The main left-to-right pipeline is readable and numbered, but the diagram is information-dense with many supporting callouts (sources, extraction methods, chunking strategies, embedding models, DB options, and metadata fields), so clarity is only partial without zoom.
What was measured
Visual clarity
Are labels, arrows, and flow readable without explanation?
decisive for this rankingtransformation
If labels, arrows, and flow are hard to read, the diagram animation fails its main communication job. (3 of 3 judges)
What was given, what came back
Test input: RAG Ingestion Pipeline · text
Input — what we sent
The exact prompt
Create an animated flowchart titled "RAG Ingestion Pipeline". A Document is uploaded and its text is extracted. The extracted text is split into smaller chunks. Each chunk is converted into embeddings. The generated embeddings are stored in a Vector Database, and the metadata is stored in a Metadata Store.
A text prompt asking a tool to create an animated flowchart of a RAG ingestion pipeline: document upload, text extraction, chunking, embeddings, and parallel storage into a vector database and a metadata store. It stresses sequential pipeline animation plus a branch into two output paths.
Why this input is hard
- · Sequential process visualization
- · Parallel branching into two outputs
- · Label accuracy for pipeline stages
- · Animated flowchart generation from plain text
Output — unretouched
Also checked on this input — same tool, 1 other criterion
Provenance
- Observation
- 8f76e2d3-d820-4c51-8a13-29f0e052b5c7
- Evidence run
- e7fbb451-ba1e-4de0-ad94-41cde2700aef
- Study
- Generate Diagram Animations from Text Descriptions
- Research task
- 86b8vp172
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "academa-studio"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 9 other tools
measured on Visual clarity
AnimG◐ MixedConnector lines can partially obscure node labels; in the tested RAG flowchart, the line passes straight through the Upload text instead of staying clear of the label.Claude AI✓ WorkedKeeps the diagram readable with correctly spelled labels, a clean layout, and no text overlaps in the tested pipeline rendering.EasyMotion✓ WorkedThe generated thumbnail keeps the main stage labels readable at a glance, including Document, Extraction, Chunks, Embeddings, Vector DB, and Metadata, so the branch structure is legible without explanation.Framia✗ FailedLabel rendering is unreliable on this pipeline: the title and key node names are repeatedly garbled or misspelled, so the diagram is not readable without outside context.Kodisc⚠ StruggledLeaves overprinted labels that reduce readability: the chunking stage shows garbled duplicate text, and the embedding stage is obscured by stacked icons.Remotion AI⚠ StruggledThe Metadata Store branch is visibly de-emphasized relative to the Vector DB branch, reading as a dim afterthought rather than an equally legible output path.Replit✓ WorkedThe diagram kept labels and subtitles legible on a centered layout; the report says every node had clean descriptive subtitles, and the frame-by-frame review found no clipped text or overlapping elements.Vismo Studio✓ WorkedThe RAG flowchart keeps the stage labels readable in a compact left-to-right layout, with each node name legible without extra explanation.X-Pilot⚠ StruggledCan wrap node labels mid-word when the boxes are too narrow, splitting "Document" into "Docume"/"nt" and "Embeddings" into "Embeddin"/"gs".
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com