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 Knowledge Retrieval becomes reliable with the Aspected Database generating the right answers.

Similarity ≠ Correctness

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

See for yourself

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

Aspected for Copilot

A production use case for the Aspected Database

Many organizations are adopting Microsoft Copilot on top of SharePoint.

In practice, retrieval quality often becomes the limiting factor:

  • Relevant documents are missed

  • Results vary depending on phrasing

  • Near-relevant information is not surfaced

  • Users retry prompts to improve answers

In many environments, improving these results requires extensive cleanup and restructuring of SharePoint before AI performs consistently.

Aspected reduces the dependency on perfectly cleaned SharePoint environments.

Aspected for Copilot places the Aspected Database between SharePoint and Copilot to improve how context is prepared and retrieved for AI systems. Instead of treating a request as a single similarity query, the Aspected Database evaluates multiple aspects simultaneously, such as:

Multiple Aspects

Meaning

Time

Priority

Intent

Context

Constraints

 

This results in:

  • More reliable Copilot answers

  • Fewer silent semantic misses

  • Lower retrieval complexity

  • Improved retrieval consistency

Already deployed in production at AGFA.

Copilot answers. SharePoint stores. Aspected for Copilot retrieves the right context.

Aspected enhancing the Sharepoint and Copilot combination

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.

Frequently Asked Questions (FAQ)

 
What problem does Aspected solve?

Aspected solves the retrieval problem in enterprise AI. Many RAG systems retrieve text that is semantically similar, but not necessarily correct for the user’s context. Aspected helps AI systems retrieve the right knowledge by combining meaning, metadata, structure, authority, and context into one retrieval process.

Who is Aspected built for?

Aspected is built for teams developing enterprise AI, RAG applications, knowledge assistants, service automation, and AI-powered search. It is especially relevant for organizations where retrieval quality, trust, context, and source correctness are business-critical.

What is the Aspected Database?

The Aspected Database is a retrieval engine for AI and RAG systems. It creates a unified representation of content and metadata, so queries can retrieve knowledge using multiple signals in one step instead of relying on separate filters and reranking layers.

How is Aspected different from a traditional vector database?

Traditional vector databases mainly rank results by semantic similarity. Aspected ranks knowledge using multiple aspects at once, including text, metadata, time, type, structure, and context. This makes retrieval more precise and reduces the need for extra filters, rerankers, or custom rules.

Why is similarity search not enough for enterprise AI?

Similarity search can find content that looks related, but enterprise AI often needs content that is correct, current, trusted, and relevant to a specific business context. In complex knowledge environments, “similar” and “right” are not always the same thing.

Does Aspected replace my existing RAG stack?

Aspected can replace parts of a traditional RAG retrieval pipeline, especially where teams currently rely on vector search plus metadata filters, rerankers, graph databases, or rules. It is designed to simplify retrieval by bringing these relevance signals together in one system.

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 Aspected 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 partners or system integrators work with Aspected?

Yes. Aspected works with AI consultancies and system integration partners that help customers implement enterprise AI retrieval solutions. Don't hesitate to contact us here.

Back to top

AI that works.

As aspected.