Clarifying Looping Agent Tasks for Meeting Attendee Research

Rex H. · 2025-04-21 21:45:28.657972+00

do I need to loop agent tasks so that the exit condition runs through ALL meeting attendees before sending the slack message? even though I set the exit condition for the agent to exit once ALL attendees were researched, it still is slacking me after the first one, then running through the rest, which means I got three slack messages summarizing: 1. The first attendee 2. The second attendee 3. All the attendees

Clarifying Looping Agent Tasks for Meeting Attendee Research | Lindy Community

Marvin A.
·
·
yeah the LLM might make mistakes here → more robust to use a quick loop
Rex H.
·
·
all good… I had wondered if that month be necessary… what’s the best way to loop an agent then? got any tips?
Rex H.
·
·
and where does the “swarm” come into play for these kinds of workflows?
Rex H.
·
·
also, how would one add an existing agent into a loop?
Loading attachments
Rex H.
·
·
apologies again for the 20 questions, Marvin A.! 🙏
Marvin A.
·
·
Loop = Swarm = Agents working in parallel 🙂 so as soon as you have an array of elements to go through I’d usually go for looping with some exceptions
Marvin A.
·
·
you can’t copy and paste it into the loop at the moment
Rex H.
·
·
got it… all good! any tips on enter and exit prompts to have the agent loop through and properly grab all the necessary items and pass them through the next set of actions? looping agents is new to me here on Lindy… thanks!
👀1
✅1
Marvin A.
·
·
not sure I understand the question :S are we talking about the AI Agent step? Or Looping?
Rex H.
·
·
…both… in this Lindy, what’s the best way to loop an agent to run research on all meeting attendees to then get that full list of researched attendees via slack
Michael S.
·
·
i think you need to have your agent inside the loop then the slack message prompt be output from the loop no? That's what you had in your presentation wasn't it?
Rex H.
·
·
with a platform like Zapier or Make, there’s no concept of looping an agent and keeping all its output in the context window for a future single output… you’d have to instead load into Google Sheets or something like that
Michael S.
·
·
in make, you'd call a scenario then use an iterator/aggregator and return all that data via webhook response (or scenario output, I forget what they call it)
Michael S.
·
·
similar concept here, the enter loop is your iterator, exit loop is your aggregator
Rex H.
·
·
and the legendary Michael S. enters the chat! good call… I think that’s what I’m wondering on the aggregator
1

46 comments