Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
Introducing Subagents on Omnara Managed Agents transcript
Omnara · @OmnaraAI
Published September 22, 20263:0414 views
Transcript analysisComputed from the caption text
Words
462
Runtime
3:04
Speaking pace
151wpm
Reading time
2min
151 words per minute, below the 160 25th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
Hey folks, I want to just start showing off some parts of the new version of Amnar here from now on. We recently launched sub aents in Nara. So if you've never seen this version of before, uh we've kind of started building a managed agent API which lets you basically build all the agent experience parts without having to deal with the complicated backend parts of of building an agent. And one more piece of
76 words, the words spoken in the first 30 seconds at 151 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 31 |
| Average words per sentence | 14.9 |
| Longest sentence | 59 words |
| Questions asked | 1 |
| Sentences containing a number | 0 |
Most used terms
- agent16
- sub14
- uh7
- aent5
- sub aent5
- aents4
- lets4
- sub aents4
- ask3
- close3
- cool3
- parent3
Filler phrases
14 in total: uh 7 · kind of 3 · like 2 · actually 1 · basically 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
Audit this video's script
Run the check on the words above: where attention is likely to drop, with a rewrite for each weak line. The free check shows the scores and the one issue costing the most.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
No Script X-ray for this video: YouTube shows a Most replayed graph only once a video has enough views.
Transcript
Hey folks, I want to just start showing off some parts of the new version of Amnar here from now on. We recently launched sub aents in Nara. So if you've never seen this version of before, uh we've kind of started building a managed agent API which lets you basically build all the agent experience parts without having to deal with the complicated backend parts of of building an agent. And one more piece of functionality that we have is this concept of agent profiles which essentially are just reusable configs for an agent.
And this lets you set the model. It lets you set sandboxes. And now it lets you set sub aents. And the cool thing about how we've implemented sub aents is that sub aents are really just a reference to another agent profile. And I've already created one example sub aent here which is just a sub aent with access to linear. And I'm going to kick off this parent agent which has access to that sub aent. And we're going to ask it to fetch my linear tickets.
I can interact through the API but today we're just going to interact through the chat. So let me just ask it. And that's going to go ahead and spawn a sub agent. You can see it in the tools list and in the sidebar. And you can see that this is just a normal agent uh like any other uh agent, but it's being used by that parent agent, which is very cool. And I'm going to come back in a second once it completes fetching these uh tickets.
Awesome. So it looks like it came back with some results. Those results automatically get sent uh to the parent agent. And now I'm going to ask it to close out one of these statements. So can you close out this ticket? And the cool thing about uh how we've built this is we we've tried to think about the complicated concurrency behavior and interactional behaviors with sub agents which means that this sub aent is doing a write action and those kind of write actions and specifically actions any action that needs permissions gets propagated up to the main agent.
So this is actually a request from the sub agent. I can submit this interaction from the main agent and the sub agent is just making those changes. Uh, and we've got another one. If I just allow it to do those things, it will execute and close out that ticket. And sub aent is still running. And now it's completed and it's it's kind of done those tasks. But yeah, that's that's sub agents from NAR. We hope you you test it out and use it.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Working on a video like this one?
Free tools for your own script: paste a draft and see where it stands before you record it.
Script Audit
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Hook Analyzer
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Policy Pre-Flight
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Channel Skill Generator
Read this channel's public videos and transcripts, and download a writing brief for it.