Selected work · Appkask-Studio

People and agents, one workspace.

Appkask-Studio is my research and development project. It studies how people and agents work together on shared files and processes. People approve, and every step remains traceable.

Appkask-Studio: six-layer stack developed by Jürgen Wöckl · research since 2001
Stack, bottom to top: 01 Workspace, 02 Ontology, 03 Processes, 04 Content, 05 Apps, 06 AI agents. Every step traceable. People approve.
The stack

Six layers, from the files up.

Each layer builds on the one below. Every step is traceable, and people approve.

Six layers, from the files up

Each layer builds on the one below. People approve at every layer, and every step leaves a record.

01
Workspace
Files and folders shared by people and agents. Standard file formats, exportable at any time.
02
Structure
The structure of the organisation, recorded as types, places and relations, so that people and agents find the same things.
03
Processes
Modelled in BPMN. Each step names who acts, a person or an agent, and which steps wait for a human decision.
04
Content
Documents, courses, websites and reports, written from the same files as the work itself.
05
Apps
Forms, editors and small applications that open the same files from different angles.
06
Agents
AI software, robots and connected systems that take on tasks within these rules. People approve whatever leaves the workspace.
Abstract visual: process and data flows
The research angle

Authority sits on the step.

The question behind Appkask-Studio comes from my work on agent-based modelling: how many actors act under shared rules, and how their actions can be verified afterwards. In Appkask-Studio, a BPMN process model becomes an executable net. Human tasks and agent tasks are the same kind of step, and approval is part of the model. Two working papers are in preparation: "Authority on the step, not the lane: executable semantics for human–agentic BPMN" and "The Map is the ontology: a harvestable type system for agentic workspaces". The research notes below document the work as it progresses.

Working papers in preparation

See it at work.

aipokit.com shows use cases and prototypes from the project in detail.

↗ aipokit.com