Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
1
2
Power your Dynamics 365
with bots
Joris Poelmans
@jopxtwits
November 17th 2018
3
About me
• Solution architect
• Work at Realdolmen
• Blog: http://jopx.blogspot.com
• Twitter: @jopxtwits
• Board member...
4
Agenda
5
What is a (chat)bot and why should I care?
6
Use cases
7
Value proposition
Improve your image
Differentiating factor
Ambassador for innovation
Reduce costs
24/7 service
Automate...
8
Bot communication
API
9
How bots evolved
Simple
• One medium
• Keyword based
Moderate
• Multiple mediums
• Use custom messaging
• Keyword based
...
10
Channel connector frameworks
Google Dialogflow (API.AI) Microsoft Bot Framework
11
Types of bot interactions
12
QnA Maker
• Data - Aggregate and extract
knowledge from non
structured data
• Low code way for setting up a
FAQ style b...
13
Demo – QnA Maker sample bot
14
Microsoft Bot
Framework
• SDK for building bots
• V3 - C#, Javascript
• V4 – C#, Javascript, Python & Java
• Multiple c...
15
16
Microsoft Bot Framework – Important concepts
17
Microsoft Bot Framework - Activities
public async Task<HttpResponseMessage> Post([FromBody]Activity activity)
{
if (act...
18
Microsoft Bot Framework - Dialogs
19
Microsoft Bot Framework
Attachments, cards and actions
20
Microsoft Bot Framework – FormFlow
Jane user John bot
21
Microsoft Bot Framework – FormFlow
Jane user John bot
22
Microsoft Bot Framework – FormFlow
Jane user John bot
23
FormFlow
24
Demo – Customer Service Bot
25
Bot Builder SDK v4 – What’s changed
26
SDK Extensibility through Middleware
Adding Telemetry (App Insights) middleware Standard Middleware Calling Pattern
Mid...
27
Author Dialogs
Design Cards
Visualize
Bot Builder SDK
Cognitive Services
Getting Started
Templates
Emulator​
Applicatio...
28
New templates and solutions
 New series of templates and
solutions to enable more complex
scenarios
 Based on best pr...
29
Demo – Enterprise template (v4)
30
Omnichannel
Customer Service
Architecture
… and where do bots fit?
31
Challenges
32
Improve agent productivity and customer experience
Web Mobile
Social
Store Phone / Chat
Video Chat
Co-browse Secure Doc...
33
Customer/Agent
Effort, FCR, AHT, SLAs
Intelligence
Predictive, proactive, personalized and insightful service
Customer ...
34
AI
Capabilities
Bot Features:
Personality
Dialogs
Language Model
Knowledge
Sources
Manuals
(PDF)
Data Sources
General
K...
35
36
37
38
39
40
QUIT TALKING AND BEGIN DOING.”
“THE WAY TO GET STARTED IS TO
Walt Disney
41
Specifications Architecture
Build
UI Testing
(Bot) Training
Improve
Pilot
Launch
Monitor
Workshop themes
and personas
W...
42
References
https://docs.microsoft.com/en-us/azure/bot-service/?view=azure-bot-service-4.0
https://www.qnamaker.ai/
http...
Upcoming SlideShare
Loading in …5
×

Dynamics 365 Saturday Brussels 11/2018 - Dynamics 365 and chatbots

720 views

Published on

Bots represent a new channel for businesses to expose their products & services via messaging platforms. In this session we will explore how Azure Bot Framework, Azure Cognitive Services can be integrated with Dynamics 365 for Customer Engagement and Customer Service. Updated with info about Azure Bot Framework v4.0

Published in: Technology

Dynamics 365 Saturday Brussels 11/2018 - Dynamics 365 and chatbots

  1. 1. 1
  2. 2. 2 Power your Dynamics 365 with bots Joris Poelmans @jopxtwits November 17th 2018
  3. 3. 3 About me • Solution architect • Work at Realdolmen • Blog: http://jopx.blogspot.com • Twitter: @jopxtwits • Board member Belux CRM User Group https://crmug-belux.eu
  4. 4. 4 Agenda
  5. 5. 5 What is a (chat)bot and why should I care?
  6. 6. 6 Use cases
  7. 7. 7 Value proposition Improve your image Differentiating factor Ambassador for innovation Reduce costs 24/7 service Automate tasks Filter incoming requests Increase client engagement Improve customer experience Flexible & guided user journeys Understand client language (NLP) Extend client reach New channels: Facebook messenger, Slack, Skype, Teams, …
  8. 8. 8 Bot communication API
  9. 9. 9 How bots evolved Simple • One medium • Keyword based Moderate • Multiple mediums • Use custom messaging • Keyword based Advanced • Multiple mediums • Use custom messaging • Understands natural language
  10. 10. 10 Channel connector frameworks Google Dialogflow (API.AI) Microsoft Bot Framework
  11. 11. 11 Types of bot interactions
  12. 12. 12 QnA Maker • Data - Aggregate and extract knowledge from non structured data • Low code way for setting up a FAQ style bot • Architecture. The data and runtime hosted in your Azure subscription. • More control
  13. 13. 13 Demo – QnA Maker sample bot
  14. 14. 14 Microsoft Bot Framework • SDK for building bots • V3 - C#, Javascript • V4 – C#, Javascript, Python & Java • Multiple channels • Rich conversations with dialogs and cards • Open source project 10+ public repos • Natural Language Processing – QnA or LUIS.AI
  15. 15. 15
  16. 16. 16 Microsoft Bot Framework – Important concepts
  17. 17. 17 Microsoft Bot Framework - Activities public async Task<HttpResponseMessage> Post([FromBody]Activity activity) { if (activity.Type == ActivityTypes.Message) { var connector = new ConnectorClient(new Uri(activity.ServiceUrl)); Activity reply = activity.CreateReply($"You sent {activity.Text} which was {activity.Text.Length.ToString()} characters"); await connector.Conversations.ReplyToActivityAsync(reply); } var response = Request.CreateResponse(HttpStatusCode.OK); return response; }
  18. 18. 18 Microsoft Bot Framework - Dialogs
  19. 19. 19 Microsoft Bot Framework Attachments, cards and actions
  20. 20. 20 Microsoft Bot Framework – FormFlow Jane user John bot
  21. 21. 21 Microsoft Bot Framework – FormFlow Jane user John bot
  22. 22. 22 Microsoft Bot Framework – FormFlow Jane user John bot
  23. 23. 23 FormFlow
  24. 24. 24 Demo – Customer Service Bot
  25. 25. 25 Bot Builder SDK v4 – What’s changed
  26. 26. 26 SDK Extensibility through Middleware Adding Telemetry (App Insights) middleware Standard Middleware Calling Pattern Middleware 1 // logic Next(); //more logic Middleware 2 // logic //more logic Request Response Find this sample on https://github.com/Microsoft/BotBuilder-Samples And https://github.com/BotBuilderCommunity
  27. 27. 27 Author Dialogs Design Cards Visualize Bot Builder SDK Cognitive Services Getting Started Templates Emulator​ Application Insights Conversation Transcripts DevOps Tools Azure BYO Web Host WebChat Cortana Skype, FB + Custom (DirectLine) Application Insights LUIS Suggestions Plan Build Test Publish Connect Evaluate Better support for the whole project lifecycle
  28. 28. 28 New templates and solutions  New series of templates and solutions to enable more complex scenarios  Based on best practices and supporting components from first wave of Conversational Experiences  Templates  Basic & Enterprise  Solutions  Virtual assistant (private preview)  Customer support (coming soon)
  29. 29. 29 Demo – Enterprise template (v4)
  30. 30. 30 Omnichannel Customer Service Architecture … and where do bots fit?
  31. 31. 31 Challenges
  32. 32. 32 Improve agent productivity and customer experience Web Mobile Social Store Phone / Chat Video Chat Co-browse Secure Docs Secure Messaging 2-way Text Channels/Touch Points Live Engagement Modes Customer Agent CRM Social Media Monitoring Technicians Consumer Loans Eligibility Customer Insights Order Management Offer Management Credit Check Premiums Resources … Bots Supervisor Agent Assist - Bot
  33. 33. 33 Customer/Agent Effort, FCR, AHT, SLAs Intelligence Predictive, proactive, personalized and insightful service Customer Segments: Channel Transition Channel Mix, Next Best Channel Knowledge Suggestions Sentiment Analysis Expert recommendation Service Bots OperationalProactive/Predictive Case Management Business Process Voice of the Customer Entitlements, SLAs, and Escalations Field Service Knowledge Management Omni- Channel Interactions Optimized Resource Scheduling Sentiment Analysis Next Best Action Channel Guidance Cross Channel Correlation Customer Effort Automatic Case Escalation Knowledge Suggestions Intelligent RoutingExpert Recommendation Next Issue Avoidance Cognitive Services Azure Machine Learning Bot Framework Cortana Analytics Suite Work Order Management Contract Management Schedule & Dispatch Inventory Management Van Stock Mobile
  34. 34. 34 AI Capabilities Bot Features: Personality Dialogs Language Model Knowledge Sources Manuals (PDF) Data Sources General Knowledge Conversational AI Azure Bot Service + Cognitive Services LOB Apps Enterprise stores Language Understanding Speech Vision QnA Type Speak Tap User Input Devices Channels Azure Bot Services Adaptive Cards
  35. 35. 35
  36. 36. 36
  37. 37. 37
  38. 38. 38
  39. 39. 39
  40. 40. 40 QUIT TALKING AND BEGIN DOING.” “THE WAY TO GET STARTED IS TO Walt Disney
  41. 41. 41 Specifications Architecture Build UI Testing (Bot) Training Improve Pilot Launch Monitor Workshop themes and personas Workshop(s) conversations and UX 2 1 Workshop architecture and interfaces 3 Start your bot journey Contact joris.poelmans@realdolmen.com or dirk.gepts@gfi.be
  42. 42. 42 References https://docs.microsoft.com/en-us/azure/bot-service/?view=azure-bot-service-4.0 https://www.qnamaker.ai/ https://www.luis.ai https://blog.botframework.com/ https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-virtual-assistant-introduction https://blogs.msdn.microsoft.com/geoffreyinnis/2018/08/30/phone-call-transcription-and-insights-with- video-indexer-and-dynamics-365-part-2/ https://github.com/Microsoft/botbuilder-dotnet • https://github.com/BotBuilderCommunity http://jopx.blogspot.com

×