From Research to Context Management

Research has changed more in the last two years than it did in the previous twenty.

When we first built Collabwriting, research meant opening 27 tabs, reading everything yourself, highlighting the useful parts and sharing them with your team.

Today, AI can search, read, summarize and generate a finished document before you finish your first coffee.

So, is research management dead?

I think it just became something bigger.

The Core of Cluing Never Changed

From day one, collecting information was only half of the idea.

The other half - and the more important one - was adding your unique insight to every find.

Not only what you found, but:

➜ Why you saved it

➜ Why it matters

➜ How it connects to something else

➜ What your team should do with it

A source without that layer is just another link in a folder.

Your insight turns it into knowledge.

And now that we do more of our research with AI, that layer matters even more.

AI has Information. It needs Your Context.

Frontier models already know more facts than any of us ever will.

But they don’t automatically know:

➜ What your team already knows

➜ Which sources you trust

➜ Why you collected a specific paragraph

➜ What conclusions you reached six months ago

➜ What you’re actually trying to produce

You can give the same source to ten people and get ten different insights from it.

AI sees the source.

Context helps it see what you see.

This is why we’re moving Cluing from research management toward context management.

Collaborating with People - and AI

We originally built Cluing so people could collect findings, leave insights and reach conclusions together.

That workflow is still here.

We’re simply adding a new collaborator.

With AI Chat, you can work with leading models inside the same space where your knowledge already lives.

With MCP, you can bring your Cluing context into the AI tools where you already work.

And with Canvas, you can turn that shared context into documents, strategies and other finished outcomes.

The workflow becomes:

Find ➜ Add your insight ➜ Build shared context ➜ Collaborate with people and AI ➜ Produce something useful

Not another blank chat where you explain your company, project and thinking from scratch.

Not another AI-generated answer disconnected from its sources.

A persistent context layer that both your team and your AI can build on.

We Didn’t Move Away From Research

We followed where research was going.

The old bottleneck was finding and organizing enough information.

The new bottleneck is giving people and AI the right context to understand that information - and use it well.

Cluing started as a place where teams could explain the why behind the find.

Now, that same idea helps humans and AI think together, reach new conclusions and create better outcomes.

Research was always about more than collecting facts.

Now the tools are finally catching up. 😄