Claude Dashboards and Motion or a Sume schedule for a weekly recap
For a weekly metrics recap, Claude Dashboards plus Motion fits warehouse data and edits by hand; a Sume schedule fits footage and a $1.00 default cap per run.
Use Claude Dashboards with Motion when the recap is numbers from your warehouse and a person will review and edit it. Use a Sume schedule when the recap needs generated footage, a presenter or a voice and must run on a clock without anyone opening an editor. Both can produce a weekly video; they start from different inputs.
Anthropic announced Dashboards and Motion on 2026-10-08. Dashboards connects to Redshift, BigQuery, ClickHouse, Databricks, Snowflake and Salesforce. Motion turns a prompt into an animated explainer made of code-driven text, charts, shapes and images, and it is in beta on Team and Enterprise.
Side by side
| Question | Claude Dashboards + Motion | Sume schedule |
|---|---|---|
| Data source | Warehouse and CRM connectors listed on the announcement | Instructions you save; the agent fetches or generates in a fresh thread |
| Footage | None; no video generation model, no AI people | Generated media is possible, billed per use |
| Edit a number | Change any word, number or timing in the editor or ask Claude | Edit the saved instructions, or start a new run |
| Output | MP4 download; opens in Adobe, Descript, HeyGen, Higgsfield, invideo, Luma AI or Runway | Structured receipt with artifacts and an optional signed webhook |
| Spend control | Not stated on the announcement | Per-schedule spend cap, default $1.00 |
| API access | The announcement does not mention an API | Runs start and read via API; creating a schedule is done in the dashboard or by asking the Agent |
What a Sume schedule needs
A schedule is a saved Agents automation with instructions, a model, a cron expression and a spend cap. The cron has five fields and an IANA time zone. The Developer API can list schedules, read them, start runs and monitor runs, but it cannot create or edit them.
Each run starts in a fresh thread. If the previous run is still going when the next tick arrives, on_active_run decides what happens: skip records a terminal skipped run, and reject refuses the new one. A skipped run does not send a webhook, so do not wait for one.
Worst-case spend
The default spend cap is $1.00 per run. A weekly schedule left at the default can therefore spend at most 52 x $1.00 = $52.00 in a year. Raise the cap only when the recap needs generated footage; the cap is an upper bound, not a charge, so a run that spends $0.30 bills $0.30.
Compare that with a manual workflow: nothing runs until a person opens the editor, which is a feature when every number needs a human eye.
A reasonable split
Do the quantitative slide-style recap in Dashboards and Motion, where Claude can read the warehouse directly. Use Sume for the branded intro, a presenter or a voiced version of the same script, and set a run webhook so your system hears when the file is ready. The two are not exclusive: a Motion export can be an input to a Sume Timeline render once it is hosted.
Sources
Related posts
More in Use cases
- Narrated Lesson Video From 10 Slides: A Seven-Minute Cost Breakdown
A 7-minute course lesson from a script and 10 slide images: TTS, gpt-image-2.5 slides and a Timeline 1.0 render, with each line of the bill worked out.
- Cut away to B-roll without breaking the voice: one detached spine
Detach the A-roll audio once ($0.01) and render three slots in one Timeline job ($0.10): 32 s of picture, B-roll over the middle, the voice unbroken.
- Daily news brief voiceover: 1,400 characters a day for 30 days
A 1,400-character daily brief costs $0.0665 on Sume TTS, so 30 days is $1.995. Table for 1,000, 1,400 and 2,000 characters, plus a retry-safe daily job.
- Do 480p AI video clips pass TikTok's ad minimums? 540x960 and 640x640
TikTok's non-Spark ad minimums are 540x960, 960x540 and 640x640. A 480p AI clip is named for 480 pixels on its short side, which is below all three. Use 720p.
Written by Sume