d-k-p

For sure, you can handle generating both images and text in the same workflow running multiple AI SDK operations in parallel or sequence, and then combine the outputs however you need for your PDFs.

I'd recommend browsing our examples docs (https://trigger.dev/docs/guides/introduction) if you want to see different ways of using the AI SDK and converting / generating PDFs (React to PDF / Libreoffice, etc).

That's fair, we understand there can be trade-offs when picking a workflow tool. Was there anything else we were missing or was it purely the hosting model which made the difference?

We appreciate the support either way!

(other Trigger.dev co-founder here) That's awesome.

Let us know if there's anything we can do to make the product better for you

Thank you, really appreciate that comment. That's the bracket we see ourselves in, and for the same reasons (as product builders).

We have a few examples with descriptions in the docs here: https://docs.trigger.dev/examples/examples

The example repo eallam shared has more though, we will be moving all of them to the docs soon!

In Trigger.dev workflows are created completely in your code rather than in a node-based UI (which to be fair does allow you to write code sometimes). We found developers could actually put together workflows faster if the whole thing was code rather than a hybrid of UI / code (because you get to use your own IDE + Copilot).