Presented by Rasa Director of Engineering Tom Boklisch at the 2021 Rasa Summit. Tom shared what's new and what's next for Rasa Open Source. Link to talk recording on YouTube: https://youtu.be/fmDZT1iFX08
This document discusses Conversation-Driven Development (CDD) as a process for building conversational AI assistants. It describes CDD as involving six key actions: sharing prototypes with test users, reviewing user conversations, annotating conversations as training data, testing the assistant, tracking the success of conversations, and fixing issues found. CDD captures lessons learned from building conversational AI to help teams iteratively improve assistants based on user feedback. The document also promotes Rasa X as a tool that can help teams implement CDD through features like reviewing conversations, annotating data, and continuous integration testing.
Webinar: How to Use Integrated Version Control in Rasa XRasa Technologies
The document discusses integrated version control in Rasa X, which allows teams to version training data and push changes made in Rasa X to a target branch connected to a remote git repository. It provides an overview of getting started with setting up version control by deploying Rasa X, adding an SSH key to GitHub, and connecting Rasa X. The document also discusses how integrated version control connects Rasa X to downstream workflows like automated testing and deployments and brings it in line with software engineering best practices.
Developing Intelligent Chatbots using RASA, OW2con'19, June 12-13, 2019 in ParisOW2
In this presentation given by Tobias Wochinger from RASA and Richard Popa from Orange, find out how Orange is developing AI assistants using the best solutions on the market in collaboration with RASA.
Building an AI Assistant Factory - Rasa Summit 2021Rasa Technologies
Presented by Dominique Boucher Chief Solutions Architect – AI Factory, National Bank of Canada and Eric Charton Senior AI Director AI, National Bank of Canada at the 2021 Rasa Summit. Check out the talk recording on YouTube https://youtu.be/EzTfSDDE8u0
Using Rasa to Power an Immersive Multimedia Conversational Experience | Rasa ...Rasa Technologies
Human-to-human electronic communication has moved from text (email) to voice (VoIP) to augmented video (Zoom/Skype). Similarly, the medium for human-to-machine conversation has moved from text (chatbots) to voice, with voice-enabled chatbots in wide use today. The next step in this evolution is a video-enabled conversational experience. Each medium change brings its own technical challenges. Creating a good voice experience involves more than just hooking up a chatbot to a text-to-speech and speech-to-text service. Vocinity has developed a platform for voice-enabled chatbots that has been in production for almost 2 years. We're updating our platform to support a multimedia experience where the bot communicates via video, voice and text messages and images. Using Rasa to provide the conversational logic for the immersive multimedia bot enables us to meet the challenges in voice/video communication. Rasa’s power and flexibility enabled us to extend it to support voice and video.
Presented by CTO of Vocinity, Nathan Stratton at the 2021 Rasa Summit https://rasa.com/summit/
This document discusses Conversation-Driven Development (CDD) as a process for building conversational AI assistants. It describes CDD as involving six key actions: sharing prototypes with test users, reviewing user conversations, annotating conversations as training data, testing the assistant, tracking the success of conversations, and fixing issues found. CDD captures lessons learned from building conversational AI to help teams iteratively improve assistants based on user feedback. The document also promotes Rasa X as a tool that can help teams implement CDD through features like reviewing conversations, annotating data, and continuous integration testing.
Webinar: How to Use Integrated Version Control in Rasa XRasa Technologies
The document discusses integrated version control in Rasa X, which allows teams to version training data and push changes made in Rasa X to a target branch connected to a remote git repository. It provides an overview of getting started with setting up version control by deploying Rasa X, adding an SSH key to GitHub, and connecting Rasa X. The document also discusses how integrated version control connects Rasa X to downstream workflows like automated testing and deployments and brings it in line with software engineering best practices.
Developing Intelligent Chatbots using RASA, OW2con'19, June 12-13, 2019 in ParisOW2
In this presentation given by Tobias Wochinger from RASA and Richard Popa from Orange, find out how Orange is developing AI assistants using the best solutions on the market in collaboration with RASA.
Building an AI Assistant Factory - Rasa Summit 2021Rasa Technologies
Presented by Dominique Boucher Chief Solutions Architect – AI Factory, National Bank of Canada and Eric Charton Senior AI Director AI, National Bank of Canada at the 2021 Rasa Summit. Check out the talk recording on YouTube https://youtu.be/EzTfSDDE8u0
Using Rasa to Power an Immersive Multimedia Conversational Experience | Rasa ...Rasa Technologies
Human-to-human electronic communication has moved from text (email) to voice (VoIP) to augmented video (Zoom/Skype). Similarly, the medium for human-to-machine conversation has moved from text (chatbots) to voice, with voice-enabled chatbots in wide use today. The next step in this evolution is a video-enabled conversational experience. Each medium change brings its own technical challenges. Creating a good voice experience involves more than just hooking up a chatbot to a text-to-speech and speech-to-text service. Vocinity has developed a platform for voice-enabled chatbots that has been in production for almost 2 years. We're updating our platform to support a multimedia experience where the bot communicates via video, voice and text messages and images. Using Rasa to provide the conversational logic for the immersive multimedia bot enables us to meet the challenges in voice/video communication. Rasa’s power and flexibility enabled us to extend it to support voice and video.
Presented by CTO of Vocinity, Nathan Stratton at the 2021 Rasa Summit https://rasa.com/summit/
Conversational AI with Rasa - PyData WorkshopTom Bocklisch
Workshop building a simple chatbot with Rasa NLU and Core. Additional resources can be found in the repository https://github.com/tmbo/rasa-demo-pydata18/edit/master/README.md
The document discusses what a chatbot is and how to build one using tools like Rasa NLU and Core. It provides an overview of the chatbot development process, including collecting domain data, tagging it with labels and entities, defining stories, and deploying the chatbot using Rasa on private or public clouds. The presentation then demonstrates a Rasa chatbot and takes questions from the audience.
Behavior Driven development is the process of exploring, discovering, defining and driving the desired behavior of software system by using conversation, concrete examples and automated tests.
Rasa Developer Summit - Josh Converse, Dynamic Offset - Three Part Harmony: H...Rasa Technologies
It has been said of the Beatles that the whole (the band) is greater than the sum of the parts (the band members). The same can hold true for open source software. This talk explores combining disparate open source technologies, backed by a Rasa "brain", to yield amazing results, explored through building a phone-based voice receptionist.
WHAT YOU'LL LEARN
The open source ecosystem represents a suite of great standalone technologies. Combining them in a product can yield even more amazing results
Rasa provides the much-needed flexibility for your system to react and adapt to the real world.
Leveraging open source (Rasa included) allows you to spend more time on the most interesting parts of your product.
Josh Converse is the founder of Dynamic Offset, a boutique consulting firm specializing in mobile, web, and conversational experiences. Prior to consulting he held tech lead roles at both Google and Apple.
Mengenal Software Development Life Cycle - Gilang RamadhanDicodingEvent
Menjadi seorang Software Developer tak akan lepas dengan namanya pembuatan aplikasi. Membangun aplikasi yang berkualitas, pasti telah melalui flow atau alur yang sangat panjang. Mulai dari memikirkan ide, membuat desain, menulis kode, mengujinya, hingga memasarkan aplikasi tersebut secara publik. Ini biasanya disebut dengan SDLC atau Software Development Lifecycle.
Namun, tahukah kamu proses yang harus dilalui untuk membuat sebuah aplikasi yang berkualitas? Jangan lewatkan sesi LIVE kali ini.
Poin-poin yang dibahas:
- Pengertian Software Development Life Cycle
- Tahapan yang biasa dilalui
- Tips dan Trik seputar alur kerja pembuatan aplikasi
QA has always been under-rated and thus it is important to consider this equally important as the Dev. If we look at the Chatbot QA, it had been considered as a highly challenging work specially when you do not know where your bot may break while you sequentially will be only running your flow (stories). Most of the companies / tools only check the flow which are coded in a fixed format which often breaks while testing. There may be cases where bot are migrated to new version and it breaks. The presentation will discuss the possibilities to test the bots by helping folks to create their coverage matrix for your stories, efficiently looking at the logs and mine information and most importantly what to test and which components to test.
Presented by Director QA, DevOps & AIML at APTY.IO, Soumya Mukherjee at the 2021 Rasa Summit https://rasa.com/summit/
Conversational interfaces for chatbots and artificial intelligence finalDon Holloway
This document discusses conversational interfaces for chatbots and AI. It defines a conversational interface as the next evolution in user interfaces that allows computers to communicate like people through messaging platforms powered by machine learning (NLU). The key concepts discussed include using natural language understanding (NLU) to extract a user's intent and entities to take appropriate actions and provide conversational responses based on machine learning models. Popular Python libraries for building conversational interfaces include Rasa NLU for intent recognition and entity extraction, Rasa Core for dialog management, and connectors like Flask. Code examples and resources for further learning are also provided.
Voice First: Ready Your Content to Serve 50% of Global Searches | Rasa Summit...Rasa Technologies
Future of Digital Experience would be driven by the intersection of Content & Context, where Context would take the lead. Search is changing, and so is the way consumers choose to engage with businesses locally or globally. There is a distinct move away from screens and keyboards, and into voice-based interactions. Voice search is becoming a fast-growing habit across consumer segments and fundamentally transforming how people and businesses transact on the internet. Consider this:
- In 2020, there will be 4.2 billion digital voice assistants being used in devices around the world. Forecasts suggest that by 2024, the number of digital voice assistants will reach 8.4 billion units – a number higher than the world’s population.
- Sales revenue from wearable devices is projected to grow from around 16 billion U.S. Dollars in 2016 to around 73 billion U.S. dollars by 2022.
- McDonalds is adding 1000 kiosks per quarter for self-ordering and checkout since 2018 and acquired Appente to boost voice tech on these devices.
In the talk which includes hands-on demo, we will talk about how the current CMS ecosystem is structured and how the new-age headless CMS is changing how we create content. We will also look at the Schema.org usefulness.
Here are some key takeaways:
- Why a voice content strategy is critical for enterprises
- How and Why to make your content future proof
- The differences between voice-based and web-based content, and how that affects the user experience
- The basics of optimizing your content for voice search
- Why bots should be your next strategic investment
Demos:
- A quick view of the schemas important for the VSO
- Example of sites ranking in the Voice
Presented by Director - Digital Experience at Srijan, Gaurav Mishra at the 2021 Rasa Summit.
Testing stage. being ahead business with cucumberAlex Mikitenko
Cucumber is a tool that allows teams to collaborate and define executable specifications for software features using a common language. It operates at a high level of abstraction to drive implementation rather than simply reflect code. The document discusses how Cucumber can be used with a Spotify engineering model through a BDD workflow involving user stories, business scenarios, step definitions, and page objects. It provides guidelines for writing good behavior specifications and references additional resources for learning more about Cucumber.
So, you have an API! Should you leave it at this or also offer a client library/SDK? Using examples from other API providers, this talk will help you decide. We‘ll look at good practices for designing and documenting APIs as well as SDKs, to achieve good developer experience, no matter which choice!
This talk was held at "API the Docs" in Paris on April 24th, 2018.
https://apithedocs.org/paris2018
Choosing a career goal as an IT graduateTahsin Abrar
The document discusses career path options for IT graduates including programming, UI/UX, systems engineering, cybersecurity, project management, and data science. It recommends choosing a career path and programming language wisely. It also suggests becoming familiar with buzzwords, using common tools like Git and IDEs, and avoiding procrastination. The document aims to help graduates choose the right IT career.
This document summarizes a talk on using Behavior Driven Development (BDD) with Cucumber and Java. The talk covers:
- An overview of BDD and its format using user stories and scenarios
- How Cucumber supports BDD with plain text specifications that can be implemented in multiple languages like Java
- The advantages of Cucumber like having a single source of truth and focusing development on customer needs
- Using Cucumber-JVM for Java projects, including running tests with JUnit and the command line
- Setting up a sample project in IntelliJ with Cucumber
- An overview of the Geb framework for automating web tests in Groovy
- Time for questions at the end
This document provides an overview of building conversational chatbots using Dialogflow. It begins with defining what chatbots are and discussing their history. It then explains the types of chatbots and how Dialogflow uses artificial intelligence to enable chatbots that can learn from interactions. The document demonstrates how to create an agent and intents in Dialogflow to develop a basic chatbot. It also discusses entities, integration options, and using fulfillment for additional functionality. The presenter provides resources for learning more about Dialogflow and chatbot development.
How to Build a Dialogflow App by using Actions on Google.Yuting Liu
This document discusses building actions for Google Assistant using Dialogflow. It covers setting up a Dialogflow agent project, training the agent with sample conversations, defining intents and parameters, configuring responses, adding fulfillment logic, and integrating the agent with other services like Line. The document also provides instructions for deploying the Dialogflow agent to Firebase Functions and includes some tips for getting started with building agents.
MongoDB World 2019: Look, Ma, No Servers! Serverless Application Development ...MongoDB
This document summarizes a talk about serverless application development using MongoDB Stitch. The talk discusses what serverless and Stitch are, how to use Stitch's QueryAnywhere, Functions, and Triggers features, and how to deploy serverless code. Serverless applications can reduce infrastructure management, allow independent deployments, and only charge for resources used. MongoDB Stitch is a platform that allows building serverless applications using MongoDB as the database with features like serverless functions and mobile sync capabilities.
Deprecating the state machine: building conversational AI with the Rasa stackJustina Petraitytė
Rasa NLU & Rasa Core are the leading open source libraries for building machine learning-based chatbots and voice assistants. In this live-coding workshop, you will learn the fundamentals of conversational AI and how to build your own using the Rasa Stack.
The document provides an overview of the MEAN stack, which consists of MongoDB, Express, Angular, and Node.js. It describes each component and how they work together. Node.js is a JavaScript runtime built on Chrome's V8 engine. Mongo is a NoSQL database with a flexible JSON data model. Express is a minimalist web framework for Node.js. Angular allows building dynamic web applications in JavaScript for both server-side and client-side execution. The Angular CLI makes it easy to create and develop Angular applications.
Surbhi Gupta is a full stack developer at Cognizant with 1.9 years of experience. She has a Bachelor's degree in Computer Science and Engineering from Jaypee University of Engineering & Technology. Her technical skills include Java, Python, Angular 6, Node JS, HTML, CSS, Bootstrap 4, PostgreSQL, Neo4j, Elastic Search, RabbitMQ, and Grafana. She currently works on Insights, Cognizant's DevOps monitoring application, where she contributes as a front-end developer and is involved in migrating the product to newer technologies and adding new features. Previously, she worked on an identity access management project for Nomura Holdings in Mumbai.
“We have had MuleSoft for more than a year, so where is my reusability?” My new client asked this question in an almost exasperated tone. Many companies purchase MuleSoft with the expectation that it will deliver on reusability, decreased integration costs, and accelerated innovation. Achieving reusability is deliberate. Tim will share three essential tips to help any enterprise achieve more reusability with MuleSoft.
ChatGPT and Beyond - Elevating DevOps ProductivityVictorSzoltysek
In the dynamic field of DevOps, the quest for efficiency and productivity is endless. This talk introduces a revolutionary toolkit: Large Language Models (LLMs), including ChatGPT, Gemini, and Claude, extending far beyond traditional coding assistance. We'll explore how LLMs can automate not just code generation, but also transform day-to-day operations such as crafting compelling cover letters for TPS reports, streamlining client communications, and architecting innovative DevOps solutions. Attendees will learn effective prompting strategies and examine real-life use cases, demonstrating LLMs' potential to redefine productivity in the DevOps landscape. Join us to discover how to harness the power of LLMs for a comprehensive productivity boost across your DevOps activities.
The document is a curriculum vitae for Sameer Ishwar Singh Parihar that outlines his educational qualifications and work experience. It summarizes his skills in programming languages like C#, VB.Net, and databases like SQL. It also lists 5 projects from his previous roles developing applications in C# and VB.Net for testing, asset management, and automating industrial processes.
Conversational AI with Rasa - PyData WorkshopTom Bocklisch
Workshop building a simple chatbot with Rasa NLU and Core. Additional resources can be found in the repository https://github.com/tmbo/rasa-demo-pydata18/edit/master/README.md
The document discusses what a chatbot is and how to build one using tools like Rasa NLU and Core. It provides an overview of the chatbot development process, including collecting domain data, tagging it with labels and entities, defining stories, and deploying the chatbot using Rasa on private or public clouds. The presentation then demonstrates a Rasa chatbot and takes questions from the audience.
Behavior Driven development is the process of exploring, discovering, defining and driving the desired behavior of software system by using conversation, concrete examples and automated tests.
Rasa Developer Summit - Josh Converse, Dynamic Offset - Three Part Harmony: H...Rasa Technologies
It has been said of the Beatles that the whole (the band) is greater than the sum of the parts (the band members). The same can hold true for open source software. This talk explores combining disparate open source technologies, backed by a Rasa "brain", to yield amazing results, explored through building a phone-based voice receptionist.
WHAT YOU'LL LEARN
The open source ecosystem represents a suite of great standalone technologies. Combining them in a product can yield even more amazing results
Rasa provides the much-needed flexibility for your system to react and adapt to the real world.
Leveraging open source (Rasa included) allows you to spend more time on the most interesting parts of your product.
Josh Converse is the founder of Dynamic Offset, a boutique consulting firm specializing in mobile, web, and conversational experiences. Prior to consulting he held tech lead roles at both Google and Apple.
Mengenal Software Development Life Cycle - Gilang RamadhanDicodingEvent
Menjadi seorang Software Developer tak akan lepas dengan namanya pembuatan aplikasi. Membangun aplikasi yang berkualitas, pasti telah melalui flow atau alur yang sangat panjang. Mulai dari memikirkan ide, membuat desain, menulis kode, mengujinya, hingga memasarkan aplikasi tersebut secara publik. Ini biasanya disebut dengan SDLC atau Software Development Lifecycle.
Namun, tahukah kamu proses yang harus dilalui untuk membuat sebuah aplikasi yang berkualitas? Jangan lewatkan sesi LIVE kali ini.
Poin-poin yang dibahas:
- Pengertian Software Development Life Cycle
- Tahapan yang biasa dilalui
- Tips dan Trik seputar alur kerja pembuatan aplikasi
QA has always been under-rated and thus it is important to consider this equally important as the Dev. If we look at the Chatbot QA, it had been considered as a highly challenging work specially when you do not know where your bot may break while you sequentially will be only running your flow (stories). Most of the companies / tools only check the flow which are coded in a fixed format which often breaks while testing. There may be cases where bot are migrated to new version and it breaks. The presentation will discuss the possibilities to test the bots by helping folks to create their coverage matrix for your stories, efficiently looking at the logs and mine information and most importantly what to test and which components to test.
Presented by Director QA, DevOps & AIML at APTY.IO, Soumya Mukherjee at the 2021 Rasa Summit https://rasa.com/summit/
Conversational interfaces for chatbots and artificial intelligence finalDon Holloway
This document discusses conversational interfaces for chatbots and AI. It defines a conversational interface as the next evolution in user interfaces that allows computers to communicate like people through messaging platforms powered by machine learning (NLU). The key concepts discussed include using natural language understanding (NLU) to extract a user's intent and entities to take appropriate actions and provide conversational responses based on machine learning models. Popular Python libraries for building conversational interfaces include Rasa NLU for intent recognition and entity extraction, Rasa Core for dialog management, and connectors like Flask. Code examples and resources for further learning are also provided.
Voice First: Ready Your Content to Serve 50% of Global Searches | Rasa Summit...Rasa Technologies
Future of Digital Experience would be driven by the intersection of Content & Context, where Context would take the lead. Search is changing, and so is the way consumers choose to engage with businesses locally or globally. There is a distinct move away from screens and keyboards, and into voice-based interactions. Voice search is becoming a fast-growing habit across consumer segments and fundamentally transforming how people and businesses transact on the internet. Consider this:
- In 2020, there will be 4.2 billion digital voice assistants being used in devices around the world. Forecasts suggest that by 2024, the number of digital voice assistants will reach 8.4 billion units – a number higher than the world’s population.
- Sales revenue from wearable devices is projected to grow from around 16 billion U.S. Dollars in 2016 to around 73 billion U.S. dollars by 2022.
- McDonalds is adding 1000 kiosks per quarter for self-ordering and checkout since 2018 and acquired Appente to boost voice tech on these devices.
In the talk which includes hands-on demo, we will talk about how the current CMS ecosystem is structured and how the new-age headless CMS is changing how we create content. We will also look at the Schema.org usefulness.
Here are some key takeaways:
- Why a voice content strategy is critical for enterprises
- How and Why to make your content future proof
- The differences between voice-based and web-based content, and how that affects the user experience
- The basics of optimizing your content for voice search
- Why bots should be your next strategic investment
Demos:
- A quick view of the schemas important for the VSO
- Example of sites ranking in the Voice
Presented by Director - Digital Experience at Srijan, Gaurav Mishra at the 2021 Rasa Summit.
Testing stage. being ahead business with cucumberAlex Mikitenko
Cucumber is a tool that allows teams to collaborate and define executable specifications for software features using a common language. It operates at a high level of abstraction to drive implementation rather than simply reflect code. The document discusses how Cucumber can be used with a Spotify engineering model through a BDD workflow involving user stories, business scenarios, step definitions, and page objects. It provides guidelines for writing good behavior specifications and references additional resources for learning more about Cucumber.
So, you have an API! Should you leave it at this or also offer a client library/SDK? Using examples from other API providers, this talk will help you decide. We‘ll look at good practices for designing and documenting APIs as well as SDKs, to achieve good developer experience, no matter which choice!
This talk was held at "API the Docs" in Paris on April 24th, 2018.
https://apithedocs.org/paris2018
Choosing a career goal as an IT graduateTahsin Abrar
The document discusses career path options for IT graduates including programming, UI/UX, systems engineering, cybersecurity, project management, and data science. It recommends choosing a career path and programming language wisely. It also suggests becoming familiar with buzzwords, using common tools like Git and IDEs, and avoiding procrastination. The document aims to help graduates choose the right IT career.
This document summarizes a talk on using Behavior Driven Development (BDD) with Cucumber and Java. The talk covers:
- An overview of BDD and its format using user stories and scenarios
- How Cucumber supports BDD with plain text specifications that can be implemented in multiple languages like Java
- The advantages of Cucumber like having a single source of truth and focusing development on customer needs
- Using Cucumber-JVM for Java projects, including running tests with JUnit and the command line
- Setting up a sample project in IntelliJ with Cucumber
- An overview of the Geb framework for automating web tests in Groovy
- Time for questions at the end
This document provides an overview of building conversational chatbots using Dialogflow. It begins with defining what chatbots are and discussing their history. It then explains the types of chatbots and how Dialogflow uses artificial intelligence to enable chatbots that can learn from interactions. The document demonstrates how to create an agent and intents in Dialogflow to develop a basic chatbot. It also discusses entities, integration options, and using fulfillment for additional functionality. The presenter provides resources for learning more about Dialogflow and chatbot development.
How to Build a Dialogflow App by using Actions on Google.Yuting Liu
This document discusses building actions for Google Assistant using Dialogflow. It covers setting up a Dialogflow agent project, training the agent with sample conversations, defining intents and parameters, configuring responses, adding fulfillment logic, and integrating the agent with other services like Line. The document also provides instructions for deploying the Dialogflow agent to Firebase Functions and includes some tips for getting started with building agents.
MongoDB World 2019: Look, Ma, No Servers! Serverless Application Development ...MongoDB
This document summarizes a talk about serverless application development using MongoDB Stitch. The talk discusses what serverless and Stitch are, how to use Stitch's QueryAnywhere, Functions, and Triggers features, and how to deploy serverless code. Serverless applications can reduce infrastructure management, allow independent deployments, and only charge for resources used. MongoDB Stitch is a platform that allows building serverless applications using MongoDB as the database with features like serverless functions and mobile sync capabilities.
Deprecating the state machine: building conversational AI with the Rasa stackJustina Petraitytė
Rasa NLU & Rasa Core are the leading open source libraries for building machine learning-based chatbots and voice assistants. In this live-coding workshop, you will learn the fundamentals of conversational AI and how to build your own using the Rasa Stack.
The document provides an overview of the MEAN stack, which consists of MongoDB, Express, Angular, and Node.js. It describes each component and how they work together. Node.js is a JavaScript runtime built on Chrome's V8 engine. Mongo is a NoSQL database with a flexible JSON data model. Express is a minimalist web framework for Node.js. Angular allows building dynamic web applications in JavaScript for both server-side and client-side execution. The Angular CLI makes it easy to create and develop Angular applications.
Surbhi Gupta is a full stack developer at Cognizant with 1.9 years of experience. She has a Bachelor's degree in Computer Science and Engineering from Jaypee University of Engineering & Technology. Her technical skills include Java, Python, Angular 6, Node JS, HTML, CSS, Bootstrap 4, PostgreSQL, Neo4j, Elastic Search, RabbitMQ, and Grafana. She currently works on Insights, Cognizant's DevOps monitoring application, where she contributes as a front-end developer and is involved in migrating the product to newer technologies and adding new features. Previously, she worked on an identity access management project for Nomura Holdings in Mumbai.
“We have had MuleSoft for more than a year, so where is my reusability?” My new client asked this question in an almost exasperated tone. Many companies purchase MuleSoft with the expectation that it will deliver on reusability, decreased integration costs, and accelerated innovation. Achieving reusability is deliberate. Tim will share three essential tips to help any enterprise achieve more reusability with MuleSoft.
ChatGPT and Beyond - Elevating DevOps ProductivityVictorSzoltysek
In the dynamic field of DevOps, the quest for efficiency and productivity is endless. This talk introduces a revolutionary toolkit: Large Language Models (LLMs), including ChatGPT, Gemini, and Claude, extending far beyond traditional coding assistance. We'll explore how LLMs can automate not just code generation, but also transform day-to-day operations such as crafting compelling cover letters for TPS reports, streamlining client communications, and architecting innovative DevOps solutions. Attendees will learn effective prompting strategies and examine real-life use cases, demonstrating LLMs' potential to redefine productivity in the DevOps landscape. Join us to discover how to harness the power of LLMs for a comprehensive productivity boost across your DevOps activities.
The document is a curriculum vitae for Sameer Ishwar Singh Parihar that outlines his educational qualifications and work experience. It summarizes his skills in programming languages like C#, VB.Net, and databases like SQL. It also lists 5 projects from his previous roles developing applications in C# and VB.Net for testing, asset management, and automating industrial processes.
The document provides an overview of software development methodologies and best practices used in corporate America. It discusses waterfall and agile methodologies, emphasizing agile's benefits like constant delivery of small features, transparency, and adaptability. It also covers topics like source control using Git, code quality practices like testing and code reviews, and considerations for applying agile principles in a research lab setting.
This document outlines functional requirements for a document management system. It includes requirements for document creation, versioning, approval workflows, categorization, search, and reporting. It also includes requirements for software capabilities like templates, electronic signatures, distribution, and compatibility with Microsoft Office. Vendor services and technical requirements are also specified relating to implementation, support, hosting, and compatibility with browsers and devices.
This document provides an overview and summary of Steve Forte's half-day Agile seminar presented by SSW. The seminar covers topics including an introduction to Agile and Scrum, Agile estimation, Agile and offshore teams, and Agile tools. Attendees can ask questions throughout the interactive seminar.
This document discusses concepts and practices related to Scrum project management methodology. It addresses frequently asked questions about Scrum roles like Product Owner and Scrum Master. It also covers Scrum artifacts like the Product Backlog and Sprint Backlog, as well as Scrum events like the Sprint Planning meeting and Daily Scrum. The document provides guidance on properly defining acceptance criteria for user stories, estimating story points, and ensuring the Product Backlog is ready before Sprint Planning.
This document discusses rapid software development methods like agile development and extreme programming (XP). It explains that agile methods use iterative development with customer involvement to quickly deliver working software. XP in particular emphasizes practices like test-driven development, pair programming, and frequent small releases. The document also covers rapid application development tools and the use of prototypes to help define requirements before full system development.
Ravi Kumar is an SAP ABAP Consultant with over 8 years of experience developing and supporting SAP R/3 implementations. He has extensive experience developing reports, BDC programs, user exits, enhancements and other custom ABAP objects for clients across various industries. His most recent role is as an SAP ABAP Consultant for HP Enterprise India, where he is developing custom objects for an SAP implementation at Welspun India Limited.
Cleaning Up the Mess: Modernizing Your Dev Team’s Outdated WorkflowBohyun Kim
A talk given at the 2017 ALA (American Library Association) Annual Conference, Chicago, June 25, 2017. Presenters: Bohyun Kim, Associate Director for Library Applications and Knowledge Systems, Brad Gerhart, Web Developer, Zak Burke, Senior Web Developer from
University of Maryland, Baltimore - Health Sciences and Human Services Library.
This document provides information about a proposal to develop version 3 of the Mifos Android Field Operations app as part of Google Summer of Code (GSoC) 2016. The proposal outlines refactoring the app to use the Model-View-Presenter architecture pattern, adding offline content availability, increasing test coverage, and implementing new features like collection sheets, staff notifications, and client editing. The proposer provides their contact information, previous projects, and a 12-week schedule to complete the work in two phases - refactoring and adding core functionality in phase 1, then additional features and enhancements in phase 2. The proposer has already submitted 5 patches or pull requests to the Mifos-X project on GitHub.
This document discusses Puppet's plans to introduce team workspaces in Puppet Enterprise. Workspaces will allow organizations to separate infrastructure, code, and access by team. This will give teams more autonomy while still allowing organizations to standardize certain aspects across teams. Workspaces are already integrated with Continuous Delivery for Puppet Enterprise and will soon include additional reporting and running of tasks and plans directly within workspaces. The document encourages providing feedback on workspaces through a short survey.
My name is Senthil Kumar and I hold a Degree in Master of Computer Application with the total working experience of 8.5+ years having a good knowledge of Automation test life cycle which includes the designing, coding, testing, documentation and implementation of the automation framework. Expertise in designing of Hybrid framework for web, windows, main-frame and Siebel applications. I had done Automation Test Estimation for the same. I am confident that my presentation skills and high quality and cost effective methodologies can secure big automation projects for the company. As I worked with a global company I am well aware about the work culture of MNCs. My command over QTP/UFT, QC/ALM, VB Scripting, VBA, SQL and languages like C, C++ makes me a qualified Automation Test Engineer.
Integrating User Centered Design with Agile DevelopmentJulia Borkenhagen
The document discusses integrating user experience (UX) design into an agile development process. It recommends doing initial user research, creating a high-level concept upfront with sitemaps, wireframes and templates. The UX team should work one sprint ahead of development to test prototypes and pass designs to developers. Frequent short usability tests are more efficient than long tests. Development and UX teams should collaborate throughout with UX involved in analysis and development sprints. Challenges include resource availability, working on multiple sprints, and client demands and involvement.
The document discusses agile engineering practices for software development, including user stories/use cases, test-driven development, continuous integration, precise design, merciless refactoring, collective code ownership, coding conventions, pair programming, code reviews, and steps for adopting agile practices. It provides an overview of each practice and emphasizes adopting test-driven development first when transitioning to agile.
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...AgileNetwork
Agile Mumbai 2022
Combining Human and Artificial Intelligence for Business Agility
Rohit Handa
Director, Digital Products & Platforms, HCL Technologies Ltd
The document provides an overview of Agile and Scrum methodologies. It describes key concepts like the Agile manifesto, Scrum roles, ceremonies like daily stand-ups and retrospectives, and practices like user stories, estimation, and burn-down charts. The objective is to familiarize people with the basic principles and processes in Agile and Scrum development.
Software design is the process of planning the structure and interfaces of a software program to ensure it functions properly and meets requirements. It includes architectural design to break the program into components and detailed design to break components into classes and interfaces. Software design patterns provide reusable solutions to common problems in design. The most important patterns include adapter, factory method, state, builder, strategy, observer, and singleton. The software design process involves research, prototyping, development, testing, and maintenance.
n this talk, Rsqrd welcomes Emad Elwany, CTO and Co-Founder of Lexion! He discusses his experiences with ML tooling and how it has evolved through the lifespan of Lexion, and shares his findings on important considerations, problems and solutions, and how decisions about ML tooling have changed over time through the stages of a startup.
**These slides are from a talk given at Rsqrd AI. Learn more at rsqrdai.org**
Slides from "Taking an Holistic Approach to Product Quality"Peter Marshall
This is the base material used during a half day workshop at expoQA 17 June 2019. Peter Marshall runs over the necessary technical, organisational, and improvement practices required to deliver high quality software. Deep dives into Continuous delivery, devops, organisational structures, agile and digital transformation.
Abstract
The methods used for conventional software development cannot be used directly for the development of web applications. Today
most of the companies use scrum methodology for the development of web applications. But it seem to be difficult to use the scrum
in large projects because of the change of requirement late in the project and also it is difficult apply scrum in a big team. This
paper identifies and analyses the various changes required in the scrum methodology to make them applicable for the large
projects and reduce the cost.
Keywords: software development model, hybrid model, scrum methodology, prototype models
The document discusses creating empathetic conversational experiences through affective intelligence and mental state inference. It describes how sentiment analysis, emotion detection, and mental state tracking can be used to develop empathic dialog policies that improve the user's affective state. The system utilizes commonsense knowledge bases and reasoning to predict how events affect a user's emotions and motivations. The goal is to create more engaging experiences for users by understanding their perspective and responding supportively and understandingly.
End-to-end dialogue systems, or a feature which wasn’t meant to happen | Rasa...Rasa Technologies
End-to-end training allows a model to directly predict responses based on the preceding text rather than using abstract representations like intents. The researcher conducted experiments showing end-to-end could work for dialogues, then integrated it into Rasa by allowing mixed format stories and an optional intents system. They welcomed users to try the new experimental end-to-end feature in Rasa 2.2.
The missing link: How AI can help create a safer society and better businesse...Rasa Technologies
According to Home Office data, the proportion of crimes solved by police in England and Wales has fallen to the lowest level recorded. Crime investigations are inherently expensive and each case takes a lot of man-hours and resource-poor cities are less able to reduce investigators' caseloads. With the growing amount of information held in siloed systems and people’s minds, it’s becoming increasingly difficult to grasp all the links and see the relations. Data is overwhelming. What if by using latest technology such as AI and NLP we could reduce time in solving crimes and the response times at the scene? What if more lives can be solved because AI can help automatically make a link between information faster than any human could do? What if that same technology could help us become more efficient and satisfied employees while decreasing costs for the companies? In this talk I would share the specific formula governments companies can adopt to successfully employ AI while keeping humans in the loop making them more efficient, productive and happy.
Presented by Managing Director of Untrite, Kamila Hankiewicz at the 2021 Rasa Summit https://rasa.com/summit/
Boss - Bringing More Diversity to Tech | Rasa SummitRasa Technologies
Bruna Moreira created the Big Open Source Sister (BOSS) mentoring program to welcome and guide underrepresented groups through contributing to open source communities. The program focuses on teaching the basics of open source through a 12-week online class, mentorship, and hands-on practices contributing to the LAPPIS rasa boilerplate project. Participants gain autonomy to contribute to other open source projects after completing the program.
How Our Team Uses Rasa to Learn from Real Conversations | Rasa SummitRasa Technologies
Autodesk created the Autodesk Virtual Agent (AVA) to provide customer support for their products. The initial AVA used a decision tree and natural language processing to answer questions. Autodesk collected feedback showing customers preferred a conversational interface over a decision tree. Autodesk then redesigned AVA using a modular architecture to improve customer experience and scale across channels. The new AVA aims to reduce customer effort through natural language, personalized solutions, and routing customers to self-service options or human agents when needed.
The document discusses applying conversational AI in the enterprise. It notes that Rasa has over 10 million downloads worldwide across various industries. It also discusses some challenges of applying conversational AI at scale in enterprises, including meeting security standards, integrating with third-party services, varying DevOps expertise, and scaling conversations while maintaining a seamless user experience. The document provides examples of how AI assistants need to address security, integration with other services, and DevOps practices when scaling within an enterprise.
STAR: A Schema-Guided Dialog Dataset for Transfer Learning | Rasa Summit 2021 Rasa Technologies
This document introduces the STAR dataset, a schema-guided dialog dataset for transfer learning. It contains over 5820 dialogs across 24 tasks in 13 domains. The dialogs were collected using task-specific schemas to guide the interactions. This allows the data to be used for zero-shot transfer learning across tasks. The document discusses how the schemas and task structures were designed to improve consistency, handle various user behaviors, and increase task difficulty progression. It also presents several schema-guided models that achieve improved next action prediction and response generation compared to non-schema models, including on zero-shot transfer tasks. The goal of the dataset and models is to enable dialog agents to quickly adapt to new tasks using only a task-specific schema
Ethnobots: Reimagining Chatbots as Ethnographic Research Tools | Rasa Summit ...Rasa Technologies
Presented by inChat Co-Founder & Design Anthropologist, Hector Fried and inChat Co-Founder & Technology Developer Rory Gianni at the 2021 Rasa Summit. Watch the talk recording on our summit site: https://rasa.com/summit/
The State of Conversation Design - Designing for the Conversational FutureRasa Technologies
The document is a transcript from a conversation design training course. It covers many topics related to designing conversational interfaces and assistants, including fundamentals of conversation design, understanding user scenarios, designing prompts, testing assistants, improving performance metrics, building training phrases, and more. The transcript copyright is held by Conversation Design Institute B.V. and encourages learning more about conversation design through their courses.
Building an End-to-End Test Automation Pipeline for Conversational AI | Rasa ...Rasa Technologies
Presented by Botium GmbH Co-founder and CEO Christoph Börner at the 2021 Rasa Summit. Check out the talk recording on YouTube: https://youtu.be/YfOxeoFRMmM
Research Updates from Rasa: Transformers in NLU and DialogueRasa Technologies
Alan Nichol, co-founder & CTO of Rasa talks about the role that transformer-based architectures play in the state-of-the-art models for dialogue and language understanding. Alan covers the dialogue transformer (aka the TED policy) as well as a new state-of-the-art lightweight, multitask transformer architecture for NLU: Dual Intent and Entity Transformer (DIET) designed by the Rasa research team.
Rasa Developer Summit - Bing Liu - Interactive Learning of Task-Oriented Dial...Rasa Technologies
Task-oriented spoken dialog system is a prominent component in today’s virtual personal assistant (e.g. Alexa, Siri), which enables people to perform everyday tasks by interacting with devices via voice interfaces. Recent advances in deep learning enabled new research directions for end-to-end dialog modeling. Such data-driven end-to-end learning systems address many limitations of conventional dialog systems. This talk will review the research work on deep learning and reinforcement learning for neural dialog systems. We will further discuss hybrid dialog learning frameworks that combine offline training and online interactive learning with human-in-the-loop. This talk will conclude with the challenges and directions in further advancing data-drive conversational AI systems. Bing Liu is a research scientist in Facebook working on conversational AI. His research interests focus on machine learning for spoken language processing, natural language understanding, and dialog systems. He develops conversational AI system that learns from both offline annotated samples and online interactions. Bing received his Ph.D. degree from Carnegie Mellon University in 2018 where he worked on deep learning and reinforcement learning for task-oriented dialog systems. Before joining Facebook, he interned at Google Research working on end-to-end learning of neural dialog systems.
Rasa Developer Summit - Praneeth Gubbala, NLP Engineer, Sam's Club at Walmart...Rasa Technologies
Sam's Club at Walmart is helping works and customers through voice and text-based assistants. Find out what Walmart engineers are doing with technical working details, details of advantages of Rasa plus custom improvements made to Rasa, along with challenges faces in text classificiation and entity extraction issues.
WHAT YOU'LL LEARN
The Conversational AI helping to solve in the area of the retail facility workers
Overview of the voice-based personal assistants with in-depth technical working details
Advantages of using Rasa along with the various number of improvements made on Rasa to customize based on the need
The Challenges resolved in the Text classification and entity extraction issues while implementing various entities.
Praneeth Gubbala works as an NLP Engineer at Sam's Club Technology (Walmart) developing chatbots and digital assistants that power one of the largest companies in the world. Praneeth previously worked with the Samsung Bixby NLU team for three years in the conversational AI field.
Rasa Developer Summit - Tom Bocklisch, Rasa - Product Updates from RasaRasa Technologies
Rasa recently released new versions of Rasa 1.3 and Rasa X 0.21 that focus on improving developer workflows for building, improving, and deploying conversational AI assistants. Some key areas of focus include integrating domain knowledge, improving response generation, a new response editor in Rasa X, visualizing conversation flows through multi-story graphs, and increasing scalability.
Rasa Developer Summit - Alan Nichol, Rasa - Welcome & IntroRasa Technologies
This document provides an introduction and overview of information for the Rasa Developer Summit 2019. It notes there are 150 companies and 23 speakers in attendance. It also shows statistics on attendees' experience with Rasa and provides a brief history of Rasa's products. Additionally, it outlines the 5 levels of conversational AI that Rasa is working towards and emphasizes that conversational AI is still a work in progress where attendees can learn from each other and speakers.
Rasa Developer Summit - Juste Petraityte, Rasa - Rasa Community Updates & Out...Rasa Technologies
Community is at the heart of what we do at Rasa. In this talk, you will hear all about the latest community projects and events and will be the first to hear what exciting things are awaiting the Rasa community.
Rasa Developer Summit - William Galindez Ariaz, Octesoft - Dial Rasa for DinnerRasa Technologies
This document discusses using a chatbot to learn the Czech language and solve various problems. It proposes:
1. Creating a receptionist chatbot that can handle ordering food, seeing a doctor, or complaining, to learn Czech in a realistic conversational context.
2. Improving the problems the chatbot aims to solve by adding more contexts like flirting, and consolidating related datasets to build the chatbot's knowledge.
3. Exploring using the chatbot architecture for other tasks like automating invoice processing or searching a staff database, to build technical skills.
UiPath Test Automation using UiPath Test Suite series, part 5DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 5. In this session, we will cover CI/CD with devops.
Topics covered:
CI/CD with in UiPath
End-to-end overview of CI/CD pipeline with Azure devops
Speaker:
Lyndsey Byblow, Test Suite Sales Engineer @ UiPath, Inc.
UiPath Test Automation using UiPath Test Suite series, part 6DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 6. In this session, we will cover Test Automation with generative AI and Open AI.
UiPath Test Automation with generative AI and Open AI webinar offers an in-depth exploration of leveraging cutting-edge technologies for test automation within the UiPath platform. Attendees will delve into the integration of generative AI, a test automation solution, with Open AI advanced natural language processing capabilities.
Throughout the session, participants will discover how this synergy empowers testers to automate repetitive tasks, enhance testing accuracy, and expedite the software testing life cycle. Topics covered include the seamless integration process, practical use cases, and the benefits of harnessing AI-driven automation for UiPath testing initiatives. By attending this webinar, testers, and automation professionals can gain valuable insights into harnessing the power of AI to optimize their test automation workflows within the UiPath ecosystem, ultimately driving efficiency and quality in software development processes.
What will you get from this session?
1. Insights into integrating generative AI.
2. Understanding how this integration enhances test automation within the UiPath platform
3. Practical demonstrations
4. Exploration of real-world use cases illustrating the benefits of AI-driven test automation for UiPath
Topics covered:
What is generative AI
Test Automation with generative AI and Open AI.
UiPath integration with generative AI
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...Neo4j
Leonard Jayamohan, Partner & Generative AI Lead, Deloitte
This keynote will reveal how Deloitte leverages Neo4j’s graph power for groundbreaking digital twin solutions, achieving a staggering 100x performance boost. Discover the essential role knowledge graphs play in successful generative AI implementations. Plus, get an exclusive look at an innovative Neo4j + Generative AI solution Deloitte is developing in-house.
Communications Mining Series - Zero to Hero - Session 1DianaGray10
This session provides introduction to UiPath Communication Mining, importance and platform overview. You will acquire a good understand of the phases in Communication Mining as we go over the platform with you. Topics covered:
• Communication Mining Overview
• Why is it important?
• How can it help today’s business and the benefits
• Phases in Communication Mining
• Demo on Platform overview
• Q/A
How to Get CNIC Information System with Paksim Ga.pptxdanishmna97
Pakdata Cf is a groundbreaking system designed to streamline and facilitate access to CNIC information. This innovative platform leverages advanced technology to provide users with efficient and secure access to their CNIC details.
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionAggregage
Join Maher Hanafi, VP of Engineering at Betterworks, in this new session where he'll share a practical framework to transform Gen AI prototypes into impactful products! He'll delve into the complexities of data collection and management, model selection and optimization, and ensuring security, scalability, and responsible use.
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfMalak Abu Hammad
Discover how MongoDB Atlas and vector search technology can revolutionize your application's search capabilities. This comprehensive presentation covers:
* What is Vector Search?
* Importance and benefits of vector search
* Practical use cases across various industries
* Step-by-step implementation guide
* Live demos with code snippets
* Enhancing LLM capabilities with vector search
* Best practices and optimization strategies
Perfect for developers, AI enthusiasts, and tech leaders. Learn how to leverage MongoDB Atlas to deliver highly relevant, context-aware search results, transforming your data retrieval process. Stay ahead in tech innovation and maximize the potential of your applications.
#MongoDB #VectorSearch #AI #SemanticSearch #TechInnovation #DataScience #LLM #MachineLearning #SearchTechnology
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Albert Hoitingh
In this session I delve into the encryption technology used in Microsoft 365 and Microsoft Purview. Including the concepts of Customer Key and Double Key Encryption.
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfPaige Cruz
Monitoring and observability aren’t traditionally found in software curriculums and many of us cobble this knowledge together from whatever vendor or ecosystem we were first introduced to and whatever is a part of your current company’s observability stack.
While the dev and ops silo continues to crumble….many organizations still relegate monitoring & observability as the purview of ops, infra and SRE teams. This is a mistake - achieving a highly observable system requires collaboration up and down the stack.
I, a former op, would like to extend an invitation to all application developers to join the observability party will share these foundational concepts to build on:
Introducing Milvus Lite: Easy-to-Install, Easy-to-Use vector database for you...Zilliz
Join us to introduce Milvus Lite, a vector database that can run on notebooks and laptops, share the same API with Milvus, and integrate with every popular GenAI framework. This webinar is perfect for developers seeking easy-to-use, well-integrated vector databases for their GenAI apps.
Climate Impact of Software Testing at Nordic Testing DaysKari Kakkonen
My slides at Nordic Testing Days 6.6.2024
Climate impact / sustainability of software testing discussed on the talk. ICT and testing must carry their part of global responsibility to help with the climat warming. We can minimize the carbon footprint but we can also have a carbon handprint, a positive impact on the climate. Quality characteristics can be added with sustainability, and then measured continuously. Test environments can be used less, and in smaller scale and on demand. Test techniques can be used in optimizing or minimizing number of tests. Test automation can be used to speed up testing.
In his public lecture, Christian Timmerer provides insights into the fascinating history of video streaming, starting from its humble beginnings before YouTube to the groundbreaking technologies that now dominate platforms like Netflix and ORF ON. Timmerer also presents provocative contributions of his own that have significantly influenced the industry. He concludes by looking at future challenges and invites the audience to join in a discussion.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
Presentation of the OECD Artificial Intelligence Review of Germany
Rasa Open Source - What's next?
1. Rasa Open Source - What’s next?
Rasa Summit 2021
Tom Bocklisch, Director of Engineering @ Rasa
February 2021
2. Rasa Open Source
New Training Data Format
Rule Policy
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
3. YAML Training Data Format
Rasa Open Source 2.0
https://rasa.com/docs/rasa/training-data-format
4. YAML Training Data Format
Rasa Open Source 2.0
Why did we do this?
● Well-known standard
● Good editor support
● Unified extensible format
● Composable
money_transfer:
- I want to transfer money
- I want to make a transfer
Financial bot
loan_queries:
- I need a loan
- I want to take out a loan
https://rasa.com/docs/rasa/training-data-format
5. Rasa Open Source
New Training Data Format
Rule Policy
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
New Documentation
6. New Documentation including
a brand new Playground
Rasa Open Source 2.0
Why did we do this?
● Better structure
● Completeness
● No-install quick start
https://rasa.com/docs/rasa/playground
7. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
New Documentation
8. Incremental Training
Rasa Open Source 2.2
https://blog.rasa.com/rasa-new-incremental-training/
Why did we do this?
● Iterate quickly
● On-the-spot retraining
● Composability
9. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
New Documentation
Automated Testing
10. Automated Testing of Assistants
Rasa Open Source 2.2
Why did we do this?
● Ship with confidence
● Easy to set up
● Follow SE best practices
https://github.com/marketplace?query=rasahq
11. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
New Documentation
Automated Testing
12. Machine Learning Model Inspection
Rasa Open Source 2.3
Why did we do this?
● Customization
● Research
● Debuggability
https://github.com/rasahq/rasalit
14. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
New Documentation
Automated Testing
15. Where do users drop off? Why do users drop off? What can I do to fix that?
Identifying Unsuccessful Conversations at Scale
FEATURE PREVIEW
More powerful, proactive filters
(e.g. notifications to review new conversations where a
fallback action was triggered, free text search, etc.)
Incorporate emerging research (IntentTED)
(e.g. detect where an unexpected intent was expressed at a point
in the conversation)
16. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
Continuous Model
Evaluation
New Documentation
Automated Testing
17. Continuous Model Evaluation methodology for CDD
FEATURE PREVIEW
What do we want to achieve?
● The ability to compare versions of
a bot despite the fact that they
participated in different
conversations.
● Providing a quantifiable measure
of progress.
● Estimating and evaluating the
impact of a new
feature/model/model component.
Second Bot
Version
First Bot
Version
18. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
Continuous Model
Evaluation
Breaking free
from Intents
New Documentation
Automated Testing
19. Adaptive Assistants will never come if everyone
sticks with designing and implementing
hypothetical conversations, training on synthetic
data, etc.
20. To get to level 3 and beyond we have to reinvent how conversational AI works.
LEVEL 3 AND BEYOND
What you expect: What users also do:
21. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
Continuous Model
Evaluation
Breaking free
from Intents
Experimental
e2e Training
New Documentation
Automated Testing
22. Get end-to-end ready for prime time. Breaking free of intents is just the start.
FEATURE PREVIEW
All of these changes will make it easier to modify models or integrate research ideas.
We are aiming to make end-to-end
part of every assistant.
Still some heavy lifting ahead:
● Refactor Structure of
Dialogue Events
● Refactor Tracker Store
Persistence
● Refactor Agent / Processor /
Tracker Store
23. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
Continuous Model
Evaluation
Breaking free
from Intents
Experimental
e2e Training
Controllable NLG
New Documentation
Automated Testing
24. Controllable Natural Language Generation (NLG)
FEATURE PREVIEW
What do we want to achieve?
● Adapt responses to their context →
currently possible with custom logic in
an action → does not scale
● NLG model that learns from examples
but guarantees transparent control
for conversational designers and
developers (longer term)
What does this look like?
1. Mirror users word choices
● If user uses “sneakers” assistant uses “sneakers”
● If user uses “runners” assistant uses “runners”
● If user uses “kicks” assistant uses “kicks”
2. Adjusting response based on previous responses
● First time: “I’m sorry. I don’t understand. Could you
try rephrasing?”
● Second time: “I’m very sorry. I don’t quite get what
you mean. Would you like to speak to customer
service?”
● Third time: “My apologies. Let’s hand you over to a
customer service agent, ...”
25. Rasa Open Source
New Training Data Format
Rule Policy
Incremental Training
Last Major Release
2.0
Current Version
2.3
Upcoming
Releases
Machine Learning
Model Inspection
Identifying Unsuccessful
Conversations at Scale
Continuous Model
Evaluation
Breaking free
from Intents
Experimental
e2e Training
Controllable NLG
New Documentation
Automated Testing
26. Tom Bocklisch
Director of Engineering
tom@rasa.com
@tombocklisch
Excited? Help us make
these ideas become reality!
rasa.com/jobs
👩💻 👨🚀 🚀