Build Conversational Agents of Any Complexity
We combined multiple platform libraries, NLU engines, persistence layers and servers in the single framework for a transparent dialogue state management
JAICF provides comprehensive open-source architecture, mixing all these components into conversational agents framework enabling the developer to create a context-aware dialogue and connect it to multiple platforms
JAICF Highlights
Multi-channel Support
Create dialogue scenarios that work simultaneously on multiple platforms with no restrictions. JAICF is built on top of native channel libraries thus it provides access to the native channel’s features Connect to any voice and text channels like Amazon Alexa, Google Actions, Slack, Facebook Messenger, and others
Extendable Architecture
JAICF works with any NLU engines such as Dialogflow or Rasa. JAICF uses third-party libraries and services that implement this functionality and provides ready-to-use NLU modules for your projects
Deployment Environment of Your Choice
Connect to any database that maintains the state of dialogue for each user. Deploy your conversational agent into any environment or use our feature-rich JAICP (Just AI Conversational Platform) seamlessly as cloud deployment and debug environment and get access to even more channels, dialogs and logs storage, end-to-end analytics, voice broadcasts and other cool features
Ready-to-Use Dialog State Machine
Save your time and create bot’s logic easily. Building context-aware agents is as simple as ABC, because our engine already has all the basics: dialog manager control flow, event system, state transitions, processing, and special features for statistics gathering and bot’s performance
Expressive Syntax
Create a reliable and maintainable code that is easy to troubleshoot with Kotlin. Static typing makes complex enterprise-level solutions error-free
Kotlin-based DSL
Build context-aware dialogue scenarios in a declarative style using a proprietary DSL
Autotests
Use a JUnit-based test suite to automate dialogue scenarios testing. With JAICF you can autotest your conversational project through already-familiar unit testing. Automatic tests that run on each gradle build, secure your project’s performance with each new change
Android Compatible
Launch JAICF scenarios on any platform with no additional servers – Kotlin is an Android-compatible language
Scale-up Potential
Use the ability to leverage an entire ecosystem of tried and true Java libraries and create enterprise-level solutions. Being a Kotlin app, JAICF-driven bot can use any Kotlin or Java features and third-party libraries
Runs Everywhere, Available on Any Channel
Lifecycle of your JAICF project
Design
Design a natural language dialogue between the user and your application
Build
Build a dialogue scenario and NLP model using JAICF framework, docs and samples
Test
Test your scenario using JAICF unit testing capabilities to ensure your application works as expected
Connect
Connect your scenario to one or more channels like Amazon Alexa or Facebook Messenger
Evaluate
Test your application through selected channels, make changes in your scenarios if required
Push Your Project to the Whole New Level
Spin up your conversational project in a sustainable production environment of a full-fledged JAICP (Just AI Conversational Platform)
Enjoy the benefits of seamless access to NLU service, dialogs and logs storage, metrics, rich end-to-end analytics and easy integrations including AI-powered voice calls
Use JAICP as a cloud or on-prem deployment and debug environment
FAQ
Is JAICF free?
Yes. JAICF is free of charge even for commercial purposes. It is available under the Apache 2.0 license
How is it different from Dialogflow and RASA?
JAICF is not an NLU engine or messenger. It is a dialogue manager that enables to create context-aware agents with any third-party NLU engine like Dialogflow or Rasa
What languages does it support?
JAICF works with any languages due to integrations with many NLU engines that recognize users’ requests
What voice assistants and messengers does it support?
JAICF features ready-to-use libraries for Amazon Alexa, Google Actions, Facebook Messenger, Slack, Telegram, and others. Moreover, it is open-source and can be easily extended with new channels and integrations