Building CogniSwitch at 64 - Navigating the Generative AI landscape

For all of 2024, not a day has gone by for the Generative AI ecosystem without the breaking story of a new model or a paper outlining a new approach or startups surfacing from stealth mode with multi-digit first rounds of VC funding.  

Amidst all these uplifting stories, the results of surveys among Fortune x companies by some of the leading analysts show that less than 20% of all proof of concepts and pilots in this space has gone into production.  

The transition from Pilot To Production is mission critical for everyone in the value chain. Enterprises, Startups building GenAI products and the VCs who have taken a bet on these startups.  

While a ton of new technologies and approaches have surfaced, the mob attitude that it has to be a particular technology or a specific approach that will work is killing the collaboration and collective innovation required to move forward some of the very exciting possibilities for progress that mankind has encountered.  

A case in point is using embeddings and vector databases and a ton of variations in retrieval augmented generation (RAG) in conjunction with LLMs and hoping that hallucinations and serious reliability issues will somehow get eliminated.  

When we started working on the very first versions of CogniSwitch, much before GenAI surfaced on the radar, we had set ourselves the vision of helping organizations create digital twins of their knowledge. There is a reason for us to start thinking that knowledge accessibility would suddenly become critical for organizations to the extent that they will be concerned about creating digital twins. The reason was simple – Enterprises were becoming hybrid - teams consisting of human beings and artificial beings (AI).  

Organizations are yet to reconcile to this hybrid nature of their teams. And even if they did, it would be impossible to utilize the current proven process of on-boarding members to a team given that the process was built with humans in mind. We are convinced that organizations need to adopt newer means of doing this with AI members of your teams. And when this is not done, sh*# happens as in the case of the now (in)famous of what happened with a customer of Air Canada!  

 
Every credible organization has their product, service and process knowledge as well as policies, regulations and other SOPs documented. And this documentation is done primarily using natural language. This is the foundation on which any organization operates. And it is critical that we bring this to bear on any member in our teams, especially the hybrid ones. I have personally struggled with versions of this problems over my 40 years long technology career. Having built a code generator in early 2000s was the first step towards realizing the future of work will be hybrid.  

This is why we are building Cogniswitch - to enable this transition. CS consumes these important natural language content and gather the facts and knowledge contained within and organize in a structured knowledge base. We also built CS to be able to provide reliable information when team members seek these facts and knowledge relevant to the tasks/actions they are performing, especially the AI members in the team. CS provides both the ingestion and retrieval mechanisms using APIs so that this can happen in a seamless fashion with existing and new applications that the organization utilizes. The ingestion of your natural language sources of data, transforming it to an enabling structure and persisting it in a knowledgebase utilizes an automated, optimized and configurable pipeline. This speeds up the process of getting the critical data into a shape and form directly accessible by AI and other applications. The fact that the data comes from facts and knowledge shared by human experts and curated by them, and that the data retrieval process is based on a deterministic algorithm ensures that the retrieved data is reliable and relevant for the task at hand. Once this is set up, it becomes much easier to retrieve the relevant knowledge required to respond to a query or feed a creative Generative AI pipeline to produce a desired output.  
 

For those of you with a technical bend of mind, CogniSwitch internally utilizes a set of capable mechanisms like embedding, LLMs, NLP, ontology/taxonomy and knowledge graph logic and rules among other things in the ingestion pipeline. CS also uses natural language, knowledge graph traversal, flow and decision engines as part of the platform to ensure reliability. In the case of GenAI, the most important point to note is that while CS utilizes most of the current approaches including an external data source, the unique approach and combination of these technologies is what makes it work.  

In this case, natural language data sources and LLMs dominate the system, but utilizing the right component for the right task in the system is crucial. We chose to utilize the highly capable LLMs for their strengths in the ingestion pipeline and avoided using them in the retrieval pipeline where their weaknesses could destabilize and make most systems unreliable. In case you would like to understand more about our approach or try it out on any of your use cases, check out the rest of our website for more details.

‍