It's New! Now Available!

No APIs, No Coding!
Results? Today!

AiModelBuilder...a tool that generates insight from texts based on your selection of ready to go Artificial Intelligence Models, Extractors and Parsers! Simply select what you need, adding them to a Workflow. Upload your data. AiModelBuilder generates results, compresses all supporting files into one, and emails you a direct download link, to support your offline analysis. Optionally reuse the same Workflow for other files or change things up by swapping out one Model for another. Super simple point and click setup. No APIs, No Coding! Results? Today!

Usage Scenario

Example: You have chat data and you want to identify the most popular topics from all conversations, extract email addresses and phone numbers to determine if a topic was discussed in a Positive, Neutral or Negative manner.

Via our point and click Workflow Builder, you could add a Topic and Sentiment model and Parser objects.

Upload your texts with a unique row identifer for each sentence or conversation. AiModelBuilder schedules the job and passes the data to the Workflow. It creates various files with there own system generated keys, all related to your unique row identifier!

It zips up all files and sends you a direct download link to the results by email. Simply import them into your data store to support your offline analysis.

If you were using any other service, that would be a minimum of two API calls, each requiring custom coding to reach the different API services and custom models for each, not to mention the time invloved in building those models. And then your development team would need to code a system to parse the results and then create a data design to keep all those results related to support the data analysis.

AiModelBuilder does all of the above.

And when you need to add a different Model, Extractor or Parser, you can simply modify a Workflow or create a new one to solve another business need! No Coding, No API's!

Looking for Insight?

Variety of Models, Extractors and Parsers!

Select from a variety of AI Models, Extractors or Regular Expression Parser objects. Optionally create your own Models or Extractors.

Sentiment Model: When you want to identify a sentence or conversation that has a Positive, Negative or Neutral sentiment, include the General Sentiment Model in a Workflow.

Topic Extractor: When you want to identify the theme or subject of a sentence include this Extractor in a Workflow. Helps you identify trending statements across a large data set.

Part of Speech Extractor: When you want to identify the nouns, pronouns, adjectives and other parts of speech for each token inlude this Extractor in a Workflow. As you can imagine, this type of extractor produces a ton of results. This extractor generates a one to many set of files. One includes system generated keys linked to your unique row identifer and sentence. The other is linked to the sentences with a list of the many tokens and Penn Treebank Part of Speech. When you include this Extractor and a Sentiment Model you can for example identify which products or services by name were mentioned in a Positive or Negative conversation.

Emotion Model: When you want to identify the mood of a sentence, include the Emotion Model. A variation on a Sentiment Model, this unique model identifies Love, Hate, Suprise and other Emotions in a sentence.

Big 5 Model: When you want to identify the personality of a person based on what they write about themselves, add this model to a Workflow. For example you could pass a cover letter from a resume to determine the writers personality. You could pass a LinkedIn profile summary to determine there temperament.

Urgency Model: Have chat data? Include the Urgency, Topic and Sentiment Model in a Workflow. May identify the top issues, sentiment and conversations that express a need to change sooner, rather than later. Find out if feature enhancements can wait or not.

We took a different approach

Create Your Own Extractor In Record Time!

When building a Custom Extractor, big tech companies will have you tag every occurence of text you wish to extract from your corpus when building an Extraction Model, also known as Named Entity Recognition. When you have 15,000 sentences to wade through, this could take quite some time, not to mention the staffing costs. We took a different approach. Imagine you have 20 texts you would like to extract. Simply search for the first occurence and tag it. Repeat for the other 19. You're done! AiModelBuilder automatically locates every occurence before it trains the model, saving you an immense amount of time, and money.

Redact Option

Add Regular Expressions to a Workflow. Convert Results to a Token or Custom Label!

Each plan includes a Parser Library. Select form an assortment of common Regular Expression patterns. To protect customer privacy in processed results, select a Redact method. Set any Regular Expression to replace texts with either a Custom Label or a Token! AiModelBuilder returns the original sentence, the redacted version, and also identifies which items were replaced and the related Label or Token in the same result! Simply store the undredacted version in a secure datastore, and release the redacted version to your computer geeks or data scientists to support there data analysis.

It's All Related!

Generates One to Many Relationships! Import Results into your data store. All tables related based on system generated keys and your unique row identifier!

Processing of your data generates various results. Each includes system generated unique identifiers that are linked to your row id. Some results will output two files, where one includes many items extracted from a sentence, and the other a list of the sentences (one to many relationship). Where a row of text has multiple sentences as determined by our sentence parser model, the system generates a key for each. All results from the different models you include in a Workflow include the same sentence identifier, allowing you to link all the results and potentially to other tables in your database via your unique key.

Parse Texts

Regular Expresssions

Select from an assortment of Regular Expresssions to parse texts. A Regular Expression identifies a pattern in texts. For example, you could extract emails, phone numbers, credit card numbers, social insurance numbers, file names, hashtags, postal/zip codes and so much more. Add them to a Workflow as a Task. When patterns are identified, AiModelBuilder extracts texts. No Coding, No APIs! Yes we took care of that. Regular Expressions tested, and ready to do parse, today!

Try It Today!
All Plans come with a Free PDF, DOC, DOCX, TXT, HTML, Web Page Conversion Utility!
Creates files compatible for processing by an AiModelBuilder Workflow.


  • Process 1 File
  • Process 500 Rows
  • 1 Workflow
    With Up to 4 Tasks
  • Priority 3


Per Month
  • Process up to 2,000
    Rows per file
  • 1 Custom Model
  • Admin Account
  • 2 Workflows
    With Up to 2 Tasks Each
  • Priority 3


Per Month
  • Process up to 5,000
    Rows per file
  • 2 Custom Models
  • Admin Account
  • 2 Workflows
    With Up to 4 Tasks Each
  • Priority 2


Per Month
  • Process up to 10,000
    Rows per file
  • 2 Custom Models
  • Admin Account
  • 4 Workflows
    With Up to 6 Tasks Each
  • Priority 1

Frequently asked questions

We have included the most common answers to questions we have recieved. If you still have an unanswered question please try our Contact Us form at the bottom of this page.

Top Questions

Enter your email address in the form and select the Signup button. We will send you a login URL and credentials. Login with the credentials.

Limits are as outlined on this page and are also visible in the My Accounts section of the AiModelBuilder dashboard. When Free plan limits have been reached, the number of files processed are not reset on the first day of the month. When you add tasks to the Workflow in a Free account they can't be removed or modified.

In general you configure one Workflow that contains up to X number of tasks. A task could be X number of models or regular expressions. You can then upload X rows of data in a tab separated format where Column 1 is your unique row identifer and the Column 2 is a sentence/text to a maximum of 500 characters per row. Once you setup a Workflow with the various tasks, you schedule it for processing from within the AiModelBuilder dashboard.

The free version is designed to give you an overview of the capabilities of AiModelBuilder and the type of output you can expect.

When results are ready, we send you a direct link to download the results which are stored for 24 hours and then automatically removed.

Upgrade to a paid plan to remove these limitations. A paid plan allows you to include more steps in a Workflow; which generates additional results. You can also create Custom Models or Extractors. With a paid plan you have Admin rights which allow you to add/remove Tasks performed in the Workflow, so you could change the Workflow periodically, to support different result scenarios. Payments are made via PayPal. You are billed each month by PayPal. To cancel your plan, cancel it with PayPal prior to the next payment due date, as indicated at PayPal.
Paid accounts allow you to include more steps in a Workflow; which generates additional results during processing. With a paid plan you can change the tasks in the Workflow, so you can change the Workflow periodically to support different result scenarios. You can also create your own Custom Models or Extractors!
If you upload a file with X rows below the maximum available there is no credit system for rows not included in the file. In short, load up to the maximum rows where possible.

If you upload a file with more rows than the maximum as specified by the plan details or in the My Account section in AiModelBuilder, the system will limit the number of rows uploaded.

A processed file is stored for a maximum of 24 hours and is available via a direct download link in an email, sent automatically after processing.

If you are on a paid plan, each row of data can house up to 1,000 characters of text. You can instruct AiModelBuilder to split the row of data into sentences or pass the body of text to a model for tag/intent identification. As you can imagine, even though there is a limit on the number of rows to be processed as indicated above, the tool may find many more sentences in your rows of data, potentially increasing the number of rows returned.

As results are processed, some results will generate two files. For example, the Part of Speech model flags every token in texts with its respective part of speech and those results appear in a 1 of 2 file. The sentences represented by that file appear in a 2 of 2 file. A key is generated to link the results in file 1 with file 2. This allows you to import the results into a database and join the two sets of data creating a one to many relationship!

Some of these paired files have a conversation and sentence key. For example if a row of data in your file contained multiple sentences in it (as determined by our sentence parser), the system generates a Conversation key for those sentences and different keys for each sentence in the Conversation; which allows you to determine the source of the results via a one to many relationship in your datastore. Some results inlcude a Sentence Order so you can determine where it was located inside the row/conversation.

When a file has been processed (typically 24 hours or less), the system packages all results/files and generates a compressed zip file and then sends you an email with a direct link to download the results. There is also a link inside the AiModelBuilder File manager. As mentioned, we store results for a maximum of 24 hours after processing.

When you upgrade to a paid plan, we will link your free account to the paid. Please allow 24 hours for support to link the accounts. Payments are made via PayPal. You are billed each month by PayPal. To cancel your account, cancel it with PayPal prior to the next payment due date, as indicated at PayPal.

Important: Each row of data in your file must contain one sentence with a unique row identifier, so that when keys are created by the system to link various processed outputs, your unique identifer is linked to one sentence and not many. During processing our sentence parser will determine the number of sentences in a row and process each, preferrably finding once sentence per row; however if during processing it determines that there are multiple sentences in a row, it automatically splits out sentences and processes each if the split setting is set to Yes (default setting). If a row of data exceeds the character limit number of 1,000 characters per row for a paid plan, you may see partial sentences in the results.
Files are processed faster, depending on there Priority Level. The lower the number, the faster those jobs are processed. For example if you are on the Large or X-Large plan, your scheduled jobs are processed faster than those of the Small plan. AiModelBuilder has X number of Time Slots open for processing in each hour of the day. Priority goes to those on a Large or X-Large plan. This does not necessarily mean that a Small or Medium scheduled job is all depends on what is in the queue. If there were no Large plan jobs scheduled, Medium plan jobs are scheduled for faster processing over Small plan jobs.

Typically all jobs scheduled by AiModelBuilder are processed in 24 hours or less, regardless of the plan. In short, you can expect a direct link to download results for any plan in 24 hours or less.
A Workflow is a top down list of Tasks to complete. You define which tasks to complete. Tasks can return any tag/intent as determined by a model or you could set the task to determine if a text/sentence meets a specific tag/intent as shown below.

In our example above, the wizard driven Workflow Builder steps you through the build process (Build). When you have defined the Rule, select the Save button; which inserts a Task (run this). As outlined in your plan you have X number of Tasks per Workflow, each of which returns results. When you schedule a job to generate results from texts, AiModelBuilder works through Tasks as defined in the Workflow.

The Task in the example above returns all sentences where the Sentiment is Positive. To return all sentences regardless of sentiment you would setup a Rule like the following...

Note: The free Sentiment model identifies three tags/intents where 0 = Negative, 1 = Neutral and 2 = Positive.
A Custom Model is comprised of your corpus/texts that identify X tags/intents.

There are various methods to creating a model. For example, if you wanted to determine if customer input was related to a specific product, you could create a story about that product. The idea is to create a cohesive set of sentences that describe the product in a natural way, so that when you feed those sentences from the story into the model, it will have an understanding of the product based on contextual patterns.

Based on the example above, you create a spreadsheet with two columns. Column 1 is the name of the product. Column 2 is each sentence from the story. To identify different tags/intents, include them in other rows of your file with sentencs/texts that uniquely identify that intent/tag. You now have one spreadsheet where Column 1 identifies all the tags/intents for each related sentence in Column 2.

From within AiModelBuilder you give your model a name and then upload the corpus (tags/intents and texts/sentences) and then train it. Optionally add or remove sentences inside the tool or change the intent/tag of exiting sentences. Train, test, tweak and repeat until the intent/tag returned is what's expected. To test it, enter texts with a similar context to your original inputs (sentences/text).

You can create X Custom Models as outlined in the pricing for each plan. Note that if you have Admin rights, you can add or remove models at anytime and store X Custom Models up to the plan limits.

A number of rows in a Custom Model is limited to the file upload limit. For example, if your paid plan has a 2,000 row limit for processing of texts, the corpus row limit is 2,000. There is no limit on the number of tags/intents you have defined for you Custom Model; however if its a Custom Model, typically 4 tags/intents or less works well, depending on the effectiveness of your corpus. If you build a Custom Extractor Model you can include any number of tags/intents.
We have created a range of models that can be used to extract intelligence from your texts. These are models built by AiModelBuilder staff and have been tested to return tags/intents for specific purposes. Simply add them to your account/dashboard and then include them in a Workflow.

You can include one or more free models in a Workflow and define which tags/intents you want to validate or just have it return a result based on what X model does.
A Regular Expression is a pattern that identifies X (a pattern) and returns that (the matched text). We provide many Regular Expressions that have been tested and are ready to go. For example, we have Regular Expressions to locate email addresses in texts, common credit card number patterns, phone numbers and so much more.

If you need a Regular Expression that we don't have, send us a request via the My Account section in the dashboard for a quote on adding it to your account.
Optionally redact texts where a Regular Expression finds a pattern. For example, if you wanted to hide customer credit card numbers in texts you can set a Regular Expression to replace the credit card number with a unique token (numbers and letters) or a label of your choosing. AiModelBuilder returns the original text in the result, the redacted version and identifies which items were replaced and with what (token or label).

If your business requirements are to perform analysis on texts without exposing a clients personal information, you could save the redacted result in one database for X audience, and optionally store the original text in another database for a different audience; which may require specific privileges to access the sensitive data.

When your business needs to redact texts without uploading data to our system, contact us for a custome solution. Simply enter the request via the Feedback form below and we will be in touch as soon as possible.
Each plan is limited to X number of characters per row in a file for processing. For example, if you are on the Free plan and you upload data for processing where a row exceeds 500 characters of text, the system chops off any text greater than 500 characters. If you are on a paid plan the system limits a row of data to 1,000 characters.
If you are on a paid plan, you can add or remove tasks from a Workflow up to the number of task limits as outlined in the My Accounts section of the tool (inside the Builder), add or remove Models, Extractors or Parsers (Regular Expressions). Paid plan's have add/remove functionality enabled by default, effectively giving that plan Admin rights.
No we do not offer refunds...The Free account should have given you plenty of time to try most of the functionality in AiModelBuilder, and to make your executive decision.

Contact us

Have a comment, suggestion, or are we missing a feature? Need an On Premise solution? Fill in the feedback form below, click Send, and we will respond as soon as possible.