Sim's resources take agentic workflows to the next level. Everything's stateful, it's not just third party input to third party output, you can manage files, sync company resources and RAG over it, store and manage tabulated data, it all meshes together, all with collaboration built in.
The Sim agent ties everything together, controlling all those resources. There's a level of trust with the agent that I rarely feel with other copilots - I don't need to babysit every chat, I can just send prompts and check the results. There's a lot of nifty features packed in that extend far beyond workflows (a favorite of mine is generating and editing videos).
Some of the cool stuff i've made:
Creating an incident response tool that triggers on slack messages in a channel and root-causes the issue, using Github Knowledge base and AWS Cloudwatch
A leads CRM table to find sales prospects, research the company, and draft personalized outreach
A email brief about all the meetings
Even a daily Bengali lesson workflow that teaches me new vocab words, sent to my Gmail and tracking my progress
Big fan
n8n
1,000+ integrations is a lot to keep working. Are those maintained in house or community contributed?
Sim
@suyash_kr all maintained in house by our own agents.
i like the focus on production ready AI agents instead of simple demos. how does Sim monitor agent health and recover from failed workflow executions?
Sim
@james_carter35 great question. In logs, you're able to see the full trace span from a workflow run. If you error in that run, there's a debug from logs where the Sim agent can identify what went wrong and triage/fix the problem.
Open source is the reason I'd actually build a workflow on this instead of renting one that vanishes in a year. When a step in the middle of a run fails, does Sim let me resume from that step or does the whole thing start over? Re-running everything from the top is what made me drop the last couple orchestration tools I tried.
Sim
@chielephant great question. You can resume from a point in time in a workflow. If your workflow fails at point C, instead of re-running from point A, you can resume from C onwards.
Quick question: when an agent workflow fails in production, how do you actually debug it? Like, is there a trace/replay view, or are you digging through logs across the different integrations it touched? Anyways, congrats on the launch!!
Sim
@mshen316 thank you! Great question. You can see the full trace span then launch a debug agent on Sim that finds the issue with your workflow, solves the problem, then re-deploys your agent.
Congrats Emir!
Most agent builders just throw LLM calls at everything and the bill quietly becomes a problem at scale. How does Sim decide which steps get deterministic code versus an LLM call, is that the builder's call or does Sim suggest it
Sim
@jasnoor_singh_oberoi great question! Sim will suggest using deterministic processes for steps that don't need to be brought into an agent.
When chatting with Sim, it will build everything for you, but the way we think about it is if that step requires some nuance then you should bring an agent in.
@emirkarabeg That makes sense , using agents only where nuance is actually needed keeps the workflow lean and the costs predictable. Curious whether Sim tracks cost per workflow run over time so builders can see exactly which steps are eating the most tokens and optimize from there.
Sim
@jasnoor_singh_oberoi there's something called a "Sim" block so you can set up a workflow that triggers on every run and then keep track of the cost in tables or elsewhere.
Sim
@ridhwikvinod absolutely. You can use the human-in-the-loop node to gate agent actions behind human intervention.
@emirkarabeg The per-node flexibility between chat, canvas, and code is what other tools get wrong. Curious, which mode do most of your users end up living in?
Sim
@maurya_abhiranjan most users use the chat to workflow feature. It's very powerful! Give it a try.