Dream Render · Team Console

Operations at a glance

A bounded, auto-refreshing view of work that may need attention.

Running now: UnavailableNon-terminal work owned by the platform.
Waiting on people: UnavailablePaused for user input, not stuck platform work.
Unsuccessful in 24 hours: UnavailableFailed, cancelled, superseded, and completed-without-output runs in the durable sample.
Unreviewed deliveries: UnavailableCounted from the newest 25 delivered versions.

Needs attention

Waiting to load workflow data.

Open Monitoring

Review next

Waiting to load review work.

Open all review work

New here? This is the Dream Render video review tool.

Dream Render turns a text prompt into a short marketing video. This tool lets the team watch those generated videos, optionally reveal the panel judge scores, and leave human feedback. Hover any iCircled “i” icons like this one explain where a value comes from and where it’s used. for details, or open the for the full guide.

No version selected

Select a project version from the queue

Version preview

The project's latest delivered version. It uses the exact MP4 when one exists; otherwise it uses the iframe preview. GET /v1/review-compositions/:composition_id

Pick a project version from the queue, or paste a composition id.

Human review iFeedback is still saved against the producing run in this first increment. Exact per-render multi-review panels come next.POST /v1/runs/:run_id/feedback

Rate the six observable dimensions. Each score is optional; add concrete evidence where useful.

Full rating guideline

Loading review rubric…

Questions (1–5, optional) iThe same six score anchors and full guidance used by the benchmark calibration platform.GET /v1/feedback/criteria

Loading review rubric…

Overall comment (optional)

Share a reference video iLinks to great videos Dream Render should be able to make — inspiration + a target bar for the team, kept as a shared library.POST /v1/feedback/references

Inspiration the pipeline should aspire to. GET /v1/feedback/references

URL a great video Dream Render should be able to make

Bugs & feature requests iReports submitted from Studio's floating feedback nub — product bugs and feature requests, each with the page context (route, project, viewport, console errors) captured at report time.GET /v1/feedback/bugs

What people hit in the product, newest first. GET /v1/feedback/bugs

Search loaded reports

Loading…

AI insights iA bounded recent window of feedback, automatically clustered into recurring themes (a Gemini model when configured, else grouped by tag). The window and completeness are shown below.GET /v1/feedback/insights

Recent team feedback, grouped into themes with suggested fixes. GET /v1/feedback/insights

Loading…

All feedback iThe raw corpus — every video + general comment from everyone, newest first.GET /v1/feedback/export

The complete, cross-user feedback corpus. quality analysis

Add note

Record a cross-cutting observation that is not tied to a project or run.

General feedback

Evaluation trends iIs the product getting better or worse over time? The offline eval re-scores a fixed golden set on every commit + nightly (free, deterministic) and commits one row per commit. This charts that history — separate from the live per-video judge.GET /v1/quality/trend · eval-harness/history/golden.jsonl

Two series: live delivered-video quality (per day, from every AI-judge verdict) + the offline golden regression gate (per commit). GET /v1/quality/trend quality_results

Loading…

Investigate a project or run iStart with a project or run ID. Project lookup shows recent runs; run lookup shows context, error, costs, timings, assets, composition, infrastructure, and events.GET /v1/review-projects/:project_id/debug · GET /v1/review-queue/:run_id/debug

Find why a project failed or why its result was not ideal. Paste an ID, or follow an Investigate link from Overview or Monitoring.

Enter a project or run ID to start.

Requests refused before a Run

Find safe admission receipts by owner. These attempts are separate from Run delivery rates.

Workflow monitoring

Live durable workflow state and run-level diagnosis. This is workflow data, not service uptime or client telemetry.

Open Monitoring to load workflow data.

Projects iEvery project's lifetime run counts + completion rate, across all users, worst first — spot projects that aren't producing video. Click a column header to re-sort. Open a project to inspect its runs and available details.source: GET /v1/admin/preview/projects

Run outcomes per project, worst completion rate first. GET /v1/admin/preview/projects

Min runs Search loaded

Loading…

Enterprise Projects

Browse Projects created by employees of attributed enterprise clients. Internal and test accounts are excluded. Re-run creates a new Generate project in your account from the first prompt text only; it does not change the employee's Project or copy its Assets. GET /v1/admin/preview/enterprise-projects

Enterprise client Search loaded Projects

Open this tab to load enterprise Projects.

Public Templates

Create, validate, and publish the revisioned platform Template catalog. Private agent instructions are visible only in this protected view. /v1/admin/templates

Search loaded Templates Show archived

Open this tab to load Templates.

Select a Template

Choose a draft to inspect it, or create a platform Template.

New public Template

Slug

Title

Card subtitle

User input fields

0 of 16 fields

No user input fields.

Generated input schema JSON

This JSON is generated from the fields above and is the value saved with the Template.

{"schema_version":"v1","fields":[]}

Fixed Asset bindings JSON blank keeps all on edit; use retain_keys + add

Presentation media

Choose automatic media to generate the preview and poster from the full demo, or upload each file yourself. The server verifies all bytes before they can enter a draft.

Setup

File

Upload the full MP4. The server uses its first 3–4 seconds for a silent 540×960 preview and creates the matching PNG poster.

Save the Template draft before staging media.

Revision and audit history

Select a Template to load its history.

New chat placement

Choose up to four published, active Templates. Saving replaces the complete New chat order. PUT /v1/admin/template-placements/new-chat

Position 1

Position 2

Position 3

Position 4

Open this tab to load placement.

Feature flags

Runtime, per-environment feature toggles. Ordinary changes are revision checked and take effect on each user's next Studio load. GET /v1/admin/feature-flags · POST /v1/admin/feature-flags/:key/conditional

Search flags State

Loading feature flags…

Organizations

Loading…

Select an organization.

Loading…

Find one user's organization attribution by id or email address. GET /v1/admin/users/:user_id/organization · POST /v1/admin/users/organization/lookup

Enter a user id or email above.

From To (inclusive)

Choose a window and select Load.

Users & roles

Search accounts, inspect effective Console roles, and manage auditable role grants. GET /v1/admin/users GET/POST/DELETE /v1/admin/console-roles

Search loaded users

Role

Loading users…

Select a user

Choose an account to inspect its effective roles and grant history.

Docs & help

Dream Render turns a text prompt into a short, social-ready marketing video (think 6–20s vertical ads). This tool is where the team reviews what the pipeline produced: watch each generated video, optionally reveal the six panel judge scores, and leave human feedback.

How a video gets here

Promptuser brief

→

Rungenerate / chat

→

Videorendered MP4

→

Panel judgessix scores

→

Your reviewhuman verdict

→

Evaluationcompare results

A Project holds one creative task. Its latest delivered Composition is the review version. The tool shows its MP4 when present, or its iframe preview.

Where things live

The sidebar keeps every Console destination visible. Only Video Review opens the contextual review queue. Run Diagnostics accepts a project or run ID and can also use the run selected in Video Review. The other destinations use their own data and controls.

Overview: Shows the verified environment, workflow snapshot freshness, active platform work, 24-hour unsuccessful outcomes, and a bounded sample of versions that need a first review.
Operations: Overview shows work that needs attention. Monitoring provides the complete workflow view. Projects compares run activity across projects. Run Diagnostics finds a project or run and shows its context and technical details.
Review queue GET /v1/review-queue: The left rail shows the latest delivered composition for each project. Filter narrows loaded rows. Scope, Owner, Mine, and External request a server filter. The account-type badge on each row is server-authoritative. It can show internal, external, test, or unknown.
Feedback: Explorer searches the cross-project corpus and contains the Add note action. Product Reports tracks bugs and requests. Feedback Themes groups recurring feedback. Reference Library stores examples.
Evaluation: Video Review lets you inspect a delivered project version and leave run feedback. Enterprise Projects filters employee work by client and can start a text-only replay in the administrator's account. Benchmarks opens the external benchmark catalog.
Administration: Organizations manages organization attribution. Users & Access manages auditable administrator grants. Templates manages revisioned public templates. Feature Flags manages rollout settings.
Help: Task guide explains the console, data sources, review flow, and access rules.

Panel judge scores

Six independent judges use the same dimensions as the human form: visual defects, text legibility, hook strength, voiceover quality, brief adherence, and product fidelity. Their exact-output scores are hidden until you choose Reveal judge scores. Preview-only versions have no panel scores because there is no judged MP4.

Where your data comes from & goes

What you see	Comes from	Where it's used
Video & prompt	`runs` + S3 `Asset` (signed URL)	You watch & judge it
Panel judge scores	`quality_results`	Compare with human ratings after reveal
Your review	you → `POST /v1/runs/:id/feedback`	Human quality analysis
Conversation	project `messages`	Context for chat-generated videos

Why your reviews matter: comments and scores make quality problems concrete and comparable across finished videos.

Identity & access

This tool is administrator-only. Your identity and active administrator authority are resolved from current server state on every request. Review actions remain attributed to your account, and you can edit or delete only your own comments.

Sign in to Console

Operations at a glance

Needs attention

Review next

New here? This is the Dream Render video review tool.

Version preview

Human review iFeedback is still saved against the producing run in this first increment. Exact per-render multi-review panels come next.POST /v1/runs/:run_id/feedback

Share a reference video iLinks to great videos Dream Render should be able to make — inspiration + a target bar for the team, kept as a shared library.POST /v1/feedback/references

Bugs & feature requests iReports submitted from Studio's floating feedback nub — product bugs and feature requests, each with the page context (route, project, viewport, console errors) captured at report time.GET /v1/feedback/bugs

AI insights iA bounded recent window of feedback, automatically clustered into recurring themes (a Gemini model when configured, else grouped by tag). The window and completeness are shown below.GET /v1/feedback/insights

All feedback iThe raw corpus — every video + general comment from everyone, newest first.GET /v1/feedback/export

Investigate a project or run iStart with a project or run ID. Project lookup shows recent runs; run lookup shows context, error, costs, timings, assets, composition, infrastructure, and events.GET /v1/review-projects/:project_id/debug · GET /v1/review-queue/:run_id/debug

Requests refused before a Run

Right now

Selected range

Investigate unsuccessful runs

Platform-owned work

Waiting on user

Operation performance

Daily activity

Broader analysis

Projects iEvery project's lifetime run counts + completion rate, across all users, worst first — spot projects that aren't producing video. Click a column header to re-sort. Open a project to inspect its runs and available details.source: GET /v1/admin/preview/projects

Enterprise Projects

Public Templates

Select a Template

New public Template

User input fields

Presentation media

Revision and audit history

New chat placement

Feature flags

Organizations

Users & roles

Select a user

Docs & help

How a video gets here

Where things live

Panel judge scores

Where your data comes from & goes

Identity & access