VDF is spatial reasoning. It keeps thinking with AI inspectable, connected, and attached to what you mean. You talk. Spaces take shape.
AI conversation does not have to stay linear. VDF gives loose thinking a place to form and keeps the path visible before anything becomes output.
Before deliverables, VDF gives loose thoughts enough structure to hold.
The path stays visible as the thought holds, strains, branches, or recovers.
VDF forms working readings of clarity, density, and restraint from inputs to make posture legible.
Thinking becomes visible in parallel surfaces instead of blending into one long chat.
When the structure is ready, it becomes a usable surface with the original point still visible.
It starts with a loose thought. Take the turn to watch thinking take shape, then hover or click the glowing moments to see whether the answer is still attached to the idea from the starting point.
“I want to help families preserve recipes, but every AI answer turns it into a startup.”
Illustrative spatial sequence. The example inputs and responses are predefined.
The interactive compass is not running in this viewer. Open the full page in a browser with JavaScript enabled to try this example.
Chat makes thinking with AI look linear. But the working structure can branch, drift, recover, and form underneath. VDF makes those relationships visible enough to inspect and steer inside the same conversation.
The interface shows a list of turns, even when structure is already branching underneath.
VDF treats the turn as a shape: origin, path, pull, strain, and recovery.
Preserve stories, substitutions, voices, and rituals around recipes.
The tree doesn’t appear all at once. It takes shape as the conversation develops. In the Room, VDF keeps a provisional Reading beside the conversation so you can inspect what is forming, respond to it, and keep the work open before anchoring a direction.
The interactive example is not running in this viewer. Open the page in a browser with JavaScript enabled to use Send reply and the other controls.
“I want to help families preserve recipes, but every AI answer turns it into a startup.”
Leave the startup frame aside. What matters most about preserving the recipes?
The stories and voices matter more than organizing the ingredients.
Then let’s keep the stories and voices in view. We do not need to choose a product format yet; first we can clarify what you want to preserve.
Yes. I’m still thinking about how to begin.
We can leave the starting point open. Nothing new here changes the Reading yet; how to begin is still yours to work out.
Let’s start with one recipe and the story of the person who made it.
One person’s recipe story gives us a small starting point. That gives the work a direction without deciding what form it needs to become.
Is this about preserving family memory rather than building a recipe business?
The family purpose may be getting lost when the idea is framed as a startup.
What should be preserved is still open. A product plan need not be the next move.
What matters about the recipes has not yet been made specific.
Available when the example reaches a proposed direction.
Send replies to see the Reading change. Inspect earlier Readings at any time.
Illustrative Room sequence. The inputs and Readings are predefined.
Ground, Trail, and Surfaces are not separate apps. They are different perspectives on the same underlying structure. The data does not move. Your perspective does.
Choose a card to see how the same recipe idea moves from uncommitted thought, to visible path, to usable surface.
VDF reads turns before output forms. It uses working estimates of clarity, density, restraint, and motion to help determine when to ask, hold, park, or proceed. Some checks run in application code without calling a model. When VDF does call one, the call is made within the current frame.
VDF's coherence work includes PCP, the Portable Coherence Protocol, a separate instrument for packaging selected context for continuation. It carries what is true now, what changed, what must remain, and what comes next as an explicit handoff rather than relying on the transcript alone.
It lives in the transcript, and the transcript does not travel. The next session gets re-explained, and re-explaining drifts.
In plain language, held for the next session.
Selected state is available before the first turn.
Purpose research asks how human intent can remain coherent when AI systems are fluent but not yet grounded. VDF carries that question into visible interfaces and instruments that can be inspected.
Developed an external posture-control overlay for conversational coherence.
Read the researchExplored systems modeling and simulation for intent-driven interaction.
See the modelApplied Purpose-informed distinctions in a live organization setting.
View findingsVDF is explored through live surfaces: raw context, guided structure, and the visible artifacts and systems that emerge from the work. Four domains, one method: a scent house, a product surface, a bookkeeping service, a tax workflow. The distance between them is deliberate. The rhythm that produced them is the same.
Raw context about scent, memory, and laundry as ritual became a live brand system exploration.
View exploration →Raw product thinking became a navigable project surface for innovation-based project management.
View exploration →A Jackson Hewitt Bookkeeping service frame became a clear landing surface for small-business clients.
View exploration →A Jackson Hewitt tax recovery workflow became a clearer client surface for checking missed refund opportunities.
View exploration →VDF gives AI-mediated thinking a visible structure people can see, adjust, and inspect, so ideas, artifacts, research, and decisions stay connected to their sources, relationships, and history as they evolve.
Research Lab