AI that works.

As aspected.

Aspected combines semantic text and structured metadata into one query, allowing you to search everything in a single, unified vector space. Enterprise AI Retrieval becomes reliable with the Aspected Database generating the right answers.

Similarity ≠ Correctness

Vector Databases retrieve similar text. Enterprise AI needs the right knowledge.

Demo

Select one of the questions on the bottom left and compare the results. The correct answer delivered by Aspected.

Why the RAG Stack is getting more complex

Because you are adding layers, context is added after retrieval
As similarity search lacks context, teams keep adding layers on top of their vector databases. This increases complexity, reduces reliability and still not providing the correct answers.

Vector Database

Embedding - text only

Ranking signal - semantic similarity

Metadata - filtered after retrieval

Authority - ignored

Structure - ingnored

Result - similar documents

Extra Layers

+ metadata filters

+ rerankers

+ graph DB

+ rules

 

 

The Aspected Database

We are fixing retrieval at the source and provide it as ONE system.

Instead of asking: "What text looks similar?"

We ask: "What knowledge is correct in this context?"

Simple, reliable and correct!

Aspected

Embedding - text + metadata + context

Ranking signal - multi-aspect relevance

Metadata - part of ranking at index time

Authority - first-class-dimensions

Structure - native to index

Result - correct information

 

Aspected diagram

Frequently Asked Questions (FAQ)

 
What is the history of the company Aspected?

Aspected is a Spin-off from Xillio - a global enterprise data transformation company.

Over two decades, Xillio worked inside some of the world’s most complex enterprise knowledge environments — building software to transform and migrate large-scale content systems. This experience led directly to the creation of Aspected.

We invented the Aspect Database, a retrieval engine for AI systems that enables organizations to access the right knowledge from complex enterprise data. By combining semantic understanding with operational context such as metadata and system signals, Aspected helps AI assistants retrieve relevant information instead of just similar text. This makes enterprise AI more reliable and useful in real-world operations

Can I use the Aspected Database in my own environment?

Yes you can, don't hesitate to contact us for a call to explain how.

Can I use the Aspected Database and test it separately on my own?
Yes you can, don't hesitate to contact us for a call to explain how.
Can I use the full Aspected stack and test it?
Yes you can, don't hesitate to contact us for a call to explain how.
We are a IT system integrator / consultancy firm focused on AI, can we become a partner of Aspected?

Yes, you can, we very much value additional in many cases local, expertise on top of our products. Don't hesitate to contact us here.

Back to top

Organisations that deploy Aspected already today

Aspected Partners adding value to our AI retrieval solution

Partners

Aspected works with different local and global AI consultancy and system integration partners. Such as Novadoc and Capgemini.

AI that works.

As aspected.