Tessera Viz
PX-02
Life sciences
See biology as a system, not a spreadsheet.
Two of the 19 layouts exist because this work asked for them. A metabolic pathway is not a force-directed graph that happens to be biological, and a kinship tree is not a dendrogram.
01
03
Built for how research teams actually work.
01
Layouts that exist for this
Metabolic pathway and kinship tree are in the twenty because this work asked for them. So is dendrogram, for hierarchical clustering results you need to show rather than describe.
02
Protein interaction networks
Dense, undirected and large. Community detection over them, with the result driving colour and size directly rather than being written back to a server and re-fetched.
03
Clinical timelines
Events and continuous measures on the same axis, one track per subject, with aggregation from seconds to years.
04
Lineage
Kinship trees where the relationship has a direction and a generation, drawn as a tree rather than settled by a force.
05
An honest limit
Charts here are presentation, not analysis. There is no statistical modelling and no forecasting — compute the numbers, and hand us the numbers.
02
And with an agent
03
Ask in words. Get the pathway back.
01
What it changes here
A model that can already read the literature can return the pathway drawn in the idiom the field expects, so the reader checks a diagram against what they know instead of reconstructing one from prose.
02
A document, not a picture
The model returns one JSON document — the graph, the layout, the algorithm, the theme — and the library draws it in the page. Nothing renders server-side, so there is no image to regenerate when the next question changes the filter.
03
Checked before it draws
The document is validated first. A field the model invented comes back as a list of issues rather than as a blank panel or a thrown error, which is the difference between an agent that can be trusted in front of an analyst and one that cannot.
04
It can arrive as it is written
The stream reader takes the document while the model is still producing it, so a large graph starts appearing at the first complete object instead of after the last token.
05
MCP carries it; this draws it
Expose that document as the return value of an MCP tool and an agent draws straight into the conversation. The library does not implement MCP, any more than an image decoder implements HTTP — it is the renderer at the end of whichever transport you already run.
06
Why this is possible at all
Because the drawing runs in the browser and takes its instructions as data. A library that renders server-side hands an agent a picture; this one hands it a surface that the next question can change.