INTRODUCING ASPECT MANAGEMENT
The silo we never saw.
Content, metadata and context are stored apart, and searched apart. People joined them in their heads. AI can't, so search became a black box, and the AI took control. Aspect management adds one layer between your content and your search, so your AI finds the right document, shows why, and stays under your control.
AI-ready data isn't clean data. It's aspected data.
Available on Azure, AWS and as a sovereign deployment. Your content stays where it is.
Search changed what we expect. Our information didn't change with it.
Advanced search
Pick the repository, the type, the date range. Fill in the fields. It worked if the metadata was right and you knew which fields to use.
One search box
Type what you mean and the best result comes first. Nobody fills in fields any more.
NOW
Ask AI
A full question in plain language, and an answer instead of a list. At home it works. At work you get last year's policy, or an assistant that keeps checking.
AI understands the intent of a question. But between the question and the answer sits the search, and search keeps very little of that intent. The problem is not the AI model. It is how our information is organised.
ASPECT MANAGEMENT
The silo isn't only between systems. It sits inside every one of them.
Data
What a document says. Search finds it.
Metadata
What we know about it. Advanced search filters on it: in or out.
Context
How it connects. A graph follows it, if there is one.
Aspects
All three in one fingerprint, weighed in one search, every aspect with its own score.
Aspects are weighed, not filtered. "Latest" can matter more than "signed" for one question and less for another. And aspects are an additional index, not an additional search: a layer between your content and your search. Your search, filters and graph keep working, on top of it.
SEEING IT WORK
Ask the way you ask any AI chat. Get the precision of advanced search.
An engineer types: "Printer P7 shows error 49 after the update." Ten bulletins mention error 49. Only one is for the P7, for the firmware just installed, and released.
The question becomes aspects too. The right bulletin matches on every one; the similar one falls away on model, firmware and status. No fields to fill in, and you can see exactly why it came first.
“Printer P7 shows error 49 after the update.”
Each line is a fingerprint. The closer to the edge, the better that aspect matches.
Finding the right document is only the beginning.
01
Validation
Today you either believe an AI answer or check it yourself, so people check everything and the time AI should save is gone. With aspects, every answer comes with its evidence: which document, and why it was chosen, aspect by aspect. An answer you can validate is an answer you can trust. That is what turns an AI pilot into something people use.
02
Transparency
Retrieval stops being a black box. IT, compliance and auditors see why a document was retrieved, and can explain it afterwards.
03
Steering
For contracts, "signed" counts more than "latest". For a similar proposal, the reverse. Move a weight instead of writing another rule.
04
A feedback loop
When an expert picks the second answer over the first, the weights can follow. Capture the picks, and you capture the judgement.
05
Across repositories
A contract in your ECM, its amendment in SharePoint, the case on a file share: weighed together, without moving any of them.
And because aspects are weighed by math rather than another round of model calls, your AI needs fewer LLM calls to reach the right document.
Don’t take our word for it
“Aspected has added the context Microsoft Copilot needed. The answers are now perfectly aligned with how we organize and use our information.”
Rob Kasslack
IT Business Partner, AI & Innovation, Agfa
“Aspected includes all context directly in the search query upfront. This enables immediate governance, cuts search times in half, and delivers maximum accuracy at lower cost.”
Wim Verheij
Managing Director, Novadoc Netherlands
“The aspect model gives you, and an agent, real levers to shape relevance per query that a plain vector store simply can't.”
Andy Copland
Interim CTO, Vertex Agility (CGA Management)
“You guys are purely unique in this space… there’s your ROI, isn’t it?”
Tom Lane
Content Management Lead, Capgemini UK
THE ASPECT MANAGEMENT SYSTEM
A third layer next to the two you already have.
Collaboration management
SharePoint and similar. Where people work together.
Enterprise content management
Where workflow runs and records are stored compliantly.
Aspect management
The layer between your content and search: quality control for what your AI reads.
Management
Analyse. Classify content, build datasets, flag personal data.
Create aspects. From content, metadata and context, into one index. Your content stays where it is.
Connect. SharePoint and other sources, linked to your AI through MCP.
Maintain. Keep aspects current as content changes.
Control and governance
See why. Which aspect put an answer on top.
Set the rules. Weigh aspects, save them as policy; IT decides what gets out.
Govern access. Permissions stay hard constraints; decisions can be explained.
Keep expertise. An expert's correction can be kept for the next question.
Client demo
Mosaic
A Mosaic's pilot, told in their own words — what their assistant did before Aspected, and what changed. Recorded at the Northwest Community Health AI Summit, Portland.
Skip to 2:20 for the Aspected part →
Customer story
Agfa
Agfa uses Aspected to give field engineers more accurate answers in Microsoft Copilot. Instead of searching across manuals, instructions and tickets, engineers can ask a question and quickly get the relevant knowledge they need to work safely and solve problems faster.
WHERE TO START
Does Copilot feel slow?
It isn't slow. It is checking, and checking again, because it finds nine versions of the same document. A near-duplicate analysis of your SharePoint shows where those versions sit and which one is most likely the record. It is the lowest-hanging fruit, and the first step to aspects on your own content.
Born from 22 years of moving content.
Aspected is a spin-off of Xillio, the enterprise content migration specialist. More than 1,000 migrations taught us what happens to information when it moves, and what gets lost on the way. That experience is where aspects come from.
Xillio remains our implementation partner. When content needs to move, to SharePoint or to any other platform, Xillio migrates it, with aspects included from day one.
TALK TO US
See aspect management on your own content.
Request a demo. 30 minutes: the question, the aspects, the evidence behind every answer.
Get more information. The one-page overview and the full story, sent to your inbox.
Book a near-duplicate analysis. Start with what your SharePoint holds today.
Or write to sales@aspected.com
FOR DEVELOPERS
The engine underneath: the Aspected Database.
The Aspect Management System runs on the Aspected Database, built on our patented aspect-vector technology. Soon, developers can build directly on the aspect management layer: their own search, agents and applications on the same aspects. Join the waitlist to be among the first.
AI reads differently. AI needs aspect management.
Read "The silo we never saw" by Rikkert Engels on AIIM