Tracking How Your Research Evolves: History in Sombra

We're going to dive into a feature on Sombra that I think is quietly one of its most important — tracking the history of your web scrapes, notes, and distilled context as your collections evolve over time.

The final output looks like this, for those of you who want to skip ahead, a live synced public link: Somatic Mosaicism & Clonal Evolution

Sharing can also be a snapshot of a specific point in time - you can choose when you create a public link. Collections are always private without this.

Still here? Let's see where that came from... 🦉

It started with a question from a 10-year-old

I'd started a chat with Claude, prompted by a question from my son. He wanted to know about life that doesn't originate from a seed. Kids ask amazing questions - the kind that send you tumbling down rabbit holes you'd never find on your own.

Talking with AIs reminds me of the old Wikipedia deep-dives. You start with one question and twenty minutes later you're in a completely different universe. This was no exception.

I know less than nothing about biology, and Claude was understandably already slapping my wrists about some of my assumptions - but that's to be expected. I was curious, and curiosity doesn't require credentials.

Down the rabbit hole: Pando

Claude pointed me at something entirely new to me. I'd never heard of Pando before - a single clonal organism of quaking aspen in Utah, estimated to be thousands of years old. What looks like a forest of individual trees is actually one genetically near-identical organism connected by a shared root system. Truly astonishing.

For those of you who are seasoned Wikipedia delvers, this is all familiar territory - you start digging into a topic and suddenly you're learning about somatic mosaicism, clonal hematopoiesis, and how mutation rates scale with lifespan across mammals.

Engage superpowers: I had Sombra connected

While I was going down this rabbit hole, Sombra was right there with me. I was saving pages, adding notes, and building up a collection as I went - turning a random, wandering exploration into something structured and reusable.

At this point, my random exploration was concrete. I had a collection with links, content, and notes, plus a cheatsheet tying it all together.

Distilling the context

I wanted this collection to be more than just a pile of bookmarks and snippets. So I asked Claude - via a specialised prompt from Sombra - to distill everything into a coherent context and save it back to the collection.

The cover context you saw on the link above was distilled and added to the collection, along with the sources and notes contributing to it. From here, when I come back to this in the future, I can look briefly at the distillation, or look at the saved scrapes, and get my brain back into the same place it was when we created the collection.

Notes, sources, and context all in one place. And synced to my Dropbox and Google Drive.

Switching AIs, same collection

Later, I wanted a more focused context specifically about Pando. ChatGPT also has access to the same collection via Sombra's MCP integration, and it updated the context for me. I didn't need to get it up to speed - it just read the same docs and sources we had already saved.

This is the part that I think matters most in practice. Your research isn't locked into whichever AI you happened to be using when you did the work. The collection is the source of truth, not the chat.

History: seeing what changed

Directly in the UI, I can see exactly what changed by clicking on the history icon. Every save — whether it's a web scrape, a note, or a distilled context update — is versioned and saved.

AIs can go off on tangents. Being able to trust them to write and update data for you without a safety net is a big ask. The history feature, across all save types, gives you the confidence to let AIs update your collections freely, knowing you can always see how your research has evolved and go back to what was there before.

It's a simple idea: version everything, show the diffs, let you roll back. But when you're building a research workflow where multiple AIs are reading and writing to the same knowledge base, it becomes essential.

How would you use this?

I'd love to hear how you'd put this to work. Research projects? Competitive analysis? Learning journals? The combination of structured collections, AI-powered distillation, and full history tracking opens up some interesting workflows.

Thanks for reading, and happy research! 📚