naveedahmad@redweb.com
Nov 18, 2009
  12755
(4 votes)

EpiChatty – your personal EPiServer assistant – Gadget

Hi, here is my small contribution to the Gadget competition. Meet EpiChatty, your personal assistant (chat bot) that can give you help and information about EPiServer CMS. It could serve as a help desk assistant to EPiServer CMS editors / administrators / developers / designers and to content editors.

 

The main idea behind this is to have Google Talk client embedded as a gadget on dashboard and run EPiChatty as a console application which can interact with the user and give appropriate response.

 

Google Talk implements Extensible Messaging and Presence Protocol (XMPP) protocol which essentially exchange messages using XML between clients and servers. More information about this protocol can be found here and more information about Google Talk API can be found at here 

 

As Google do not provide any C# implementation of XMPP protocol and as I am primarily a C# developer,(not brave enough to try Google’s java based implementation for this protocol), so I have to look for different options. After bit more research,  I found out that agsXMPP is an open source SDK / library for the XMPP protocol which is written in managed C# and is dedicated to .NET and Mono technologies. More information about this SDK can be found here .

 

With all my components in place, I have to learn basics about the new protocol (which I have never used before) and also use the SDK to implement it (easy).  It took a while to do a ‘hello world’ kind of code, as Google server require a different port (5222) than 80 to be open as well so that it could communicate. Once I figured that out with help from support team at agsXMPP, next thing was to implement the automated behaviour for the asked questions.

 

There are several ways that this could be implemented, but I went for the XML based approach. I have stored questions and answers in a set patterned way so that if user ask ‘what is’ or ‘how to’ or any ‘generic’ question, a patterned would be matched and answer would be returned. The main reason behind this approach was its simplicity and extendibility.

 

Here is the screen shot how the EPiChatty gadget will look like on dashboard

epichatty_not_signed_in

The gadget view contains embedded Google Talk client and the controller simply returns the view.  The login it will redirect to central Google account services where you could login and then it will return you back to the dashboard.

epichatty_logged_in

 

once login you can ask ‘what is’ or ‘how to’ or ‘generic’ questions

epichatty_logged_in2

 

Here is the screen shot of the console application showing that EPiChatty is available to chat

epichatty_console

 

I have made the EPiChatty as a console application so that it could run separately from the main application as a light weight process in background. In case you want to start chatting and test it out, send an invite to epichatty@googlemail.com . I will be hosting it till the end of December 2009 and then EPiChatty will be on long vacations.

 

Source files contain every thing apart from the password for the EPiChatty Google’s account. If you would like to host your own, you can create a new Google account and replace the username and password in console application and run the console application.

Source

Nov 18, 2009

Comments

Please login to comment.
Latest blogs
Optimizely Opal: How to Build Effective Workflow Agents

If you're building workflow agents in Optimizely Opal, this post covers how specialized agents pass context to each other, why keeping agents small...

Andre | May 20, 2026

ReviewPR: An Azure Function That Reviews Your Azure DevOps Pull Requests With Claude

A while back I wrote about an  Azure Function App for PDF creation that we use to offload PDF rendering from our Optimizely DXP site. That same...

KennyG | May 19, 2026

Accelerating Optimizely CMS and Commerce upgrades with agentic AI (Part 2 of 2)

The Real Transformation in Optimizely CMS 13: Why the Upgrade Itself Is the Easy Part. A field-tested playbook for enterprise teams moving from...

Hung Le Hoang | May 18, 2026

Is the most powerful AI model really the best value?

Artificial Intelligence is already becoming part of everyday software development. Developers now use AI tools to generate code, write documentatio...

K Khan | May 16, 2026