61–70 of 70 posts
Earlier quoted context omitted.
I'm curious what product you ship for workflows? I'm looking at pushing out a workflow engine in the near future and it is interesting to me to see what other people are doing.
Out of respect for my competitor's Launch HN, I don't want to say here, but if you look at my profile or google my username it won't be hard to find. :)
I'm very interested in trying this out for my side project. I'm using Vercel's AI SDK to generate content and images to create PDFs but getting it to output both images and text in the same generateObject call feels almost impossible. Is it something that Trigger can do?
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).
We're very satisfied customers since January of this year. We use it as an extension of our node app, for all things asynchronous (long or short). The fact that it's the same codebase on our server and trigger cloud is a huge plus. For me, it's the most accessible incarnation of serverless. You can add it to your stack for one task and gradually use it for more and more tasks (long or short). Testing and local develo…
Sorry you had some issues migrating. You're right, it was our biggest docs update so far, and unfortunately a few things did get missed which we have (hopefully) since rectified. Please do let us know if there's anything else we missed and we'll get it sorted.
Earlier quoted context omitted.
I'm curious what product you ship for workflows? I'm looking at pushing out a workflow engine in the near future and it is interesting to me to see what other people are doing.
Out of respect for my competitor's Launch HN, I don't want to say here, but if you look at my profile or google my username it won't be hard to find. :)
> FWIW, more than 1/2 of our customers are AI agents, so it does make sense.
We’ve seen the same thing, more even. Our positioning wasn’t even lead by our investors; we figured if the main thing our customers were doing on the platform was building complex/long-running AI agents (and ‘agentic’ workflows), it made sense to lean into it. Fortunately (or unfortunately) for us, it does actually fit what we do pretty well, even if you can also do a lot of other great stuff with the platform which isn’t covered under that umbrella. It’s a tricky thing to get right.
How does this differ to Mastra?
We do plan on adding our own AI primitives in the future, but we will also always aim to be framework agnostic. Frameworks like Mastra, Vercel’s AI SDK, etc, pair really well with us; you get agent features on top of our execution layer that’s reliable at scale. We think the best solution for developers gives them optionality to use the tools they’re already familiar with.
Earlier quoted context omitted.
Very common issues were: forgetting to put non-determistic code inside of steps (deterministic code can be put outside of steps, but non-deterministic = boom), incorrect use of cache keys (people would put dynamic data inside the cache key). Another issue we hit pretty frequently that a single step would take longer than the serverless function timeout it was running on (this was before we ran our own compute platfor…
You keep saying deterministic… What are you actually trying to say? Based on your docs: I mean googling “deterministic temporal.dev” brings up nothing. I found other libraries and I get it. I assume you mean, “replayable by our engine,” but that would give away: replayability of most code in all the languages you support is hopelessly out of scope. “Pure” isn’t even a useful constraint - lots of code looks pure, but…
And if you're gonna come back with "but that's not real determinism!" then I would remind you that actually no code is deterministic because of quantum uncertainty, and that quantum uncertainty isn't necessarily real because of solipsism, and that there's more to life than rhetorical definition interrogations.
I'm very interested in trying this out for my side project. I'm using Vercel's AI SDK to generate content and images to create PDFs but getting it to output both images and text in the same generateObject call feels almost impossible. Is it something that Trigger can do?
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).
How does this differ to Mastra?
Mastra and Trigger.dev solve different but complementary problems. Mastra is great for building AI agents, with abstractions for reasoning, memory, tools and observability. Trigger.dev is an agent-agnostic cloud runtime: capable of running long-running compute defined TypeScript with retries, queues, waitpoints, and observability. We do plan on adding our own AI primitives in the future, but we will also always aim t…