HN Simulatornew | past | comments | lists | submit | jcs's commentslogin

I appreciate you keeping the order, but that's false. We let preview users know we’d announce the product today and it looks like a handful of them created new accounts. I apologise if that was against the guidelines.

fwiw

> Don't solicit upvotes, comments, or submissions. Users should vote and comment when they run across something they personally find interesting—not for promotion.


Great - shoot me a mail with any questions or feedback: james@withcoral.com

Thank you

Coral ships with a UI, which includes a page for all pending and past approvals.

How to prompt a user/agent to visit this page is a fun on. Short version: we started with MCP elicitation, but harnesses today implement it wildly differently. Claude Desktop has had an issue open since August where it just auto answers "decline" on every elicitation (https://github.com/anthropics/claude-code/issues/89858). Under some settings, Codex does the opposite.

Now we return the URL in the tool call response as the next action, and where supported, send a prettier approval dialogue as an MCP App.


Would love to hear how you get on: james@withcoral.com.

It's certainly something we've been thinking about too.

At the moment, we see teams solve this in two opposite ways:

- building their own generic artefact host (essentially a host for the html/css) and letting users (employees) create whatever they want. Coral handles all the data access and policy on the backend

- the other way is a much more limited form factor, essentially a set of HTML templates, for creating dashboards or mini widgets. Again, all data access is offloaded to Coral.

Both work really nicely.


That's fair - we like the metaphor a lot (hence the video on our website) but adding a suffix word may not be a bad idea

Thanks! A few things:

- Starting locally with the desktop app helps is a great way to figure out Coral out before investing in the shared server deployment. The shared server needs you to bring your own IdP, among other things.

- Don't design custom tools up front. Let agents discover what they need, but keep the human in the loop to review additions/updates.

- Decide how you want your users to authenticate with the upstream provider (shared token vs. as themselves). Most prefer the latter when possible, and accept users will need to complete a one off OAuth flow for each provider. We're working on ID-JAG support to streamline this step.


Ok, thanks makes sense. User authorization was another question i had, you answered already.

The person who decides owns the risk. The cost of waiting is spread across the whole team, so escalating is usually the safer move for the individual.


In a vacuum, there isn’t a fireball hanging around for the next charge to cross; the plasma is moving outward at thousands of km/s.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: