Implementation Workspace
Video transcript
00:08 — The review sits on the product
Most design reviews happen in a meeting room, with a printed schematic and whatever the reviewers remember of the requirements. In Creopus, the review sits on the board’s own place in the product, beside its requirements and its DFMEA. You upload the whole KiCad project, exactly as your team keeps it. The worker runs KiCad itself: its electrical and design rule checks, the netlist, and a 3D model of the board.
00:39 — Rules first, then judgement
Then the platform’s own checks run: rules that either fire or they don’t, and the patterns experienced engineers look for by habit. Only then does the AI review run, grounded in this board’s requirements and its DFMEA. Each finding names the check that raised it, and the requirement or DFMEA row it concerns. Here, the boost converter draws its power through the 5 volt regulator: the very load the DFMEA warns could overheat it. And a finding is settled like a review comment: accepted, rejected or deferred, with the reason, the name and the date kept on record.
01:23 — Findings, on the board
Open the board, and the findings are drawn where they are, beside the parts they name. Zoom in, and each marker shows the finding it stands for. And KiCad’s own 3D model of the board is a click away.
01:44 — Heat, against the requirement
Next, the heat. For each part that warms the board, declare the power it dissipates, and a junction to board resistance where the datasheet gives one, and the worker models the board in Elmer, a finite element solver. Back comes the temperature under every loaded part, and the heat map lies over the board layers. Bind the run to the board’s temperature requirement, and it becomes evidence: within its limit.
02:18 — The enclosure
Then the enclosure. Upload its STEP model, and the worker measures it and checks the board’s mounting holes against it. One hole is a millimetre out, and the finding names both holes it could be, before a single part is made.
02:37 — Signed off, with the evidence
Back at the requirements, the temperature limit now reads checked, for the four parts that carry heat, and it waits for a person to sign it off. Accept it, and it counts as verified, with the engineer’s name and the date on record. And the whole review exports as a controlled document. A design review in minutes, with the evidence attached.
Upload your implementation; get grounded, structured findings.
What it's for
Unlike the generative tools, this tool reviews uploaded implementation artifacts — schematic netlists, SPICE simulation decks, and PCB layouts — through a three-layer pipeline: deterministic rules (L1) → curated patterns (L2) → a grounded LLM review (L3) using the node’s requirements, DFMEA, block diagram, and BOM. It returns findings grouped by severity and filterable by discipline (EE/LE/ME) and analysis layer (L1/L2/L3), with each finding supporting disposition and discussion.
When to use it
During implementation to identify design and implementation issues before fabrication, hardware bring-up, or testing.
How it works
-
Create an implementation workspace. → Select a system from the optional System Hierarchy, describe what you are implementing in the workspace input field, and click “Create workspace” to create the implementation workspace.
▶ Create an implementation workspace▼ Create an implementation workspace
-
Upload implementation artifacts. → Upload a schematic, SPICE simulation deck, or KiCad PCB/Gerber package for automated checks and AI-assisted review. Each artifact can include an optional title and source filename.
▶ Upload files▼ Upload files
-
Run an AI follow-on review. → Select a predefined review directive — “Re-review with EMC focus,” “Thermal deep-dive,” “Re-grade as safety-critical (Class C / DO-178C),” “Re-grade for medical (IEC 60601-1),” “Suppress findings — intentional design choice,” “Deep-dive on the highest-severity finding,” “Find requirement-coverage gaps,” or “Trace DFMEA mitigations” — or enter a custom directive to re-run the AI review with a focused analysis. The follow-on review requires a schematic and hierarchy node, preserves existing findings, and applies the directive context to new findings.
▶ Run an AI follow-on review▼ Run an AI follow-on review
-
Review the findings and add comments. → Review the findings generated from the uploaded implementation data. Use the finding filters to view “All”, “EE”, “LE”, or “ME” findings and the analysis-layer filters to view “All layers”, “L1”, “L2”, or “L3”. Each finding includes the finding ID, severity, review layer, finding category, linked sub-artifact, affected item or component, status, issue description, recommended action, disposition, reason, and discussion. Use the comment field to add a discussion or reply to an existing comment, then click “Post” to submit it. Use the delete icon to remove an existing comment.
▶ Review the findings and add comments▼ Review the findings and add comments
-
Add a finding. → Click “Add finding” to manually add a finding that the AI may have missed, such as visual issues, supplier constraints, or project-specific concerns. Manual findings can use the same severity and disposition flow as AI-generated findings.
▶ Add a finding▼ Add a finding
-
Set the finding disposition. → Click “Disposition” and select one of the available options: “Accept — act on this finding”, “Reject — false positive or intentional”, “Defer — fix later”, “Note — acknowledged, no action”, or “Re-open”.
▶ Set the finding disposition▼ Set the finding disposition
-
Edit a finding. → Click the Edit button for a finding to open the “Edit finding” form, where you can modify the Severity, Discipline, Category, Location, Message, and Recommendation. Click “Save changes” to apply the updates or “Cancel” to discard them.
▶ Edit a finding▼ Edit a finding
Mechanics
- Three-layer review: L1 deterministic rules → L2 patterns → L3 grounded LLM
- Findings grouped by severity · discipline (EE/LE/ME) · layer (L1/L2/L3)
- Upload and review: schematic · SPICE simulation deck · KiCad PCB · Gerber zip
- Per-finding disposition: Accept · Reject · Defer · Note · Re-open
- Per-finding edit with Severity · Discipline · Category · Location · Message · Recommendation
- Comment threads with Reply · Post · Delete
- Add manual findings with the same severity and disposition controls
- AI follow-on review with focused directives
- Sub-artifact revisions · Compare · Document Info