|
| 1 | +--- |
| 2 | +layout: pw45-project |
| 3 | + |
| 4 | +permalink: /:path/ |
| 5 | + |
| 6 | +project_title: Interactive Workflow Replay and Step-Back Navigation for Slicer Agent |
| 7 | +category: Infrastructure |
| 8 | +presenter_location: |
| 9 | + |
| 10 | +key_investigators: |
| 11 | + |
| 12 | +- name: Puxun Tu |
| 13 | + affiliation: Brigham and Women's Hospital |
| 14 | + country: USA |
| 15 | + |
| 16 | +- name: Ron Kikinis |
| 17 | + affiliation: Brigham and Women's Hospital |
| 18 | + country: USA |
| 19 | + |
| 20 | +- name: Steve Pieper |
| 21 | + affiliation: Isomics |
| 22 | + country: USA |
| 23 | + |
| 24 | +- name: Sanghyuk Kim |
| 25 | + affiliation: Mass General Brigham & University of Massachusetts |
| 26 | + country: USA |
| 27 | + |
| 28 | +--- |
| 29 | + |
| 30 | +# Project Description |
| 31 | + |
| 32 | +<!-- Add a short paragraph describing the project. --> |
| 33 | + |
| 34 | + |
| 35 | +The Slicer AI Agent is a scripted extension that lets users use natural-language instructions and have the system autonomously generate, validate, and execute Python code within the 3D Slicer scene. For complex multi-step operations, such as extension-specific surgical planning workflows, the agent enters a deterministic workflow runtime that executes a sequence of predefined steps (automated code execution, interactive 3D mark-up placement, user choices, and branching logic) with a progress bar tracking completion. |
| 36 | + |
| 37 | +Currently this progress bar is forward-only: once a step completes, there is no way to go back, inspect what happened at an earlier step, or modify a previous choice and re-run the downstream pipeline. This limits both transparency (users cannot easily understand what was done and why) and usability (a wrong choice means restarting the entire workflow from scratch). |
| 38 | + |
| 39 | +We propose adding a workflow replay timeline that records per-step state and allows users to go back to any completed step, inspect the code and choices that were made, optionally modify parameters, and re-execute the workflow from that point onward. |
| 40 | + |
| 41 | + |
| 42 | + |
| 43 | + |
| 44 | +## Objective |
| 45 | + |
| 46 | +<!-- Describe here WHAT you would like to achieve (what you will have as end result). --> |
| 47 | + |
| 48 | + |
| 49 | +We aim to add a workflow replay and step-back navigation capability to the Slicer AI Agent's workflow runtime. By recording per-step state and exposing it through an interactive timeline, users will be able to scrub back to any completed step, inspect what happened, optionally modify a prior choice, and re-run the remaining pipeline — improving both process transparency and the ability to correct mistakes without restarting the workflow from scratch. |
| 50 | + |
| 51 | + |
| 52 | + |
| 53 | +## Approach and Plan |
| 54 | + |
| 55 | +<!-- Describe here HOW you would like to achieve the objectives stated above. --> |
| 56 | + |
| 57 | + |
| 58 | +- Step-level recording: Capture a full replay log for every workflow step, including the generated code, user choices, scene snapshots (before/after), and execution results, so that the complete history of a workflow run is persisted and inspectable. |
| 59 | + |
| 60 | +- Timeline UI with scrubbing: Replace the current linear progress bar with an interactive timeline widget that shows step markers (completed / current / pending), allows dragging to any completed step, and displays a detail panel with the code, choices, and scene diff for that step. |
| 61 | + |
| 62 | +- Step-back re-execution: Enable the user to jump back to a completed step, optionally modify a prior choice or parameter, and re-run the remaining workflow from that point, reusing the existing template-dispatch and auto-advance infrastructure. |
| 63 | + |
| 64 | + |
| 65 | + |
| 66 | +## Progress and Next Steps |
| 67 | + |
| 68 | +<!-- Update this section as you make progress, describing of what you have ACTUALLY DONE. |
| 69 | + If there are specific steps that you could not complete then you can describe them here, too. --> |
| 70 | + |
| 71 | + |
| 72 | +TBD |
| 73 | + |
| 74 | + |
| 75 | + |
| 76 | +# Illustrations |
| 77 | + |
| 78 | +<!-- Add pictures and links to videos that demonstrate what has been accomplished. --> |
| 79 | + |
| 80 | + |
| 81 | +https://github.com/user-attachments/assets/5eb1dab5-9b35-4d5e-9d96-c0cc058e951f |
| 82 | + |
| 83 | +https://github.com/user-attachments/assets/ea27d290-b2c5-4be0-9954-8051650bda90 |
| 84 | + |
| 85 | + |
| 86 | + |
| 87 | +# Background and References |
| 88 | + |
| 89 | +<!-- If you developed any software, include link to the source code repository. |
| 90 | + If possible, also add links to sample data, and to any relevant publications. --> |
| 91 | + |
| 92 | + |
| 93 | +Slicer AI Agent source repository: https://github.com/puxuntu/Slicer_agent |
| 94 | + |
0 commit comments