Skip to main content
Studio is WriterzRoom’s governed production workspace. It replaces prompt-first generation with a three-stage workflow that validates context, template structure, style behavior, and required inputs before execution.
01
Context
Select General or activate a vertical-specific corpus and compliance policy.
02
Workflow
Choose a schema-driven template and a validated style profile.
03
Production brief
Complete required inputs, select execution depth, and run the pipeline.

Context

Select General for unrestricted access, or choose an industry vertical to activate:

Scoped research

Research is grounded in the selected vertical’s corpus and domain terminology.

Compliance controls

Regulated workflows can inject disclaimers, citation requirements, and claim constraints.

Template filtering

Only templates approved for the selected vertical remain available.

Style filtering

Recommended, compatible, and all permitted style profiles remain separately visible.
Studio does not silently bypass failed vertical validation. If template or style constraints cannot be loaded, the workflow stops until the configuration service is available.

Workflow selection

The template defines the output contract: required fields, section order, structural rules, validation requirements, and agent instructions. The style profile defines voice, pacing, tone, complexity, and formatting behavior. The selector provides three style scopes: Template links from the catalog open Studio with the workflow preselected. Studio then loads the full template detail schema before allowing generation.

Production brief

The Production brief panel is generated from the selected template’s YAML schema. Field types can include text, long-form text, select, multiselect, checkbox, number, range, date, combobox, and file upload.
A displayed input count of zero means the selected template has no additional structured fields. It should not appear when the template detail endpoint contains parameters.

Source files and coverage

Upload sources in the Production brief. Studio shows a short text preview and a separate extraction report: retained units, total units when known, worksheet coverage, unreadable pages and processing limits. The preview is not the full evidence payload. Extracted records are saved to your account; original file bytes are not retained. CSV and JSON retain records beyond the preview. Spreadsheets include visible and hidden sheets; Word extraction includes tables, nested tables, headers and footers. Spreadsheet formulas are retained as text, not calculated results. Charts, drawings, embedded objects and document notes may require a text export. Required source fields must contain a complete, readable upload. Selected files with incomplete extraction hold generation even when the field is optional. Remove or replace those files before continuing. Removing a file detaches it from the brief and clears its preview and coverage; it does not delete a stored extraction or earlier generation records.
OCR is not performed. Image-only pages, detected image content and unreadable PDF pages require an OCR-processed, text-only copy or a reviewed text export. Blank pages and decorative images can also trigger this conservative coverage check. Extraction completeness does not establish factual accuracy or professional review.
Each file is limited to 10MB and 80,000 retained extraction characters, with additional page, sheet and unit limits shown in its coverage report. There is one combined 60,000-character source context limit per generation, including source labels. If the sources exceed that limit, split the work or upload a smaller relevant selection. The system holds the request before charging rather than silently dropping source material. Earlier unsaved uploads must be uploaded again to use the stored-source contract.

Generation tiers

The selected tier controls workflow depth, timeout, model ceiling, and validation stages. It does not substitute a different template or style profile.

Pipeline inspector

During execution, Studio shows the active agent and the queued or completed state of every stage. The exact pipeline changes by tier.
1

Planner

Validates the requested structure and builds the production plan.
2

Researcher

Retrieves evidence and domain context when the tier and template require research.
3

Call Writer

Assembles the writing context and drafting instructions so the Writer receives structured guidance instead of loose notes.
4

Writer

Drafts the main content body against the template structure, style profile, and available research context.
5

Editor

Reviews the draft for grammar, readability, structure, tone consistency, and AI-tell limits.
6

Formatter

Applies the final output structure and formatting rules for the selected deliverable.
7

SEO

Supports metadata, keyword alignment, and search intent where discoverability applies.
8

Quality Gate

Enforces the deliverable contract, vertical compliance rules, and structural quality. Every path reaches this stage before publication.
9

Publisher

Saves the validated output and prepares export or connected publishing actions.

Output canvas and readiness

Completed content appears in the Output canvas with copy and Markdown export actions. The Readiness panel distinguishes:
  • Required input completion
  • Workflow execution state
  • Quality-validation state
  • Output word count
A missing metric is shown as unavailable rather than being treated as a score of zero.

Visual generation

Visual generation remains disabled in Studio. It will not be enabled until image quality, persistence, moderation, retries, and audit logging meet the same production standard as written output.

Responsive layout

On medium-width screens, workflow configuration and tier controls collapse into compact horizontal grids. The pipeline inspector and readiness panel move below the output canvas. On mobile, all panels stack vertically without removing any workflow controls.

Reference files

Templates that expose a file-upload field can parse PDF, DOCX, XLSX, CSV, JSON, TXT, and Markdown inputs. Original files and extraction versions are saved privately. Choose a saved version in a Studio file input, or open Sources to inspect locations, download originals, add versions and manage access. Briefs remain pinned to the selected version.
Uploaded material is treated as grounding context, not as text to reproduce verbatim.

Saved evidence and access

Sources start private. A source owner can grant an active teammate read access or read-and-generation access for all versions, including future versions. Review assignment alone does not grant access. Reviews and the asset dossier can reopen an authorized source and its retained page, table or cell locations. Revoking a source holds further generation use and release. Revoking a grant or ending either workspace membership removes the recipient’s source access. This cannot recall downloads, completed provider calls or already published material. Older uploads without a retained original must be uploaded as a new version before reuse. Extraction coverage and location anchors do not themselves verify claims.
Last modified on September 7, 2026