Script continuity review

Compare declared scene states against maintained continuity rules and inspect exact narrative evidence with a separate AI support assessment.

Input

Result

A costume changes colour between two scenes on the same story day. A prop disappears without a documented transition. A continuity review makes such declared state changes visible without inventing missing scenes. Structured scene records, exact passages and maintained rules form the evidence. The server compares states; the AI independently marks whether the supplied passage clearly supports each declaration.

Your texts, pages and images are processed on our own servers in the EU. Trust Center

Try it now Pricing

Who it is for

Suitable for script editors, production coordinators, independent film teams, audio drama teams and game narrative teams maintaining scene-by-scene evidence. The tool supports editorial review and does not replace creative decisions or an exhaustive script reading.

Typical uses

Upload scene text, declared role/prop/costume states and explicit rules with stable IDs.
Select story days, an entity or a category.
Constant rules flag differing declared states; tracking rules document changes without automatically treating them as errors.
Same-day rules restart comparison on each story day, while whole-story rules compare consecutive maintained states across days.
Every comparison names both evidence IDs, both scene IDs, both exact passages and the rule.
Unclear AI support and missing applicable rules remain visible for review.

Example

Input

Scenes: id,day,order,text S1,1,1,Mara wears a red coat and carries a brass key. S2,1,2,Mara wears a blue coat and carries a brass key. Declared continuity states: id,scene,entity,kind,state,quote E1,S1,Mara,costume,red coat,Mara wears a red coat E2,S2,Mara,costume,blue coat,Mara wears a blue coat Maintained continuity rules: id,entity,kind,scope,policy,description R1,Mara,costume,same_day,constant,The coat remains unchanged during the same story day. First story day: 1 Last story day: 999 Continuity category: All Rule policy: All Evidence order: Story chronology AI evidence length: Brief evidence Script baseline: V1

Result

E1 declares a red coat in S1; E2 declares a blue coat in S2. Both scenes belong to story day 1. Rule R1 requires the coat to remain unchanged within that day. The result therefore lists a declared conflict with both passages and R1. The separate AI support column may mark the passages supported or unclear; it does not change the deterministic state comparison or silently rewrite the script.

A fixed example, shortened. Real results are AI-generated: please check them.

Price and limits

Price: usually 1–3 credits
Available with: Free, With package
Input limit: One page with up to 90,000 characters of HTML

Privacy

Processed on our own servers in the EU (Poland). Inputs and results are deleted after 7 days (Free) or 30 days (packages), or right after you see the result if you choose not to store them. Images are deleted right after processing.

In the API

Tool name: script_continuity. Create a job with POST /api/v1/jobs and fetch the result with GET /api/v1/jobs/{id}. You find your API key in your account.

curl -X POST https://do4u.eu/api/v1/jobs \
  -H "Authorization: Bearer d4u_…" -H "Content-Type: application/json" \
  -d '{"tool": "script_continuity", "url": "https://example.com/"}'

Full API documentation →

Questions and answers

Does the tool read an entire unstructured screenplay automatically?

No. The input contains structured scenes, declared states and explicit rules. Exact passages must already match their scene text. This makes the scope auditable and prevents invented scenes or unsupported references.

Does a different state always mean an error?

No. A constant rule produces a declared conflict; a tracking rule merely records the change. Legitimate transitions, flashbacks and intentional continuity breaks require editorial interpretation and appropriately maintained rules.

Are omitted or ambiguous scenes treated as evidence?

No. Only selected, supplied state records are compared. Missing rules can be flagged, and the AI can mark support unclear. Absence of a finding is not proof that a script is consistent.

Is my text stored?

Only as long as needed: 7 days on Free, 30 days with a package – or not at all if you choose not to store it. Processing happens on our own servers in the EU (Poland).

Can I use the result right away?

Results are AI-generated. Please read them before you publish or send them.