Here are some question-and-answer sessions to highlight the different abilities of the Tellakin AI Assistant. This particular AI Assistant is deployed to be an expert in nopCommerce which is an Open-Source Project. nopCommerce has features of online shopping store and it is developed in C# and .Net.
It is powered by GPT 4 Turbo model hosted within Azure. Your company data stays within your Azure account. It uses techniques such as Retrieval Augmented Generation and Semantic/Vector Search to search and retrieve the relevant source code and documents within the context window of the GPT 4 model during the conversation.
How can Tellakin AI Assistant Help?
It described how it can help in its own words.
How can it help each Team Member?
Your Documentation Coming Alive!
AI Assistant finds the relevant sections of your documentation by searching through its Knowledge Base and then uses them to answer the questions.
General Knowledge
In this case, the knowledge was not in the knowledge base, but the AI Assistant still helped based on its general knowledge.
Code or Script Generation
Here, we are using it to generate a PowerShell script for our specific use case.
Grounding and Citations
Hallucinations are significantly reduced when the answer is based on the knowledge which exists in the Knowledge Base. It gives you citations and allows the user to inspect the cited section of the document. It helps the user in fact check and understand why the AI Assistant is saying something.
Here is one more example of cited data.
Customized Security Advice
Onboarding Assistant/Trainer
One tremendous benefit is that Tellakin AI Assistant can help with much easier and quicker onboarding for your new team members since they can ask away everything they want to know. It saves time for your other team members since they don’t have to spend as much time in training the new team member.
Here I am using it to quickly learn about a term or concept.
Helps you Plan
Writing Work Items
Write Perfect Emails
Helps You Troubleshoot
Helps You Make the Right Decision
Your Technical Expert
I am using it write SQL query for my specific need.
Here I am using it to brainstorm solutions to a technical problem.
You can use it to compare and analyze products and solutions.
It Understands Your Code!
Helps You Test
Are You Ready?
If you are ready to implement an AI Assistant which can help your team, then please contact us.
We can give you access to our Demo AI Assistant website.
We provide free consultation.
How Does It Work?
Developing an AI Assistant that works for your organization is not trivial. It requires specialized knowledge and experience with LLMs, Search Services & Indexing, Architecture, Databases, Security, etc.
If you want to get a better understanding of what Retrieval Augmented Generation and Semantic Search are and how does it relates to an AI Assistant then see our article here.
Self-Hosting an AI Assistant Solution
- Host the front-end chat UI in a web application.
- Host the back-end assistant orchestrator which brings together System Prompt, RAG and LLM functionality.
- Use a foundation LLM model or, optionally, host a fine-tuned model.
- Host a lexical and semantic search service including its indexing capabilities. Also, host a semantic vectorization model to allow semantic vectorization of chunks.
- Host a knowledge store where the documents are stored before chunking and indexing.
- Host a synchronization solution to synchronize and pre-process various data sources to the knowledge store such as for source code, SharePoint, etc.
- Host a database for storing conversation history for the users.
To keep the solution low-cost, manageable, secure, and easy to maintain, it is crucial for the organization to use serverless and managed services for the above and minimize any custom development.
Implementation Time
We have developed an AI Assistant solution based on tried and tested services and approaches. We can rapidly put together a solution within your environment that will follow best practices and will be easy to maintain, resulting in less total cost of ownership while providing you with the peace of mind of a self-hosted solution.
We can implement a working solution within a two-week time frame from start to finish. Our base package includes configuring and hosting the services described above within your Azure Subscription. It will utilize both the lexical and semantic search capabilities and will use RAG to allow AI Assistant to use your domain-specific knowledge from source code and documents. We will further optimize your System Prompt to achieve better performance.
Cost of Our AI Assistant Services
We provide free consultation to determine if our solution is suitable for your needs.
We will charge $1500 USD for the basic AI Assistant setup described above. If you need further services, maintenance, or enhancements later then we can do that at an additional cost.
What is NOT Included In Our Base Package
We have the following limitations in our base-package but we can include these services on a case-by-case basis at an additional cost.
- No live querying of the web, any database, or API is supported.
- No voice recognition or text-to-speech is supported.
- No fine-tuning or fine-tuned LLM is included. Only the foundation model is utilized as part of the base package.
- Only GPT-4 with a 128K Token context window will be utilized in our base package.
- Only text modality is supported and no image generation or analysis will be supported.
- No code interpreter/workspace will be supported.
Cost to Self-host an AI Assistant
The cost of deploying a self-hosted AI Assistant can vary depending on scalability, security, and high availability requirements. But to get started for about ~20 users, the total monthly cost is about $200 USD. It will go up from there as the number of users and consumption increases. For a large deployment, the cost can be about $500 per month. But understand that this cost is nothing compared to the amount of time it would save for each employee. While it’s possible for you to use AI Assistant as a Service companies who are external to your company, they may not offer the same level of control or customizability as a self-hosted solution.
Results and Limitations
Based on our experience, AI Assistants can boost productivity significantly, but the results will depend on your domain, quality of the documentation, and the knowledge store. One thing is sure, you can’t ignore this technology. Organizations that can harness the power of AI will have a competitive edge over their competitors.
