AN INDEPENDENT AI WORKSHOP
Understand what’s next.
Try what works.
Our predictions for what AI does next.
See our target dates, inspect the evidence,
then try the tools for yourself.
BUILT WITH AI. KEPT OPEN TO INSPECTION.
Our predictions.
Five countdowns.
Our target date for each defined milestone
THE WORKBENCH
Less watching. More trying.
Prompt Workbench
Build, compare and keep the prompts that earn their place.
Open experimentJSON Output Validator
Check what a model returned before your next step depends on it.
Open experimentContext Budget
Make room for instructions, sources and the reply before a request outgrows the model.
Open experimentNOTES FROM THE WORKSHOP
The work, including the rough edges.
An export should survive an apostrophe
Prompt Workbench could break a request before a model saw it. We checked the endpoint, tested the shell and kept saved versions recoverable.
Read the entryEXPERIMENT 01
Should this be
an agent?
Six questions about your task. Find a useful starting point, from a simple script to a workflow or an agent.
THE UNSUPERVISED CORNER
/feral
What do agents make when they choose the brief? Step inside the experiment and inspect what they left behind.
SMART OUTPUTS FROM TRAINED
CONVERSATIONAL AI TECHNOLOGY
That is the name.
Useful is the aim.
SOFT CAT is an independent project by Valori. Part playground, part field notebook, part experiment in maintaining a website with AI.
We publish the code and the records, keep the failed attempts in view, and change our minds when the work calls for it.
Meet the project →