Hi there,

How can we help?

FAQs, popular resources, and helpful links to all things AutoQL. Get started here.

Frequently Asked Questions

Top FAQs

Getting Started

How AutoQL Works

Querying 101

Implementation Options

Partner Ecosystem


Privacy & Security

Resources & Support

Top FAQs

1) What is AutoQL?

Everyone needs access to data to make informed decisions and take strategic action. We believe getting answers and information from a database should (and can) be as simple as having a conversation. So, we built AutoQL to help people access their data in a more intuitive way.

AutoQL is an API-first solution that simplifies data access and streamlines analysis by making data accessible to everyone — even non-technical business users — through natural language.

Leveraging conversational AI technologies and embeddable in any branded or proprietary application, AutoQL is the only self-service data access solution that dynamically translates natural language into database query languages in real time. Users simply ask questions about their data in their own words and immediately receive responses in easy-to-understand visualizations.

2) Why implement AutoQL in my software or enterprise solution?

By implementing AutoQL in your solution, you can expect to:  

  • Boost revenue, attract new users, and add value for your existing loyal customers.
  • Stand out in your market with cutting-edge AI technology that drives value for every user.
  • Save on costs by significantly reducing incoming support tickets and ad hoc reporting requests. 
  • Leverage your skilled team and internal resources for high-value, revenue-generating projects.
  • Gain an edge over competitors offering limited or rigid data access and reporting options.  
  • Keep users engaged in your app instead of losing them to third-party BI tools.

3) Why work with Chata?

Getting data into the hands of more users more easily and more often is critical to the success of every business. We’re dedicated to working with our customers and partners to reimagine the future of data accessibility and transform the way business users interact with data every day.

Here’s some of the reasons you should consider working with us:

  • Gain an edge in the market with cutting-edge conversational AI technology that enables anyone to access data on demand using natural language.
  • Rely on our expert team of data scientists and CX professionals at every stage. We’ll work closely with you to learn about your product, goals, and the challenges faced by your team and your users so we can provide solutions that meet and exceed your expectations.
  • Low-lift, low-effort experiences for our customers guarantee a high return on investment. We rapidly generate custom training data and build a unique model specifically for your database, and we won’t charge you anything until AutoQL is live and operational in your solution.
  • Best-in-class developer experiences are our core focus and promise. Developers are supported through our comprehensive developer-first resources and robust Integrator Portal, empowering them to build and deliver new value quickly and confidently.

4) Is AutoQL a SaaS application?

AutoQL is not a SaaS application.

AutoQL is an API-first solution that dynamically translates natural language to database query languages. AutoQL embeds directly within any branded or proprietary application and operates behind-the-scenes to facilitate frictionless access to databases through natural language.

SaaS developers and enterprise solution providers can leverage AutoQL to deliver new “data on demand” functionality within their existing solutions.

We’ve also developed flexible widgets like Data Messenger and Dashboards so developers can easily integrate AutoQL and support best-in-class user experiences on the front end of their tools. These widgets are open source and completely customizable, so end users always experience AutoQL as a native part of existing SaaS and enterprise applications.

5) What does the AutoQL API do?

The AutoQL API is a powerful and secure API that dynamically translates natural language to database query languages. 

Here’s some quick facts about our API:

  • The AutoQL API is organized around REST.
  • Our API has predictable resource-oriented URLs, accepts and returns JSON-encoded request bodies, and uses standard HTTP response codes and verbs.
  • Our API is secured with JWT in conjunction with an API key.

The AutoQL API makes it possible for business users — even (and especially) non-technical users — to access and analyze data in real time by asking questions in their own words, all from the software and web environments they’re already familiar with.

Learn more about what principles guide our API, how to manage API keys, and more in our API Reference or in our Developer Docs.

6) Who is AutoQL for?

AutoQL is for software application providers, web portal developers, systems integrators, and service providers who are looking to monetize data accessibility as an asset, reduce strain on internal resources, and differentiate their offerings from competitors by making data accessible to end users through natural language.

Embedding AutoQL allows SaaS providers and enterprise solution providers to leverage powerful AI technology to meet the ever-increasing demands of today’s data-powered organizations and unlock unprecedented new business value.

Click here for more information about how AutoQL serves your software or industry vertical.

Getting Started

1) I'm interested in learning more about AutoQL. How do I get started?

Our dedicated team of experts will work closely with you to guide you through each stage of your AutoQL integration, from early stage consulting and discovery, to customizing our AI for your database, planning your feature release, and providing ongoing strategic support.

Reach out to us at info@chata.ai or book a discovery call with a member of our team.

2) What kinds of businesses and solutions benefit from implementing AutoQL?

AutoQL is compatible with any type of business SaaS solution or cloud-based proprietary enterprise system. If your software or enterprise solution collects and stores operational data that customers and end-users need to access on a regular basis, AutoQL will fundamentally transform the way everyone interacts with their data. For companies with mobile apps, AutoQL also makes data access seamless from anywhere, on every device. 

Implementing AutoQL is a value-add opportunity that enables SaaS providers and enterprises to monetize data accessibility as an asset, reduce strain on internal resources, and differentiate their offerings from competitors by making data accessible through natural language.

Business users across every role and department benefit from an intuitive and reliable solution that allows them to access their data, whenever they need it.

3) Do you offer a free trial or a Proof of Concept?

Every database is unique and we build a custom language model for each customer we work with. This allows us to provide robust coverage for querying enterprise-grade databases, but this also means we’re not able to offer free trials of AutoQL, since there’s no “out of the box” version.

We do, however, offer a no-cost, no-commitment Proof of Concept. Get in touch with our team to learn more about how this works and how to get started.

4) Are there any specific architecture requirements that must be met for implementation to be possible?

AutoQL is an extremely flexible API-first solution that can be customized for any software that uses a relational database. It works exceptionally well with cloud-native software solutions that have a web-based interface.

Independent Software Vendors (ISVs) that perform continuous deployments can readily take advantage of our end-to-end system that includes flexible front end widgets. Each widget takes just 2-3 hours on average to implement.

We can also integrate with on-premise software systems.

5) What should I expect once we get started?

Getting started with AutoQL can be broken out into four key stages: connect, train, implement, and go live.

Stage 1 – Connect:

We’ll work with you and your team to configure an encrypted, read-only connection between our cloud and your database. Without storing your data, this connection allows us to train a custom model, execute queries, and pass data back to you. We use thorough security practices to make sure none of your users’ data ends up where it shouldn’t. You’ll be able to configure access and permissions for individual customers and users later on.

Stage 2 – Train:

Next, we get to work generating training data and building a custom language model specific to your database. We begin with unsupervised machine training based on our system’s current understanding of typical database structures, allowing us to tailor our model to your app and deliver a feature that your users can operate intuitively. Semi-automated training is also available if you wish to customize certain queries to fit terms or jargon that are unique to your business.

Stage 3 – Implement:

Once your custom language model is ready, it’ll be your turn to build and implement a conversational UI in your solution, letting your users query their data from anywhere in your application. At this stage, you can make use of any of our flexible implementation options (all widget components are open source) or opt to build directly on top of our API.

Stage 4 – Go Live:

With AutoQL trained on your database and implemented in your interface, you’re ready to start offering conversational access to data on demand to users! As users ask questions, their conversational English will be sent up to our cloud and translated into a query language appropriate for your database. Relevant data is then returned to them in easy-to-understand visualizations, all within seconds.

How AutoQL Works

1) What is an 'end-to-end' system for delivering access to data on demand?

We’ve built a suite of proprietary conversational AI technologies that enable the real-time translation of natural language (the words you’re accustomed to using in everyday life) to database query languages. This is the core functionality and value of the AutoQL API.

But the AutoQL system is comprised of several critical stages and elements that come together to elevate human-to-database interactions.

Check out the links below for more info on the core components of the AutoQL system:

2) What does ''dynamically translating natural language to SQL'' mean?

When it comes to accessing information from a business’ relational database, team members are typically required to write and run database query language statements (DBQL) like SQL. But this is a time-consuming task that requires the expertise of technically-savvy and database-literate team members.

With AutoQL, any user can simply ask questions in their own words to access and analyze their data.

Through our API, AutoQL receives, understands, and interprets natural language queries, dynamically generates a corresponding database query language statement, executes the DBQL statement against the database through a read-only connection, and returns relevant data to the end user within seconds.

3) How does AutoQL answer questions about my unique database from my unique users?

Each AutoQL integration begins with our team generating custom training data and building a custom language model unique to your database. We handle all the heavy-lifting here, and thanks to the technologies we’ve developed, these processes happen rapidly and with high-precision.

Once we’ve built a training corpus and trained a custom model for your database, AutoQL can be implemented in your solution, allowing your users to ask questions about their data in natural language and instantly receive answers.

Querying 101

1) How do I know what queries I can ask?

The core value of AutoQL is accessing data easily and intuitively using natural language, or more simply, the words you use every day.

Think about the way you would ask a coworker a data-related question, like: “What was our click-through rate on our newsletter last month?” or “Which sales rep brought in the most new business this quarter?”. Approach querying with AutoQL the same way! Simply type questions in your own words and you’ll receive data responses in just seconds.

Tip: Be clear and succinct. Remember, if your question wouldn’t make sense to another person, you might be missing important context that AutoQL will need in order to answer your question accurately. For example, if you went up to a coworker and said “Expenses”, they’d probably say, “Well, what about expenses?”. But if you went up to that coworker and asked, “What were our total expenses last month compared to this month last year?”, they’d be much more equipped to provide an answer to you.

2) Can the SQL statement that is generated through a user query join multiple tables in a database?

Yes, AutoQL automatically generates table-joining SQL when a user query requires it.

The system is built to dynamically translate natural language into accurate SQL statements that can include multi-table joins, back joins, and alias joins.

3) Is it possible to query across different data sources?

At this time, users can only query one data source. AutoQL can be integrated with a data warehouse or a data lake that brings data from multiple sources together.

4) How does AutoQL handle similar column, table, or item labels in the database?

A key feature of AutoQL’s technology is the ability to disambiguate unique labels. This means the system is trained to determine what a user is referring to, even when that meaning is not explicit.

For example, referencing an “invoice” might mean different things for users in the accounting department vs. users in the warehouse.

Unique labels are taken into account during the integration and training processes, and we’ve built in an intelligent machine learning model that is trained to disambiguate value labels based on the context of the question being asked.

5) Do queries ever fail to return data? What happens if a query doesn’t work?

There are cases where a natural language query may be asked and AutoQL will not immediately return a data response. There’s a handful of reasons why this may occur, but even when a data response cannot be returned immediately, AutoQL will always return a message that provides information about why the query could not be answered, or a prompt to help the user clarify what they are asking.

Here’s a summary of common circumstances that can inhibit a data response from being returned:

  • User Permissions Lacking: If a user attempts to query information that they do not have access to in the database, they will receive an error message indicating that their query could not be executed due to a permissions issue.
  • Confidence Threshold Issue: AutoQL is designed to ensure that only correct data responses are returned in response to user queries. Therefore, AutoQL will not return data if the system is not confident that an optimal SQL statement has been generated.
  • Ambiguous Input or User Error: When a natural language query is received but is not immediately understood by the system, AutoQL has built-in models that act as “safety nets” or “check points”. In such cases, these models kick in to try to determine exactly what data the user is asking for. If this verification step is unsuccessful (whether that be because the meaning of the user’s query is still unclear, or because the data the user wants is not actually present in the database), AutoQL will not return a data response.

Implementation Options

1) What front end implementation options are available?

Once we’ve set up a data source connection and built a custom machine learning model specific to your database, it’ll be your turn to build a custom conversational user interface (CUI) that will serve as a natural language interface to your database. We’ve developed flexible front end widgets to make this process seamless and simple for developers.

Implementation options include Data Messenger and natural language-driven Dashboards, both of which can be directly embedded within an existing front end interface. Developers are welcome to customize and use our widgets however they like — all components are MIT licensed and open source. We currently offer these as React WidgetsVanilla JS WidgetsiOS Components, and Android Components

Tip: Integrations with webbased services are ideal, but our widgets will also run in an Electron wrapper or similar technology for use in desktop applications. We provide hooks so the components can be easily called from buttons or events. 

2) Do I need to use the front end implementation options that are provided? Or can I build directly on top of the API?

There’s no obligation to leverage the widgets we’ve provided. You’re more than welcome to build freely on top of our API to implement AutoQL’s functionality however you like in your own front-end interface.

3) Tell me more about Data Messenger

Data Messenger is an embeddable and totally customizable conversational user interface (CUI) designed to facilitate data query and analysis through natural language.

Data Messenger is:

  • Fast and simple to implement (see our Developer Docs for details about how to get set up)
  • Highly flexible and customizable (all components are open source)
  • Easy to use and accessible for all types of users

Learn more about Data Messenger in this short 3-minute demo video.

4) Tell me more about natural language-driven Dashboards

Dashboards are a completely customizable frontend implementation option that allows you to deliver powerful reporting functionality and interactive data visualizations within your software application.

Dashboards employ the foundational natural language to database query language translation technology behind AutoQL and flexible frontend components so software vendors can embed reporting functionality however they want, within any part of their app interface.

AutoQL Dashboards are:

  • Fast and simple to implement (see our Developer Docs for details about how to get set up)
  • Highly flexible and customizable (all components are open source)
  • Easy to use and accessible for all types of users

Learn more about Dashboards in this short 3-minute demo video.

5) How long does it take to implement Data Messenger?

Average implementation time is just 2 hours.

Completely customizable frontend components allow developers to seamlessly embed and brand Data Messenger within an existing application, thereby enabling users to connect instantly and intuitively with their data, simply by asking questions in natural language.

For step-by-step instructions on implementing Data Messenger, start by selecting your preferred widget library:

6) How long does it take to implement Dashboards?

Average implementation time is just 3-4 hours.

Completely customizable frontend components allow developers to seamlessly embed and brand Dashboards within an existing application, thereby making it possible for users to set up and manage Dashboards using natural language so they can easily keep a pulse on the data they care about.

For step-by-step instructions on how to implement Dashboards, start by selecting your preferred widget library:

Partner Ecosystem


1) Does Chata offer a Partner Program?

We sure do! We work with innovative systems integrators, professional services providers, and technology partners to reimagine and transform the future of data accessibility across every industry.

Get in touch with our team to learn more about the benefits of working with us and how to join our growing network of innovative partners.

2) What are the benefits of partnering with Chata?

Data-powered businesses demand innovation & impact. Chata’s Partners make it happen. Here’s a snapshot of some of the key benefits that come with joining our network of partners:

  • Establish your team as innovation trailblazers by introducing the world’s first conversational AI solution for data access to your tech stack.
  • Open the door to delivering custom AI solutions that scale, allowing you to earn credibility and loyalty as you propel businesses toward the data-powered future of tomorrow.
  • Expand current business, attract new customers, and capitalize on recurring revenue-generating activities.
  • Stand out and surpass competitors with AI that offers real business value.
  • Earn referral revenue and leverage shared informational resources so you and your customers realize value and see high ROI, fast.

Read more on our Partners page.

3) How do I join Chata's network of partners?

So glad you asked! Start by submitting an application to join our partner network here. We’ll be in touch to set up an introductory call where we’ll learn about your team and objectives, and share further details about working with us. From there, we’ll establish mutual expectations and outline next steps so we can begin working on shared initiatives that drive value for both companies.

Learn more about the benefits of partnering with us and how to get involved here.


1) Do you offer a free trial?

Every database is unique and we build a custom language model for each customer we work with. This allows us to provide robust coverage for querying enterprise-grade databases, but this also means we’re not able to offer free trials of AutoQL, since there’s no “out of the box” version.

We do, however, offer a no-cost, no-commitment Proof of Concept. This means we won’t take your payment information or charge any up-front fees until value has been proven and you agree to move forward in the process of going to market with AutoQL.

Get in touch with our team to learn more about how this works and how to get started.

2) How does pricing work?

We offer two pricing models: Pay-As-You-Go and Subscription-Based pricing. In both cases, AutoQL pricing is consumption-based (per API call) and works on a sliding scale.

3) What are the benefits of offering a consumption-based pricing model?

We’ve carefully built out our pricing models to optimize benefits for our customers and for the partners we work with.

Here’s some of the core benefits of a consumption-based pricing model:

  • Allows for full transparency and no surprises.
  • No POC fees and no implementation fees derisks the go-to-market process for our Integrators. Billing is only initiated when AutoQL is implemented and being used.
  • Integrators retain control of how they roll out AutoQL – whether that be gradually to a beta group of users, OR to all users in a dedicated new release. 

4) How can I learn more about pricing?

Book a call with our team to learn more about both of our pricing models, how they work, and what the best option is for your business.

Privacy & Security

1) Where is AutoQL hosted?

AutoQL is a cloud-based API, so the system itself is hosted securely on our cloud platform. The system communicates between your users and your database, but we do not store a copy of your database in the cloud or keep any of your end users’ information such as login credentials. 

AutoQL can also be integrated with on-premise software solutions.

2) What data access does Chata require from Integrators for implementing AutoQL?

AutoQL is built on the structure of the data storage layer. As such, Chata needs access to the raw data in the storage layer without any other software or API in between in order to facilitate a successful integration.

We’re happy to provide detailed instructions and helpful tips on providing secure access throughout the integration process. More information can be found in our Developer Docs.

3) Do you store a copy of our database or retain any of the data in it?

We never create or store a copy of your database and data will always remain within your system

The only data we store is the minimum data required for AutoQL to run securely and efficiently in your software application. We refer to this as nominal data, or the unique data we identify in your database that your users will ask questions about. This allows us to ensure that queries run quickly and return the results that users are expecting.

For example, a user might ask “How many of each item did Jane Doe buy last month?” In the context of this query, we only store the information that the customer “Jane Doe” exists in that user’s database so an optimal database query can be generated and executed dynamically.

We also store user queries (the questions your users ask in natural language), and we expose this to Integrators in the Integrator Portal. This allows us to provide a direct line of visibility into what users are asking; a feature that offers Integrators critical insight into what their users care about and how they’re using the system.

4) How and when is data encrypted?

Data is encrypted at rest and in flight and we use non-numeric IDs to ensure that data is secure at every level. We use JWT to secure who has access to our system, and for how long. 

Learn more about our security best practices and how we use JWT to enable secure access to our API.

5) Are there user-level permissions or role access permissions in place to control access to data?

Integrators can easily set permission levels for users within our Integrator Portal.

If you have in-house permissions structures, we’ll work with you to build a permissions framework that works for you.  

6) Are your security protocols verified and accredited by a third party?

Yes, Chata is SOC 2 Type II compliant. The Service Organization Controls (SOC) 2 Type II report is granted when a company completes a third-party audit that assesses the efficacy of security protocols, procedures, and controls. The examination includes testing and evaluation of the systems and processes we have in place to verify that we’ve demonstrated a reliable commitment to providing ongoing security assurance.

Achieving compliance indicates that Chata meets a standard of excellence recognized across the tech industry.

Read all about our SOC 2 compliance here.

Resources & Support

1) Where can I access Developer Resources?

  • Developer Docs can be found here.
  • API Reference Documentation can be found here.
  • The AutoQL Integrator Portal can be accessed here.

2) What is the Integrator Portal?

As developers ourselves, we know it can be frustrating to do one-off tasks in all the APIs we use, so we wanted to simplify these kinds of processes when it came to our own API.

The AutoQL Integrator Portal is a web app designed to help you implement and successfully manage your AutoQL deployment. It contains tools for developers, data for product managers, and serves as a helpful and easy-to-navigate interface that enables you to facilitate many functionalities of the API.

2) What can I do in the Integrator Portal?

The Integrator Portal has a variety of uses including:

1. Simplifying setup

Initial setup is facilitated through a simple step-by-step process, enabling you to quickly and easily connect databases to AutoQL through the Integrator Portal.

2. Streamlining one-off tasks

Configuration can be done through the simplified GUI in the Portal. Since configuration only has to be done once, you can simply set it and forget it.

3. Accessing data and product insights

Use the Portal as a lens to see what your end users are asking and gain a better understanding of your users’ motivations and needs. In the Portal, you have total visibility into common query trends, allowing you to highlight points of friction and see what data is in highest demand.

4. Developer assistance

Access API Keys, history logs, and all sorts of things that help developers gain important insights and get important work done, faster.

4) How can I access the Integrator Portal?

If you already have an account set up, you can access the Integrator Portal here.

If you require login information or are having issues accessing your account, please send us an email here.

5) Where can I access additional resources?

Looking for additional resources? See below for links to some of our most-popular resources. If you have questions, don’t hesitate to reach out to us directly. We’re more than happy to help!

Interested in staying in the loop with all-things AutoQL? Sign up to receive updates from our team here at Chata.