Burn Your Flags: Interactive CLIs for Agents — Mark Lummus & Navinkumar Patil, PayPal

0:12Hi everyone, welcome in. My name is Mark Lumus. I'm head of developer tools at PayPal. With me I have Naveen Kumar. He's our tech lead for the developer tools team. And today we're going to talk to you a little bit about CLI. The title of our presentation is meant to be a little provocative and you'll understand why at the end of the

0:38presentation. So today we're going to talk a little bit about a specific kind of CLI, interactive CLI, and we're going to set up an exercise and we're going to give you for those of you who wish to participate, this is a workshop after all. We'll give you a CLI that you can make work better in an Agentic workflow. So that's the purpose of this workshop today. So we're going to give you plenty of time. We'll talk for a few minutes. Try to keep the talking to a minimum and then we'll get

1:19you started. Now it's kind of interesting. I think someone said what's old is new. When I started my career long time ago, I have gray hair. Everything was a CLI. Everything was a command line interface. Any of you remember working with MS DOSs before we had Microsoft Windows? There you go. My first job out of college, I was designing embedded systems. And so you would connect to a computer over a serial port and you would pull up a VT100 compatible terminal and you would

2:02start typing. And that was your CLI. That was the the the way you interfaced with the computer. So with today CLIs have kind of had a resurgence I guess you know with the maybe it was clawed code that really made them much more popular and now we have codecs um and so a lot of people are are adding CLI uh tools so that it's easier to access the capabilities that they want to expose to an agent. Now, with interactive CLI, this is why we're here today with what we want to talk about. Um, agents shell out to Bash constantly, and that's

2:45good. But if they run an interactive CLI, that may be bad because not all harnesses handle interaction very well. And if they don't handle it very well, they'll fail quietly. You won't know. No errors, no nothing. But why do we care? Interactive CLIs are great because the next question can emerge based on what way you answer a previous

3:17question. Flags multiply if you try to create flags that predict all the possible flows. The choices are contextual and they can also be responsive to what's happening in an environment. So if your CLI is calling an API and getting a response and then the question comes up based on what the API returns, that's really really challenging to handle with flags and the guard rails can live in the

3:50interactive flow. So here's an example over here on the on the left. We see a a sample CLI. It's interactive. The CLI's opened an interactive prompt, an error key prompt. The human sees it. The human can use the arrow keys, but the agent doesn't see it. The agent sees a redraw loop, not a question. and the harness loses the UI

4:26state. So here's the failure mode. It's silent and invisible. So the common fix will just add flags. And flags are fine for simple use cases. You have uh you know what the you know what the flows are up front. It's a single pass. All the options are independent. Great great use case for a a a simple flag. But when the answers change based on the context or they're changing based on reactions to real time events, that's when it becomes a problem. You really can't use

5:14flags for those situations. Now, an agent is not like an automation script. An automation script knows nothing. All of the decisions are pre-baked up front. The agent can reason. It can react. It can ask. It can retry. It can back up. And most importantly, an agent can walk a decision tree if you provide provide one. You can't do

5:49that with flags. So we already have a model today for what's happening here. It's called accessibility. And so if you map what we do for humans to what we need to do for agents, then the solutions become apparent. It's the same discipline with a new reader. So here's the here's the challenge. How might we keep the guard rails and the guidance and stop pretending that agents and humans have the same abilities? Now, I'm not going to answer this question. That's the whole purpose

6:35of this workshop. So, here's the challenge. We've got a CLI. We call it Bris Barista 9000. It's going to take coffee orders and it's going to fail when you try to run it from an agent because it's interactive. And if you choose to participate in the challenge, the winner will win a Mac Mini.

7:12Walk walk away with it today. It's in that bag right there. [laughter] That was a challenge in and of itself getting a Mac Mini. I'll be straight up. Okay. Now, [clears throat] simple rules. We're going to give you a CLI. You make changes to that CLI, run it through an agent, and it's going to send some information

7:42up to our server. And then it's going to update a leaderboard. And we'll put put the leaderboard up in a moment. We don't have two inputs, so we're going to change the slide deck out for the leaderboard so you can see it. Now, here's Naveen. He's going to talk you through this. Thank you, Mark. All right.

8:05Cool. Yeah. Uh I think it's an exciting assignment for everybody and this topic is very near and dear to me but uh keeping things aside Mark are we getting any coffee after we build this [laughter] I hope so if we're successful okay cool so yeah let me uh before we start into um the assignment I want to take to a journey right uh when I started my engineering career I started to play with ids. I started to use Eclipse because I was primarily using

8:44Java. And as time went by, moved into Intelligj uh Jet Brains. It was amazing. Looking back, five or six years behind uh things started to evolve. there were new ids in the market especially Microsoft VS code which gave birth to a lot of u other ids as well. So if you look right now Microsoft had its own VS code editor but later on new AI id started to pop out like cursor

9:22windsurf to name a few. In all these journeys, CLIs were constant, right? At some point, I thought, okay, you know, CLIs are having a slow death of their own. Maybe they are not going to come back. But, you know, uh I I I actually like to see this hangover movie dialogue that um you know, all all the four friends are in the car and they say, "Hey, we are back." Imagine CLI seeing that to each other. And in the world of AI, they are actually VC, right? Whoever bought it, yeah, I don't know. But the whole story is now the CLI have changed. And who is

10:05responsible for that? Agents, right? So this workshop is primarily focusing on agents, your CLIs. And this is going to be a hands-on exercise. There are rules to it. There are no rules to it. So feel free to hack as much as possible and you know the prize is here. Um so yeah we have maybe uh ven if I can get the laptop. So

10:36we have couple of things. So we have yeah um so we have the repo which is PayPal cafe. It has the CLI that you can actually download. That's the barebone CLI. Now, it's not going to be that easy uh for a Mac Mini. Yeah. Uh so, you will get some initial commands with it. Uh play around with it. Register yourself. Uh provide your username, whatever you like. Um your nicknames, anything, and try to brew a coffee out of it. Okay, that's that's the goal. And in this whole exercise, we want you to also be innovative in your approaches and going forward, it's going to get

11:22interesting with agents using the CLI. So think it from that perspective. I change this. I just change my laptops here. Now during the during the session, we're we're not starting you out with any hints. Once we feel like enough people have gotten the the repo installed, can run the the CLI as is, then maybe every 15

11:56or 20 minutes, we'll share a good idea. Now, I'm not going to call it a best practice. I'm just going to call it a good idea because I feel like we're early enough in the journey here where we don't know what the best practices are. We're kind of feeling them out now. They're good ideas. I'm also hoping that at the end we'll hear some great ideas from you in the audience so we can share. So just keep that in mind. We're

12:31we're all learning. This is a journey. We'll come back to that towards the end.

12:46Is it not working?

12:52Give us a couple of minutes. I think we'll get the technical issues resolved.

13:13seems like people are actually using it. So on the right side you will actually see get CLI and um if you see PayPal cafe/ rules that's where you will have all the rules outlined to it. Feel free to start working on the CLI till we figure it out. Okay.

13:53Do we have the Europe? Oh, is it that one?

14:13Yeah. Hey, there you go. Nice.

14:20Awesome. Thank you. Thank you so much. Hey Cool. So you can see this is Oh, we do see some signings. Okay. So on the right side you will see get CLI. You can download that and I hope you guys can see it. It's at the bottom right. And there are some rules here. You can click on these rules and it will pop out

14:47some rules.

15:00So, we'll probably take around about 25 to 30 minutes. Um, and in between we'll interrupt with more slides and make it interesting. [laughter] Where's the laptop for the other slides? Venode's got it. Okay, that's fine. and we're here to help. If you're having trouble, please raise your hand. We'll try to assist you as best we can.

15:52a little bit about the models. Don't use models.

16:10Now, we had a little bit of a debate internally. There are some great models out there. The interesting thing about this challenge, if you use the highest thinking mode on the bleeding edge LLMs, you can probably brute way brute force your way through this. But I feel like in the current climate, teams are starting to think about their token budget. And so you don't necessarily want to waste your highinking tokens on running a CLI tool. So the real challenge is can you make Haik coup or sonnet or something at that level run your CLI? We know you can do it with the highest. Can you do it with

17:05something that's somewhere in the middle that's faster and cheaper? That's the That's the interesting challenge if you if you want to take it on. Sounds fun. Yeah. Awesome.

17:56Since we are on the coffee topic, uh Mark, were you aware that San Francisco City has the best bakeries in the entire United States? Were you aware about that fact? I was not aware of that. Yeah, you should definitely. Go on. Yeah. Go on, tell me more. Um, I have I've done some bakery crawls uh around in the city and they are so fun. Like you should definitely check

18:21out all the amazing bakeries out here. Okay. Yeah. Any favorites? Butter and crumble. My favorite one. Although I couldn't go there. [laughter]

18:38Awesome. So as of now we have J Gray Codex at the top. So guys please catch up with him or her

21:03So with the init command, you could actually register your names. I hope some of you have figured that out.

22:06Do you want to talk about the first

22:45You might have to think about

24:47Once I plug it in, I

25:44[sighs]

25:51Go ahead. Okay, cool. Um, let's move on to some presentations. Meanwhile, you can start working. I mean, you'll continue working with the CLI that you have. But as as a first hint, you know, it's it's a good idea to start using T-Max. How many of you know about T-Max here? Okay, quite a fair amount of audience out here. Um, so yeah u in short start with running T-Max

26:20and um start by putting help command. Now, help is really important because every AI agent in today's world relies on the help command before it even starts using that command. [laughter] So,

26:45yeah, send keys and capture pain gets you far. Now, T-Max actually um for those who actually don't know about it is like a multiple you could actually use multiple terminal sessions uh with the T-Max and it's like a split pane feature that you could leverage with T-Max. So, with this example, you can see here um I mean the screen is very short for me. So, let me just zoom in a little bit. Yeah, T-Max D. Now, what this flag does is it detaches the entire uh CLI and puts it under a different emox instance all together for

27:28[laughter] you. So you could see size uh T-max capture pane like I said you could actually have split panes in T-maxes. So you could actually take care of u working around with um in in the CLI and uh that's one of those cool features that can help your agents perform lot of activities. Um, think of

27:58it when you want to run multiple agents. You could actually spin up different sessions and T-Max actually takes a log of those things where it knows what are you working on and resumes those sessions whenever it's needed. So, it's actually helpful for agents to communicate and start communicating when they have multiple sessions open. And these are some long running tasks that

28:28you could actually run inside T-Max. [snorts] Second good idea is IPC site channels. So like I mentioned before, T-Max was a good upgrade. So instead of doing screen scraping, which T-Max actually does um for visual in inference, [laughter] you could start using side channels. Now [snorts] site channels would help you define your arrow keys that you have and help you understand and I'll go in the next slide uh how it works but the agent should know what is the output JSON now this becomes really critical in the entire talk is output JSONs and Asians want that since we have multiple personalities now earlier we used to

29:22only cater to human beings now we have agents. So think of both these personas so that your CLI can actually take advantage of both these use cases. So site channel for those who don't know about it let me explain to you in in simple words think of it like adding a REST API to your web application and the website gives humans a visual interfere

29:50uh interface. The API gives you a machine structured interface right so think of side channel as exactly the same that's one of those analogies that I can refer read state send input as a data [clears throat] so we have the bista brew hyphen agent now this this is a command that will help you run

30:20your CLI with background agents, right? Um, you want your agents to be running in the background and uh you put all of these commands, they are going to help you try using it in your current CLI. See if you are able to um make some progress in the barista application that is out there for in

30:44your laptops. Now, there are a couple of things that you could actually provide as an example out here. You can see barista [clears throat] brew ask and then there's a bunch of information out there. Oh, what is it? Okay, fields then small, large, medium, maybe the sizes of the coffee and yeah, default as large. What does that even mean? That's input data, right? So all you have to do is feed in this input data so that agent actually knows that and you got to do it

31:17in machine readable formats. So this is where um that thing comes in play. So don't just tell the agent what the human sees, okay? Think it out of the box. What are the agents going to think? They have different skill sets and you have to start leveraging those skill sets. Same prompt with a different brain. Now, [clears throat] so on the left side you see I was talking about different personas. One is the human beings and

31:53the other one is the agents. The CLI is the same but when you look at the way it is structured human beings want set of options but on the other hand you have agents wherein you could provide all this information in one single input file. [snorts] Okay. So this is where we call this as context injection comes in play. You provide context in such a way that let me take an example. You you are actually low on oat milk. Okay. And uh you have

32:34only two gallons of uh oat milk left. Tell your agent what kind of information it needs to ask the user. confirm it if if two ounces are good enough. Do you want me to pick a backup for you? This information should be provided using context in injection as a technique and you can leverage this in

33:00the CLI that you are actually building. Try using it. Maybe you'll be on the highest on the leaderboard.

33:12So we started a journey from T-Max which is basically screen scraping to injecting skills. So T-Max is low effort. I think a lot of you might have tried it. But this is where site channels [snorts] also will help you in providing [clears throat] good um sort of feedback to your agents and context injection will provide you those different scenarios that you can think about which doesn't happen in the

33:43human case. So yeah, keep pushing your scores.

33:54You want to show this? Yeah.

34:14It does take some time. There you go. Okay, [snorts] cool. We do see a lot of traffic out here. [clears throat] [laughter]

34:30Oh, somebody is really close to 5,000. Is it bank? Okay. [clears throat]

34:53Any questions so far? Anybody wants to get it answered? Any queries? Sorry. [laughter] Okay, let me repeat that question to you. [clears throat] What happens if multiple people reach a score of 5,000? Mark, you want to take that? So, the the idea was we would look at score and if there's a tie, we would look at which one took the least amount of time. Now, based on the resolution of this, I see several that are that have completed three of three in zero

35:38seconds. I see [laughter] a bunch of these that have completed it in zero seconds. So, I need to consult with someone because that's not supposed to be possible. But the idea is that we would look at the high score the the score first and then the time it takes to respond second. So that an accurate response returned quickly would be biased over an

36:10accurate response returned slowly.

36:26So we have only one for now. Okay, sorry. We have only one. eventually comes to

36:47this is the bottom of the leaderboard. Nicholas [snorts] game up. [clears throat]

37:090 second.

37:37Do you want to wait two more minutes? We can open it up ideas how engaged they are.

38:07Did we have

38:23[clears throat] In just a few minutes, we'll open up the floor for some idea sharing. So, I'm I'm hoping that we'll hear some great ideas that go above and beyond our good ideas because I know that there's some out there.

38:58Mark, were you expecting so many people to be in the 4,000? Yes, absolutely. At this conference? Absolutely. Awesome.

39:14Were you not? No, I was. [laughter]

39:52What do you think? Anybody can make it to 5,000? I don't know. We'll hold it open. [laughter] Why don't we open the floor up now? Yeah, sure. We'd love to hear ideas. So, did anybody in the room come up with other ideas that were able to get them to such a high score so quickly?

40:21Nobody wants to leave the desk. [laughter]

40:35Oh, we have Yes.

40:53Let me let me come over to you [clears throat] because I can barely hear you.

41:05Okay. it it's a very easy to game benchmark because the only thing that matters is you fulfill one order within like small like a very small latency. So if you do a deterministic parser um it which defeats the spirit of this challenge entirely but you deterministic parser and you have something like really close to the server you can get the latency down uh really quick if you just brute

41:31force it. Okay, which is that what you did? That's what I'm doing right now. Okay. All right. Now you said something interesting the the deterministic parser that's running in your CLI. Okay. I actually like the idea of the determinism in the CLI. And [clears throat] the reason is that if the CLI is a tool to be used by an LLM, then you absolutely want it to be deterministic. The LLM is the non-deterministic player here. We want the CLI to be as someone described it a small sharp instrument. Should be very very focused on what it does. And every time you give it a command, you want it

42:27to come back with the same response. So you don't want to build an agent into the CLI and then hand that CLI off to another agent because you don't know what you're going to get.

42:46Any other interesting ideas? Obviously we a lot of people have figured out how to game the system. [laughter] Where there's a Mac Mini, there's a way, I guess. Yeah. [laughter]

43:16Wait

43:25five minutes. Five minutes. The score hasn't changed in a while before the site crashes.

43:42Did you do refresh?

43:57[cough] [clears throat]

44:41Why does it say reconnecting? Oh, there we go. Okay. See, the network is a little laggy. The network is a little laggy out here. A lot of lot of computers. Sounds good. Crash.

45:35And we're frozen right now. [clears throat]

45:44Here we go. No change in the results. Okay.

46:11Do we want to wait a few more minutes or call it? Yeah, five minutes. Five minutes. Okay. You want to bring the PPD to PPD for the closing arguments.

46:28We're going to give it about five more minutes. Yeah. And then we'll call it. Where's Bon? Where's Bonk? Raise your hand. Who is Bon? Okay, we have something. All right. Big smile. Big smile. [laughter] Now, we do want to hear how you did it. So once once we call it, then we'll we'll we'll we'll let you explain what

46:51you did. I'd love to hear. [laughter]

47:15I need to go over here. Yeah, hold on. Sorry. I should have asked for another I should have asked for another microphone for the room for questions.

47:30Um, yeah. So, Bonk is just a an agent uh thing built on top of cloud agent SDK. Um, it built the whole thing. Prior to this, I already had a sort of eval bench skill that will create sort of an environment and um optimize. So, it basically ended up building a uh deterministic CLI solver and then now it's just

47:56running on a T-m slamming your APIs. Okay. Yeah. All right. aso. I think I got lucky because I hit it at one point at like 29 milliseconds. Uh probably because we're in the same region. Okay. It's just a network latency, right? And this is all done on claude uh claude agent SDK. Okay. Just driving

48:15it through Slack. No, which model? Opus 4.8. Okay. Yeah. Did you try it with any other models for the build uh for building the CLI or for for your a for your agent? How would we do that? The CLI is completely deterministic. Sure. Sure. So, so the agent built the CLI and is just running

48:35it on T-Max now. Okay. Yeah. Awesome. Yeah. Congrats.

48:46Going to go to the next one. Danny. Who's Danny here?

48:58You see last one.

49:11[clears throat] What do we want to know? Yeah. How'd you build it? Yeah. So, I don't know anything about uh coding at all. I'm I'm using uh I'm basically a Vibe coder. I have a couple agents and I just said, "Hey, here's the problem. Read it and then fix it and fix it." So, I just have Yeah. Cloud code up

49:32on uh VSC. Have you ever built a CLI before? Uh no. I I saw a couple hours ago that obviously there was a prize to be won. So, I got in and I said, "Hey, [laughter] uh figure this out. Explain it to me like I'm, you know, like I don't know anything." And then explain like I'm

49:51five. Yeah, I I I don't know. So, and then we came up with uh yeah, we came up with some good results and I said, "Hey, we need to make it faster and give me some suggestions and yeah, seriously." So, I I guess [snorts] we have uh two scripts running and the first one got the uh 49.98 and then I said, "Hey, make a copy and give me some suggestions for how we

50:15can get the 49.99." Right. Did you get any suggestions? Uh it's this agent's pretty automated. So I just say like hey here's the start here's the end give me a couple you know questions at the beginning if you need it but then fix the problems so I don't have to deal with it kind of thing. So sorry that's not a very good No it's good. I'm I'm sure a lot of people are wondering like writing a CLI is that something that you would ever do or would you ask your agent to do it for you? So clearly we have many people in the room and just going to point Claude

50:56or Codeex at this and say build a CLI, make it fast, make it deterministic. And those are the three ideas, right? Okay. You want to change the slide?

51:36There it is.

51:51[clears throat] So, we talked about all of our suggestions. We heard some ideas. The predominant idea was let your agent figure it out for you. I love that idea. Um, anything else before we close it out? All right, there you go. Takeaway for us based on our instructions, our recommendations. Give it good context, give it a side channel, and tell it to use T-Mox. Those are

52:31three good ideas to start with. Thanks everyone. Bonk, you want to come on up? [applause] We still have Monk as the winner, right? Yeah. Okay. No, no, we called it. We called it five minutes ago. Okay. Yeah. Yeah. I'm not gonna change [clears throat] I'm not going to change it. Yeah. We We called it.

52:55Awesome. [applause] Let us [clears throat] We'll get We'll just get a picture, you know, social media. That's right.

53:14It's a real Mac Mini. It's a real Mac. Oh my god, these exist. [laughter] All right, awesome. Where'd it come?

53:40[music]