Splotch

For the past year, we've been working to crack a really hard problem: turn any process described in text into a diagram that is *accurate* and *editable.* Today we're launching a new build embedded in a free web tool that we think achieves this bar! PLEASE LET US KNOW WHAT FEATURES / IMPROVEMENTS YOU NEED TO MAKE IT USEFUL FOR YOU. (We're offering a month free to anyone who gives us detailed feedback on what they need for their real world use cases - send to josh@splotch.ink) Okay, what can Splotch do? 1. Detect processes described in text. Not everything needs to be diagrammed. What’s the “skeleton” of the plan or process? 2. Auto-generate a diagram that’s close to the text description. Represent the core components as nodes, and link each node to its corresponding source text. 3. Keep the source text and diagram in sync. Most diagrams go “stale” quickly. “Live” diagrams stay current by linking each node to a snippet of text in a source doc. (Surprisingly, this didn’t exist until now!) 4. Edit, iterate and develop the diagram. Assume the process will evolve. Every change to one side (text or diagram) should cause a corresponding change on the other side. WHERE ARE WE HEADED? When we’re working with processes, we still live in our great-grandparents’ world: “Take twenty steps past the big oak tree, then turn right.” Most of us write them out. That’s because, like maps back then, diagrams are difficult to make, update and explain. But we still use diagrams to show important processes because–unlike a text summary (especially LLM-generated summaries)--a diagram makes it easy to see the relationship between the steps. Human memory and sense-making is visual and sequential. Stories and maps are sticky because they put information in context. AI needs context windows. Humans need context maps: diagrams! We're going to continue embedding more context into diagrams so they become the primary language for navigating how your company works--just like Github did for code.