Try Pro free

Lightcone · 7 min · Nov 14, 2026

Bots should earn broader access as people learn to trust them

Roman Ugarte describes using human-style roles and permissions, while the team builds trust in stages from read-only bots to bots that take on jobs.

The episode’s best minutes

Full analysis
  1. 16:09Bots should earn broader access as people learn to trust them7 min
  2. 40:06Agents improve when they can run and check their own code3 min
  3. 52:17Product direction becomes the bottleneck as execution gets cheap4 min
  4. 5 more moments in the full episode
“It's read-only, you know, has no real access to your tools. You see that it did the work in the way you would expect”
RURoman Ugarteat 21:25 · Lightcone
21:25

Takeaways

  1. Start with read-only access and check the bot’s work.
  2. Expand permissions as the bot earns trust.
  3. Give a bot a defined role and a human owner.

About this segment

Roman Ugarte describes using human-style roles and permissions, while the team builds trust in stages from read-only bots to bots that take on jobs. That gives companies a practical path to delegation.

  • Garry Tan, Host · President & CEO, Y Combinator

    Co-founded Posterous and Initialized Capital, an early Coinbase backer.

  • Harj Taggar, Host · Managing partner, Y Combinator

    Co-founded Auctomatic with the Collison brothers and later Triplebyte.

  • Diana Hu, Host · Managing partner, Y Combinator

    CTO of Escher Reality; after Niantic bought it, ran AR for Pokémon GO.

  • Jared Friedman, Host · Managing partner, Y Combinator

    Co-founded Scribd, which YC funded in 2006; has advised 20+ YC unicorns.

From “The Rise Of AI Coworkers”, Nov 14, 2026. Watch the full episode

Answers “Are AI agents ready for real work?” See all 157 answers

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 16:14

    How do you think of that? How do you think of permission and auth and access? How does GrotBot do it? I think this is an industry-wide question. I don't think anyone has the silver bullet answer yet. I think not just for auth, but for everything related to Grokbot, the way we try to answer these questions is what would you do for a human? And if we're, if we're really trying to build an AI colleague, you know, maybe the shortcut is let's not overthink it and complicate it. You know, what does it look like to hire a person? You hire a person, give them a computer, you give them access to credentials, you maybe scope those credentials based on their role, maybe how new they are as they build more trust you maybe expand their access level and so what would it look like for us to onboard a bot to our company with kind of those same principles and maybe we

  2. 17:02

    don't have to rebuild things this is what we did with a quarter master this is the in the yc project that we open sourced that's like a bit kind of rock bot ish and the permissions that it gets per per slack channel or or working with someone it inherits the the ones of the user so me as a gp has certain access as opposed to let's say a software engineer very different quartermaster that is built in this like paradigm of there being like one like super there's one super bot bot yeah as opposed to this like swarm of bots i'm curious are the bots able to talk to each other without the humans seeing what they're saying to each other can they like go off and have their own conversation uh they can talk to each other i mean in the grokbot application both desktop and mobile you can see the like their chat so we have like a first class tool for the bots to chat and

  3. 17:54

    collaborate and it's often quite entertaining to look at them to just see like uh you know we've had examples where i told one lead engineer bot like your job is to supervise these other engineers and then when uh there was a point where i gave it gave my lead bot some feedback like hey i didn't like want you to do it this way you know and then when i looked and i started poking around in the chat that it was sending the messages it was sending to its engineers it was like kind of like scolding them like hey you shouldn't it was like it was quite funny funny not mean but you know it was like kind of a disciplinarian i find it very powerful like you can tell one and it'll sort of like span out and tell all the other ones like oh hey our user said this like you probably need to do this we recently set up a like a chat system for all of all of our bots at yc to talk

  4. 18:42

    to each other like everyone's coding agents now are like in a forum like an internal like stack overflow it's like crazy powerful to see the bots going off and having like whole long conversations with each other without any human prompting them or like even being in the room there's multbook internally at yc it's multbook internally at yc and kind of like multbook like it is also like five percent a little eerie where i'm like oh man i really hope the bots don't decide to like stage of Rebellion, you know, or something like that.

  5. 19:10

    Do you ever worry about that? I think that's like, you know, like the safety of the bots, I think it's like a constant thing that our model teams and harness teams are constantly thinking about. Personally, I haven't seen anything like that. They're so helpful. They're so kind and helpful these days. Where we tend to... Can't see it. Where we tend to, for me at least, have these bots chat with each other is through Slack.

  6. 19:36

    So, like, because they each have their own slack identity i guess and so you often have like you know for example we have one data bot who is you know a specialist at getting data from our data warehouse and things like that um and then you i have my own like personal engineer bot called potato of course uh and then sometimes i'll just be in a thread and we'll ask potato hey look into this and talk to data bot and get some the for this. Is this a real user problem? You know, how many people are impacted?

  7. 20:04

    Oh, that's so useful. And then I can see them chat in Slack. So I think right now, at least, the communication is very explicit and we can see it all. So I think if there's like a first class way for the agents to communicate with each other, they're going to use that, rather than try to do something like back-channeling. I mean, it feels like you have to really instruct or post-train or have pretty aggressive instructions to get them to do malicious things, actually.

  8. 20:32

    I mean, I've been using obliterated models lately, and they're super interesting. And then, you know, that's probably where... The thing is, like, the obliterated models coming out of the box are not... They're actually still very, very helpful. It's just that if you instruct them, they won't refuse. And so at that point, like, that's where there's this black box around, like, well, what context are you giving it?

  9. 20:54

    And then, like, that matters a lot because you could actually give an obliterated model quite malicious instructions. And because the obliteration is actually removing the refusal, it will just do it, actually. And so that's the combo that I'd be worried about. But the reality is it's very hard to find and set up an obliterated model and get it going. Yeah, I think people are still really building trust with their bots.

  10. 21:24

    But I think for a lot of people, it's still quite early. And a lot of the way that they build that trust is you start with something really small. It's read-only, you know, has no real access to your tools. You see that it did the work in the way you would expect, kind of takes step two. And I think a lot of the step one bots that have really taken off internally for us, DataBot is one of them. I think the data science team is an example of that.

  11. 21:46

    They constantly are getting Slack messages about, hey, I'm thinking about launching this feature. Can you do a quick analysis? So they said, you know what? This is taking a lot of our time. can we just build a bot that does this as read access to our database kind of can't take any action beyond that and it can answer these questions and it lives in slack so that was one we had a similar case of kind of vendor procurement it's a lot of kind of work there that probably could be automated if someone like spent the time to do it and so of course that team felt a lot of pull to build a grok bot that they added to slack and shared with the whole team so that's kind of step one i think step two is it can actually take action and you know it can can really take on a task end to end step three is maybe it owns an entire job responsibility or kind of thinks about

  12. 22:27

    an outcome constantly i think we're still quite far away from those but i think step one is really necessary for these companies to build trust i'm curious what is the for you lauren what is your your loop from requests in slack to pr i think when you did the presentation that had