points by simianwords 1 day ago | 0 comments
Honest question, why shouldn't any agent SDK's API simply be a PROMPT.md with a runtime that runs the LLM with tools; why do you need excessive abstractions over that like langchain offers?
Is it to have boundaries of some determinism?
[–] zomtorg 1 day ago
[–] asim 1 day ago
What do you use for that?
[–] zomtorg 19 hours ago
Mainly gRPC for cross-service communication, k8s, and all the workflows on Temporal with the agent logic as activities.
For tracking and adding guardrails across many agents and having caps (e.g. the same agent type can do at most X of this action in 24 hours) I have created https://actera.dev/
[–] ashishmax31 1 day ago
>runtime that runs the LLM with tools
This "runtime" is what you are building with LangChain.. A harness like claude code/codex etc is general purpose and its env is a shell + tools. But with a custom runtime (basically a loop where we ask llm what to do next), we can give it specific tools which we define in code. This can help with things like authorization since, well its custom code you own.. so the runtime gets the tools scoped to the users permissions etc.
[–] imtringued 1 day ago
What's the point in putting the vibe back in if you're implementing a specific software development process to avoid the vibe?
The entrypoint still has to come from somewhere, and it's much more convenient to be able to explain the security and legal teams how data is handled, what is logged, how you can have control over a scenario where the agent does something unexpected.
Sure, for a personal project that could be enough, but we all know those companies target enterprise customers, and you would be surprised how little adoption there is when it comes to workflow automation due to the lack of controls.