Cloudinary, without opening Cloudinary.
Find the asset, not the folder it might be in.
“@Ray find the product shots we tagged for the spring launch”
What Ray can and cannot do in Cloudinary
Reading is free, because reading changes nothing. Everything that writes waits for you. The rest is not on Ray’s list.
Runs on its own
What Ray reads in Cloudinary
- Search every asset by query expression, by tag, by folder or by what an image looks like
- Images, videos and raw files with their tags, context and metadata
- Named transformations, upload presets, folders and moderation queues
- Storage and bandwidth usage, and how often a video was watched
Reading changes nothing, so Ray never stops to ask whether it may look something up.
Asks first, every time
What waits for your approval
- Uploading a file from a link, renaming it, or moving it between folders
- Setting tags, metadata and context on assets, and linking related ones
- Building derived media: slideshows, archives, text images, page splits
- Making private assets publicly deliverable, and restoring deleted ones
Ray posts a card showing exactly what it is about to do. Nothing happens until someone clicks approve, and no setting turns that off.
Not on the list
Things Ray is never handed
These are left out during curation, so they are not something Ray could do and decides against. They are not in front of it at all.
- Destroy an asset, empty a folder, or delete assets by tag
- Strip every tag or context value off a set of assets in one call
- Configure the account: upload presets, upload mappings, webhook triggers or live streams
How Ray works with Cloudinary
No workflow to build, and nothing to maintain when the work changes.
- 01
Connect Cloudinary
Cloudinary has no per-person login, so it takes one workspace key. Ray posts a connect card, you paste the key on Ray's own page rather than in Slack, and it covers the whole team from then on.
- 02
Ask in plain words
In the conversation you were already having. Nothing to build, no trigger to map, no tab to open.
- 03
Approve, and it lands
Reading runs on its own. Anything that creates, sends or spends stops first and shows you the exact content.
Priya
@Ray the checkout bug is back. Take a look in Cloudinary, and tell Dana it is being looked at.
Link Cloudinary assets together
- Waiting on
- your approval
What does connecting Cloudinary to Ray actually do?
Ray is an AI teammate that works in your team chat, on Slack today. Connect Cloudinary and it can do the Cloudinary part of a request without anyone leaving the conversation: read what it needs, draft the change, and post it for approval before anything is written.
It is not a workflow builder. There is no trigger to configure and no automation to repair when your process shifts. You describe the outcome in the thread and Ray picks the actions, including actions in your other connected tools when the request spans more than one.
Cloudinary has no per-person login, so it connects once with a single workspace key and covers the whole team. Ray reaches whatever that key reaches, which is worth scoping the way you want everyone to see Cloudinary. Every write still stops for approval first.
Security and permissions
- You paste the Cloudinary key on Ray’s own page, never in Slack. It goes straight to the connection and never reaches the model.
- Writes are gated in the execution path, not by a prompt. There is no setting that grants blanket approval.
- Each workspace is isolated at the database level, and that isolation is tested by trying to break it.
- An admin, or whoever connected it, can disconnect Cloudinary in a message. Uninstall Ray and every connection it held is revoked.
More storage & files integrations
Ray uses them together in a single run when a request spans more than one.
Put Ray to work in Cloudinary.
Free to start, no credit card, and it asks before it acts.