresponding IDs, which can be used for further reference or analysis.

Insights Used

The insightsUsed field provides detailed information on each individual insight that was utilized to craft the content. Each insight is represented as an object within an array, containing various properties that describe the insight, its source, and the relevant data points that were extracted and utilized.

Here's a breakdown of the properties within each insight object:

1. insightId:

   1. A unique identifier for the insight.

      Insight ID: "189550f1-dcdd-4d1f-aca8-4b1d38c02a16"
      

2. type:

   1. The category of the insight (e.g., socialMedia, insight, sharedExperience).

      type: "sharedExperience"
      

3. subType:

   1. A more specific classification within the insight type. The following are available subTypes with their respective types

      subType: "workedSameCompany"
      

4. name:

   1. A descriptive name for the insight.

      name: "You and the prospect worked at the same company"
      

5. description:

   1. A brief description of the insight.

6. variables:

   1. An object containing the actual data points extracted, which were utilized in the content generation.
      JSON

      {
          "sharedCompanyName": "Oracle",
          "userSharedCompanyStartYear": 2017,
          "userSharedCompanyEndYear": 2017,
          "contactSharedCompanyStartYear": 2013,
          "contactSharedCompanyEndYear": 2014
      }
      

We're working on a full table of all insights broken down by these properties. In the meantime, here they are broken down by type and subType.

List of all insights

The table lists various insights regarding a company, categorized by types and subtypes, along with their association timeline, age or refresh frequency, and likelihood percentage. The insights cover different areas like news, financials, and social media updates. For instance, financial insights scheduled between November 8-13 highlight concerns like dwindling earnings and high spending, with a likelihood range of 5-10%. Social media insights, set for early to mid-December, focus on recent LinkedIn posts with a higher likelihood range of 25-50%. Other insights already live are mostly news-related, with a lower likelihood of under 1%.

You can find a link to this Google Sheet (copy and sort/filter it yourself) here.

Value Props Used

The valuePropsUsed field reflects the value proposition(s) utilized in the generated content.

Currently, API customers cannot customize the value propositions that are used to generate content. This functionality will be enabled soon.

This encapsulates the core value or benefit that the seller's service provides to the prospect's company, derived automatically from various sources like the LinkedIn "About" description of the prospect's company. Here's a breakdown of the fields within valuePropsUsed:

• **valuePropId**: A unique identifier for the value proposition used.
• **name**: The name or title of the value proposition.
• **productName**: The name of the product associated with the value proposition.
• **content**: The actual text of the value proposition that is integrated into the email content.

For users who already have an account with Autobound:

• type: Indicates the type of value proposition. It can be default, competitor, persona, or complementaryTech. The default type is used most often, while the others are more specific to the competitor, persona, or complementary technology scenarios.
• shareType: It can be personal or team. Personal indicates a more tailored or individualized value proposition, while team reflects value props created and shared across the team within Autobound.

Example:

JSON

"valuePropsUsed": [
    {
        "valuePropId": "d24d61cd-0353-43f0-9285-4a53fc91ddc2",
        "name": "Company Description",
        "productName": "Autobound",
        "content": "We know how difficult it can be to research a prospect & their employer, then to craft a compelling & relevant email. But with 320 billion emails sent daily, B2B revenue teams HAVE to be highly personalized and relevant to rise above the noise. Autobound's B2B sales engagement platform is revolutionizing how companies sell using generative AI (think ChatGPT for sales). Founded by the top 1% of sellers from Oracle and Yelp, Autobound empowers sellers to increase email reply rate by generating individually personalized sales emails using AI. We’ve trained our AI on millions of high performing sales emails to identify what works best. Autobound integrates directly with LinkedIn, Outreach, Salesloft, Gmail & more. Join our beta at www.autobound.ai/sign-up-free",
        "userId": "5189fb82-34c0-462a-9dd5-cf024aef3dff",
        "organizationId": "3c1308e3-d683-4969-9298-0d979f8a0cb9",
        "type": "default",
        "shareType": "personal"
    }
]

In this example, the value proposition is oriented around the challenges of researching a prospect and their employer, and crafting compelling, relevant emails. Autobound's solution, as outlined in the content field, addresses these challenges by leveraging AI to generate personalized sales emails, thereby increasing the email reply rate. This particular value proposition is categorized as a "personal" share type and a "default" type, indicating a more tailored approach in communicating the value to the prospect.

1. 1. A more specific classification within the insight type. The following are available subTypes with their

Template Information:

• The templateId field is used for debugging purposes with the Autobound team if the content being generated has any quality issues.

Now you're all set to start generating personalized sales content with the Autobound API!

For more detailed information on the available endpoints, parameters, and response objects, refer to the full API documentation.