The pipeline
It reads the whole thing before it says a word about it.
Most AI reading tools sample. Scripitt performs one complete comprehension pass over the entire work, then runs its judgments against that read — which is why the evaluation can cite the page instead of gesturing at it.
01
Intake
Drop the material in
PDF, DOCX, DOC, TXT, RTF, Markdown, Final Draft or Fountain — single title or a whole submission pile. Scanned pages are read by vision OCR. Title, author, genre and coverage mode are detected on the way in.
02
Comprehension
One full read of the whole work
Before any judgment is passed, the system reads the material end to end and builds a structured understanding of it — characters, structure, turns, voice. Every downstream opinion is grounded in that read, with citations back to the page.
03
Analysis
Specialist passes, run in parallel
Mode-specific reviewers evaluate craft, market, character and commercial shape at the same time, then a reconciliation pass resolves disagreements between them instead of averaging them away.
04
Delivery
A report a human can act on
Verdict, weighted scorecard, strategic scores and full written coverage, distilled into a one-page Decision Brief — editable, exportable to DOCX or branded PDF, and filed in a searchable library.
In order
The five capabilities
01
Read & Understand
One complete pass over the whole work before any judgment is formed, building a structured understanding of character, structure, turn and voice.
02
Evaluate & Score
Mode-specific specialists assess craft, market and commercial shape, reconciled rather than averaged, against the lens you chose.
03
Route & Compare
Lanes, likely buyers and kindred voices with fit scores; two or three projects set against each other with the reasoning shown.
04
Remember & Organize
A searchable library with provenance, revisions and coverage numbers bound to the exact draft they describe.
05
Operationalize Insights
Decision Briefs, recorded company decisions, branded exports and answers drawn from your own catalog — the read becomes something the organization can act on.
Modes
Seven rubrics, one for each kind of read
Feature Script
Full coverage on a feature screenplay — logline, synopsis, craft breakdown, market read and a Pass / Consider / Recommend verdict.
TV Pilot
Pilot-specific analysis: engine, series-ability, character runway, episodic vs. serialized fit, and where the season two problem lives.
Book & Manuscript Review
Long-form editorial coverage for publishers and literary teams — structure, voice, market position and comparable titles.
Quick Book Triage
A fast first-pass read for a full submission pile. Sort the stack before anyone spends a weekend on it.
Book-to-Screen Adaptation
Adaptation feasibility: what survives the translation, what has to be invented, budget shape and the format the material actually wants.
Publishing Readiness
Submission-grade assessment of whether a manuscript is ready to go out, and precisely what is holding it back.
Micro-Drama & Vertical Series
Built for the vertical short-form format on its own terms: hook velocity, per-episode cliff placement, retention across an episode arc, and whether the premise sustains a full season at that length.
Capabilities
What the platform does around the report
Evaluation Lens
Patent pendingCoverage is never generic. Choose the lane, the buyer and the creative sensibility the material is being judged against, and the read changes accordingly.
Trainable taste
Patent pendingCalibrate a lens from the scripts an executive actually loved, or simply describe the taste in a few sentences. The system learns that sensibility and applies it consistently across the pile — and it cannot be instructed to force a verdict.
Alignment Radar
Names the lanes the material fits, the buyers most likely to respond and the kindred voices it sits beside — each with a fit score, not a vibe.
What-If Simulator
Re-score the material under an as-executed assumption. Separates what is wrong on the page from what is merely unproven.
Decision Brief
Patent pendingThe whole read on one page, written for the person who has to make the call: recommendation, rationale, top strength and top risk, next action, market read, a production-reality band and what would change the decision. Shareable by link, exportable to DOCX, and carrying your letterhead.
Company Decision
The AI recommends; the organization decides — and the platform records which is which. A verdict, who made it, when and why is logged against the project and travels with the brief and the library register, so the human call is never confused with the machine's.
Side-by-side
Put two or three projects against each other and get a head-of-development recommendation with the reasoning shown.
Ask the library
Every report is indexed. Ask your own catalog a question in plain language and get answers with the coverage cited.
Provenance Ledger
Patent pendingEach submission is fingerprinted at intake and written to an append-only chronology, with the coverage number bound to that exact revision. A Creator Provenance Report can be exported for any work, stating what is known and naming what is not.
White-label
Patent pendingEnterprise workspaces carry your logo, your colors and your letterhead across the workspace, every shared report and brief, the preview card a recipient sees, and the DOCX export. Brand identity is imported from your website in one step; nothing on an outward surface says Scripitt unless you want it to.
Library registers
Export or print a register of the desk, the cloud library or server activity — material and coverage numbers, recommendation, the recorded company decision, what was shared and when. Metadata only; the text never leaves.
Provenance
A record of what arrived, and when
Every submission is fingerprinted with a SHA-256 hash at intake and written to an append-only chronology enforced at the database. A coverage number is bound to the exact revision it was produced from, so a report can never quietly drift from the draft it describes.
Plainly stated
The Provenance Ledger is internal chain-of-custody documentation. It is not a copyright registration, not proof of authorship and not a credit determination.
We say this on the record and in the product because the alternative — letting anyone believe a software timestamp settles a rights question — would be worse than useless to them.
The standing rules
The machine never writes
Scripitt does not generate, rewrite or punch up creative material. Not a line. It reads, it assesses, it cites. Authorship stays entirely with the writer.
The decision stays human
Every output is an input to a person's judgment. The verdict is a recommendation with its reasoning exposed, so a reader can disagree with it on the evidence.
Nothing is asserted without the page
Claims trace back to the material. If the read cannot support a judgment, the report says so rather than inventing confidence.
Questions
Straight answers
Does Scripitt write or rewrite creative material?+
No. Scripitt does not generate creative material of any kind. It reads what is submitted and produces an assessment of it. The writing stays the writer's.
How long does an evaluation take?+
Minutes rather than days for a standard feature or pilot. Longer manuscripts take proportionally longer because the whole work is genuinely read before anything is judged. We position on speed, not on a contractual turnaround.
What happens to material submitted to the platform?+
It is stored against your organization's workspace under row-level access control, visible to your team and whoever you share it with. It is not used to train public models.
Is the Provenance Ledger a copyright registration?+
No. It is an internal chain-of-custody record — a fingerprint and a timestamped chronology. It is not a registration, not proof of authorship and not a credit determination.
Can it be calibrated to our organization's taste?+
Yes. Point a lens at material your team responded to, or describe the taste in your own words, and it calibrates against that sensibility, so evaluations reflect how your organization reads rather than a generic industry average.
What formats can it read?+
PDF, DOCX, legacy DOC, TXT, RTF, Markdown, Final Draft (.fdx) and Fountain. Scanned PDFs are handled with vision OCR.
Is the AI's recommendation the decision?+
No. The recommendation is the platform's; the decision is yours, and the two are recorded separately. When your team logs a company decision, the brief and the library register show who made it and when, alongside — never instead of — what the evaluation said.