You need data from multiple places
Your data is not in one place and might never be. Your AI will have to consume these silo-ed data and business logic as one-off tools.
Instead, if this fragmented reality was presented to your AI application as a unified SQL tool, performance would go up 10x.
Pacha DDN instantly gives you a SQL API on top of structured, unstructured and API sources.
You need an authorization model
Current authorization approaches are untenable to securely make your data available to AI applications.
Pacha DDN provides a granular model level security mechanism on the semantic object model that sits outside of the source.
You need flexible planning and orchestration
AI changes the way we interact with our systems. We expect the flexibility of natural language upfront.
Pacha DDN has AI that can create plans to access & operate on data, interleaved with LLM generation based on 2 key ideas:
Restricted to use a standardized query language (SQL)
This creates a 10x improvement in the “reasoning ability” required for autonomous planning because query language semantics are already embedded.
Generate a python program to create multi-step orchestration plans
This creates a 10x improvement in the “correctness” of plan execution, by reducing loss of information between multiple steps and allowing for auto-correction.
You need to reduce fragility with every failure
Each “failure” of your AI application to do the right thing, should result in an action that makes the end to end system better - from user to data.
Current approaches have too many variables, and improving the system increases the overall fragility. Pacha DDN provides a query plan for every run, that helps you focus on 2 key aspects to drive improvement:
Improve the prompt given to Pacha DDN
Pacha DDN will not always be able to create the right query plans, but just like any LLM, it can easily be nudged and improved in the right direction.
Improve the data connected to Pacha DDN
Pacha DDN is able to “reason” about creating plans by leveraging the semantic documentation and the underlying data modeling (move between structured & unstructured data, use business methods for specific intents) that you do.
