Ingestion Standards · Public summary
What a case has to clear before it gets in.
This is the real bar goodcase.ai applies when deciding whether a case gets published — not a mission statement. Every line here maps to a gate that actually runs in the pipeline. If we rejected your submission, this is why.
Missing any one, and it never reaches review
Author, prompt, timestamp, heat — all four, or it doesn't queue.
Author
No byline, no accountability, and no way to trace back to the original creator if the case is ever challenged. Fixed sources that don't publish an author identity are attributed to the site itself, explicitly — never to a stand-in like the repo name or a generic Unknown.
Prompt
The entire point of a case is handing someone a prompt they can verify. Without the full prompt, a case is just a nice-looking image with no use to the reader.
Timestamp
No publish date means no way to tell if the content is stale, and no way to place it in the heat-percentile comparison below — that comparison needs a time anchor to be relative to.
Heat
A case can clear every other bar and still be something nobody looked at — that's the gap this closes. Heat is the only signal that actually verifies the content was tested by an audience, not just that it exists.
Prompts reverse-engineered from output are never accepted
Training data is full of prompts that read like expert work and were never actually run. Every case we publish must be checked by a human against the original post, and a prompt a platform reverse-engineered from the output image is rejected outright. That rule has governed all published content since 2026-08-05, no exceptions — a source repo's star count doesn't buy it a pass.
A new case has to beat its peers
Heat isn't judged on an absolute number — a like on one platform and a like on another aren't the same unit, and a fixed threshold goes stale as the library grows. We judge relative position: a new case's heat score has to be at or above the median of already-published cases on the same platform. A platform without enough published cases to trust a median (fewer than 20) goes to manual review instead of applying an unproven baseline.
- 01At or above the platform median → queues for manual review
- 02Below the median → rejected outright
- 03Fewer than the minimum sample on that platform → manual review, no automatic baseline applied
- 04No verifiable engagement data at all → rejected
What L0 / L1 / L2 mean
Evidence level ships on every case. Published cases are always L1 or L2 — L0 never appears on something we've published; it's only a fallback display value when data is missing.
- L0
- Fallback value for unrated or incomplete data. Never appears on a published case.
- L1
- Author, full prompt, an accessible original source, and real media have all been checked. This is the minimum bar to publish.
- L2
- Everything L1 requires, plus an independent retest — someone actually ran the prompt again, and the stability score reflects that run instead of standing in as a placeholder.
Same source doesn't get counted twice — but replication builds trust
Same original URL, same prompt, or the same author posting near-identical content — any of the three is treated as a duplicate and rejected.
Replication is exempt
But the same prompt run by different authors into different outputs is not a duplicate. It's the opposite — the strongest evidence that prompt actually works, because it wasn't invented, it was reproduced.
These never reach the candidate pool
Not stricter review — these categories don't clear a single one of the requirements above.
- Collections with no per-item author or source post
- A large, well-starred collection with missing bylines and source links case-by-case still doesn't get in — the author and provenance requirements can't be backfilled.
- Prompts reverse-engineered from output
- Hits the provenance line above. No exceptions.
- Entries with no engagement snapshot
- No verifiable likes, comments, shares, or saves means the heat threshold can't even be evaluated. Rejected.
This bar tightens as more sources come online — it doesn't loosen. Changes here follow changes to the gates.
Read the submission guide →→