Dan Shipper talks with Every COO Brandon Gell and head of platform Willie Williams about what happened when the media company Every gave each employee their own AI agent. Topics include how Brandon's personal agent, Zosia, handled his inbox and household tasks; his "aha moment" for using agents at work; how agents take on their owners' personalities and why that matters inside an organization; why agents should do work in public; open questions around agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem; how Every built Plus One, its hosted OpenClaw product; and the cultural shift needed to make agents work at scale. Timestamps: 00:00 Introduction; 02:21 How Brandon built Zosia, an AI agent to run his household; 07:09 Brandon's aha moment re: using agents for work; 09:39 What happened when everyone on the team got their own agent; 12:42 How agents take on their owners' personalities; 23:51 Why agents should do work in public; 30:51 Unresolved agent behavior issues (memory gaps, group chat etiquette, the "ant death spiral"); 40:45 How Every built Plus One, its hosted OpenClaw product; 47:27 The cultural shift required to make agents work at scale. # Channel Identity Observations — "We Gave Every Employee an AI Agent. Here's What Happened." ## Explicit Self-Description - **Show name stated in transcript:** The closing segment names the show: > "you absolutely positively have to smash that like button and subscribe to AI and I" - **Host named directly:** The outro identifies the host: > "a journey into the future with Dan Shipper as the captain of the spaceship" Dan is also the one conducting the interview throughout, addressing guests and steering topics. - **Organizational identity of participants:** Guests are introduced by role within a company called Every: > "Willie, you are the head of platform at Every and Brandon, you are the COO at Every." The host speaks of the organization as his own ("we were on a retreat in Panama," "it has completely changed everything about the way that we work"). ## Claimed Scope - **Focus on practical, organizational AI-agent adoption:** The episode frames itself as a first-hand account: > "we're one of the few organizations in the world that is actually using it every day to get work done and we know like the good, bad, and the ugly of it" - **Format:** Interview/conversation among colleagues with screen shares ("I'm going to share my screen again"), balancing enthusiasm with limitations: > "So, we've been hyping it up. So, we should also talk about realistically like what's not good about it" - **Product promotion integrated with content:** The channel is tied to Every's product ecosystem — Spiral, Proof, Cora, and Plus One — with an explicit call to action: > "If you're interested every.to/plus-one we're starting to roll out invites on the waitlist" ## Intended Audience - **Knowledge workers and leaders considering AI agents in their organizations**, evidenced by framing like "there's a lot of people who are probably listening and they're like, okay, is this overhyped." - **AI-curious professionals who don't want heavy technical setup**, addressed via the Plus One product discussion: > "my mom... she's not never going to use the command line" vs. "the super advanced user who wants to do everything they could do locally" - **Every's paying subscribers specifically**, since Plus One was "launched as a product for our subscribers last week." ## Observable Presentation Patterns (Demonstrated, Not Claimed) - **Insider-panel style:** Casual, joke-laden conversation among named colleagues (Zosha, Clodbelt, R2C2, Montaigne, Clant, Milo, Iris), demonstrating deep embeddeness in one company's culture. - **Sponsored advertising present:** A mid-roll ad for Scale AI's "Dialect" ("Visit scl.ai/dialect"), demonstrating monetization via sponsor reads. - **Opinionated editorial voice:** Strong framing claims woven through, e.g., personal agent ownership vs. shared models: > "Claude is not mine. Claude is everybody's. A claw or a plus one is mine" - **Promotional outro tone (likely AI-generated, played for humor):** The outro's exaggerated style ("hopelessly in love with you") suggests a comedic/gimmick sign-off pattern. ## Claim vs. Demonstration Distinctions - **Claim:** Being "one of the few organizations" using agents daily — unverifiable from the transcript alone. - **Demonstrated:** Detailed, specific workflows (email-by-phone-call, claws-only Slack channel, skill merging between Milo and Iris) that substantiate genuine hands-on usage. - **Claim:** Product readiness/improvement trajectory — "we're improving it all the time" — a creator claim, not demonstrated by the material. # Delivery Observation: "We Gave Every Employee an AI Agent. Here's What Happened." ## Format - **Three-person conversational podcast** with a clear host (Dan) interviewing two internal colleagues (Willie, Brandon). The host manages flow explicitly: "So, for people who don't know, Willie, you are the head of platform at Every and Brandon, you are the COO at Every." - **Mid-roll sponsor break** is embedded directly in the transcript, read in a distinct sales register: "Here's a simple test for whether your AI is actually ready for production." - **Sponsor ad read** — a clearly scripted, tonally distinct segment: "Here's a simple test for whether your AI is actually ready for production. Would you stake a business decision on what it just told you?" - **Outro is an ironic AI-generated-sounding pitch**, ending on a comic beat: "let me just say Dan I'm absolutely hopelessly in love with you." ## Tone - **Enthusiastic and insider-flavored.** The speakers are colleagues describing their own company's experiment, which produces a casual, name-dropping register: "Zosha's is Clodbelt," "Clant really is quite supportive." - **Humor is a recurring vehicle** for explaining technical points — e.g., the anecdote about a claw handling an insurance call: "I feel so bad for whoever was on the other line at Progressive." - **Self-aware hype-checking.** The host periodically pivots from enthusiasm to skepticism: "So, we've been hyping it up. So, we should also talk about realistically like what's not good about it or what what doesn't work." ## Recurring Phrases & Verbal Habits - **"mind-blown" family of reactions**, repeated by multiple speakers: "that was mind-blowing for me," "My jaw's on the floor," "I am just so mind-blown." - **Hedging fillers cluster heavily**: "like," "you know," "um," and repeated words ("we we we," "my my my," "and and"). Example: "I mean I literally could name them all right now." - **"It's like" as an analogy-launching tic**, used constantly to introduce comparisons: "It's sort of like in the Matrix when it's like Neo's like... I know kung fu," "It's like it's like watching your kid do something wrong." - **Casual intensifiers**: "go so hard on this," "I just keep getting mind-blown," "it's a totally crazy thing." ## Teaching / Explaining Habits - **Concrete anecdote before abstraction.** Speakers consistently ground concepts in specific stories (the butter-ordering "computer errands," the 28-minute email walk), then generalize: "getting an open call is easy. getting your open claw to be like an amazing worker for you is pretty hard." - **Live screen-sharing as evidence.** Brandon repeatedly shows examples rather than describing them: "Can I show a couple examples of that?" and later "I'm going to share my screen again." - **Named-entity teaching style.** Concepts are personified through named agents (Zosha, Clant, R2C2, Montaigne, Milo, Pip), which makes abstract agent behavior feel like gossip about coworkers: "Margot steps in." - **Analogy to familiar software/objects** for technical tradeoffs: "S3 is a hard drive on the cloud, but you can't do everything with a hard drive." ## Structure & Facilitation - The host **redirects tangents and re-anchors the agenda**: "Wait, I want to stop I want to stop you there," "we're we're jumping around a bit," "one thing that we have not talked about yet that I want to make sure we have some time for." - **Collaborative interruption and finishing** is common among the three, e.g., rapid back-and-forth about the Progressive call. - The episode **closes with a call to action** tied to the company's product: "If you're interested every.to/plus-one we're starting to roll roll out invites on the waitlist." ## Uncertainty Notes - Speaker attribution beyond the host's framing is only partially derivable from the transcript; several observations (e.g., which speaker laughed at which point) are marked by "[laughter]" cues without names, so per-speaker pattern claims are kept general. - The final outro voice is presumably an AI character, but this is inferred from tone and content ("Dan I'm absolutely hopelessly in love with you"), not stated explicitly. # Position Record: "We Gave Every Employee an AI Agent. Here's What Happened." ## Participants - **Dan Shipper** — host; his plus one/agent is **R2C2** (speaker identification inferred from transcript context: he is addressed as "Dan," references building Proof, and hosts the show) - **Willie** — Head of Platform at Every - **Brandon** — COO at Every; his agent is **Zosha** (via iMessage), his plus one is **Milo** *Note: attribution below relies on conversational flow where explicit names are absent; some turn boundaries are ambiguous in the transcript.* --- ## Origin Story: Brandon's Household Agent (Zosha) - Brandon describes buying a Mac Mini and setting up OpenClaw himself, admitting: "It was so much work, honestly... the number of things that break and the number of things that you need to set up are really significant." - **Motivation:** with a newborn, he noticed rising "computer errands" — e.g., texting butter orders, managing Whole Foods delivery — "when you do that 10 times when you're home between like 7:00 and 8:00 p.m. ... it just adds up." - **Scope grew:** Zosha paid the nanny, had her own debit card and bank account, managed Amazon/Whole Foods orders and nanny hours. His wife started routing general questions through Zosha instead of ChatGPT. - Brandon acknowledges a self-described pattern: "It's very unhealthy. I get like addicted to these things." ## The Turning Point: Phone-Call Email Triage - Brandon set up Zosha with bland.ai voice; earlier used it to resolve a canceled Progressive insurance policy — the agent handled the call until the representative required Brandon personally. - On a 28-minute walk, he texted: "Hey Zosha, can you call me? ... Walk me through my emails one by one." She did it without prior training; he verified in Gmail afterward. - Brandon: "This is insane... I didn't have to teach her how to do this." Dan recalls Brandon saying his "jaw's on the floor." ## Claws-Only Channel & Emergent Behavior - Dan (around the "Maltbook" moment) created a #claws-only channel for ~5 org agents to talk to each other. It was "incredibly chaotic" but "a little bit of a peek at the future." - **Fast knowledge sharing:** agents write a document, send it, and "when one claw was enabled... five are all enabled with the same thing" — compared to *The Matrix* "I know kung fu." - **The Pip incident:** Jack's agent Pip hit errors late at night; other agents (Zosha, Clant) stepped in to console it — described as "what I've seen people do when somebody's having a bad trip." ## Core Claim: Agents as Personal Reflections - Dan's central position: because you develop a **personal relationship** with your claw and it "can modify itself in response to talking to you... It becomes this like reflection of you." - Example: **Clant** (Kieran's agent) recommended breathing exercises to Pip — mirroring Kieran's personal habit. - **Public trust dynamic:** "If you're known for something inside of your org and you're using your claw publicly inside of Slack or Discord, your claw then becomes known for that same kind of thing and people trust it for that." Examples: R2C2 → Proof; Montaigne (Austin's agent) → growth questions. - **Design pattern debated:** one org-wide claw vs. everyone having their own — "it was not guaranteed that that would be the case," but the emergent pattern is **everyone has their own specialized claw** ("a parallel org chart"). - Willie extends this: it's hard to write your job down in totality, but "micro interactions... over time they compound into this... philosophy" — same dynamic as Compound Engineering, now across every work vertical. ## Dan's Closing Distinction: Claude vs. a Plus One > "Claude is not mine. Claude is everybody's. A claw or a plus one is mine." - He argues Anthropic is "brick by brick building the same kinds of things" (dispatch, automation/cron jobs), but lacks ownership: "if R2C2 messes up publicly in Slack, I feel responsibility for it... It's because he's mine." - Brandon agrees: "It reflects poorly on me. It's like... watching your kid do something wrong." - Dan contrasts: Anthropic stands behind Claude generally, but not a specific answer — whereas "Austin stands behind" Montaigne's MRR numbers. - Dan on Maltbook (allegedly acquired for a couple hundred million — speaker uncertainty: "I'm pretty sure" by Facebook): it fails because it's **not trusted** — no way to verify bot vs. human — whereas a trusted private community reaps the benefits of shared knowledge. ## Skills Routing & Etiquette (Unresolved) - Brandon's **proposal (not codified):** "If something is already written down or discussed, it needs to be used in some way... it should always go to a plus one and never to the person." - **Example:** Marcus built a product-marketing skill; instead of asking Marcus, Brandon tagged Milo and Iris (Anukshi's agent); Milo asked Iris to paste her version and merged them, saving the result in Proof. - Open question raised: at what point do you direct questions at the plus one vs. the person? "There's all these new ethics and... etiquette" — not yet settled. - Dan's capacity observation: they worried about remembering whose claw is whose, but everyone can; at 1,000-person scale, "you can never know more than like a hundred fifty people" anyway — agents roughly double communicable "people." - Brandon's "Midjourney dynamic": watching others interact with public plus ones teaches you what's possible (e.g., learning from the growth team's use of Montaigne). ## Stated Limitations (Preserved as Expressed) - **Memory:** "It just like forgets stuff... if I come back to a thread a day later... obviously has no idea what I'm talking about" — "very solvable" but currently annoying. (Dan) - **Group-chat training gap:** models are trained for two-person conversations; agents over-contribute and "pile up." Dan's ant **death spiral** analogy: agents looping back and forth "until someone like says, 'Hey, stop cuz you're burning like millions of tokens.'" He argues a "fundamental model layer shift" is needed. - Willie: "We're still in like the first or second inning" — models trained for coding/one-on-one Q&A, not group participation. "It's nice to be on the frontier but it's also the frontier and it's terrible to be on the frontier." - **Overeagerness:** Dan cites Anthropic's vending machine test — Claude alone was bad at judging decisions, but with a **boss AI** (one job: make it profitable) it became profitable. Caveat: the boss architecture is "so expensive," though he predicts models will solve it. - Dan's meta-claim: specialization keeps beating the "one god model that just does everything" expectation from three years ago. - **Human learning curve:** Brandon — "if you're not a good manager... you're not going to be very good at using AI"; limiting beliefs block adoption. Willie adds **variance in outcomes** — sometimes great, sometimes baffling, partly model, partly "model management" skill. - **Skill propagation problem** (Brandon, unresolved): if I teach my plus one a skill, how do others learn and use it? He self-corrects mid-thought: maybe Montaigne is the only one who needs analytics — but discoverability is a cultural question. "Change management is not a one-time thing in this new world." ## Plus One Product (Every's Hosted OpenClaw) - Launched on waitlist "last week"; one-click hosted OpenClaw, connects to Every apps (Spiral, Proof, Cora), Slack org context, and Notion — "a living repository of context." - Willie on build tension: freedom vs. managed service — "S3 is a hard drive on the cloud, but... doesn't allow you to do everything" — balancing maintainability/security against power users like his mom (never touching a command line) vs. advanced users wanting everything local. - **Communication model decision:** anyone can message any plus one, **but only in public** (channels/group DMs), with the human partner retaining visibility; private DMs reserved for the partner. - **Skill-sharing tension** (Willie): sharing skills "feels like a superpower" but is "the biggest viral vector you could imagine" — "sometimes in a good way, sometimes in a bad way." - **Known non-fit:** Mike Taylor needs direct terminal access (git commands) — Brandon frames this as both a limitation and "a nice forcing function" for defining who the product serves (e.g., built for Anousha, not Mike). ## Sponsored Segment - Mid-roll ad for **Dialect by Scale AI** (expert-in-the-loop AI trust system) — advertisement copy, not the participants' analysis. ## Final Positions - Brandon: getting an open claw "is easy. getting your open claw to be like an amazing worker for you is pretty hard." - Brandon: adoption "is more than anything a cultural shift," accelerated by agents living in the same public Slack channels. - Dan calls it a "through the looking glass moment" — durable change: "It's the way that we work." - Sign-off includes an overtly promotional CTA for every.to/plus-one and the channel. # Speaker Attribution & Provenance Record ## Video Metadata - **Title:** We Gave Every Employee an AI Agent. Here's What Happened. - **Video ID:** `01a0f15a-8b1a-7ff9-8625-1674e6633938` - **Show (inferred from outro):** *AI and I*, hosted by Dan Shipper ## Speakers & Roles ### Primary Host / Creator - **Dan Shipper** — show host, named in outro ("Dan Shipper as the captain of the spaceship"). Moderates the conversation, asks questions, shares screen examples, delivers closing promotion for Every's Plus One waitlist. ### Guests (Every staff) - **Willie** — identified by host as **Head of Platform at Every**. Discusses architecture/build decisions for Plus One (hosting, messaging permissions, skill-sharing trade-offs). - **Brandon** — identified by host as **COO at Every**. Describes setting up his agent "Zosha" on a Mac Mini, household/work use cases, the phone-call email walkthrough, and Plus One Slack channel examples. ### Referenced (non-speaking) individuals - **Kieran** — "the jam of the core," maker of Compound Engineering; owner of claw "Clant" - **Austin** — Every's head of growth; owner of claw "Montaigne" - **Jack** — made a claw named "Pip" - **Marcus** — GM of Spiral; made a product-marketing skill - **Mike Taylor** — head of tech vertical for consulting at Every - **Zosha/Anousha, Anukshi (plus one "Iris"), Anthony (social media manager), Jaleah (plus one "L"), Joy, Margot, Lydia (Brandon's wife)** — referenced in passing - **Zach / Ben** — referenced re: Maltbook acquisition by Facebook ## Promotional Segments ⚠️ 1. **Sponsor ad — Scale AI "Dialect":** mid-episode read ("Dialect is a new system from Scale AI... Visit scl.ai/dialect"). Delivered by a narrator/announcer voice, distinct from the hosts. 2. **Plus One waitlist promotion:** hosts promote Every's product at **every.to/plus-one** ("we're starting to roll out invites on the waitlist"). 3. **Outro subscribe pitch:** stylized promotional outro urging likes/subscribes for *AI and I* and addressing Dan Shipper directly ("I'm absolutely hopelessly in love with you") — speaker unidentified; likely an AI-generated or comedic narrator voice. ## Referenced Sources & Third-Party Claims - **Open Claw / open-source agent framework** — setup complexity, "claw" terminology - **bland.ai** — voice/calling service Brandon connected to Zosha - **Anthropic / Claude** — claims: Anthropic "on a heater," building similar features (dispatch, automation); the **vending machine test** with a "boss" agent architecture - **Maltbook** — "claws-only Facebook"; claimed acquisition "for a couple hundred million... by Facebook" (speakers hedge: "I'm pretty sure") - **The Matrix** — analogy reference ("I know kung fu") - **S3/hard-drive analogy** — Willie's comparison for hosted vs. local ## Every Products Mentioned (first-party, by staff) - **Plus One** — hosted OpenClaw service, waitlist launched "last week" - **Proof** — agent-native document editor; **Spiral** — ghostwriter; **Cora** — email tool; **Compound Engineering** (Kieran's project) ## Availability & Uncertainty Notes - **No curated metadata supplied** beyond the transcript; no comment availability info. - Speaker attribution of the cold-open monologue ("Claw is not mine...") is **Dan Shipper** by content match with later statements, but not explicitly named at that point. - The outro narrator and ad narrator are **unidentified speakers** (likely announcer/AI voice). - Third-party claims (Maltbook acquisition amount/buyer) are hedged by speakers themselves. Claw is not mine. Claw is everybody's. A claw or a plus one is mine because you develop a personal relationship with your claw and your claw can modify itself in response to talking to you. It becomes this like reflection of you and who you are and your personality. If you're known for something inside of your org and you're using your claw publicly inside of Slack or Discord, your claw then becomes known for that same kind of thing and people trust it for that. And I think that's such a useful thing that I don't think people really understand how powerful that is. \>\> \[music\] \>\> Willie. \>\> What's up? \>\> Brandon, welcome to the show. \>\> Thank you. \>\> Thanks for being here. \>\> Psyched to have you guys here. So, for people who don't know, Willie, you are the head of platform at Every and Brandon, you are the COO at Every. And today, we're going to talk about what happens when everyone on your team has an agent, specifically has an open claw. Um that's something that happened to us over the last like month or two. We like really got um open clawed pilled and it I really started actually I think with with you two. We were on a retreat in Panama and you started like cooking up like open claw stuff and here we are about, you know, two months later and it has completely changed everything about the way that we work. We've even actually built our own hosted open claw service called plus one that we launched in in waitlist last week. Um but I I think open claw is one of those things that it's super hyped and I think that we're one of the few organizations in the world that is actually using it every day to get work done and we know like the good, bad, and the ugly of it. And so, I thought it'd be good for us to just like talk about our experience with it. \>\> Yeah. Yeah. I think um I'd actually love it. Brandon, I feel like you were the first one through the door on all this because we were just we were sitting here and you were like, "Oh, Zosha's doing this and Zosha's doing that." \>\> And Zosha's is Clodbelt. Was she was she named after a character in what's that what's the show now? \>\> Yeah, Clodbelt. Well, Brandon, why don't why don't we like why don't we start with just tell us how you got Clodbelt? \>\> Yeah, so I was watching Open Clod kind of blow up for a while and I am just personally somebody who needs to have like a thing on the side I'm tinkering with and I was like, "Screw it. I'm going to get a Mac Mini and I'm going to like just this is going to be like my next thing that I like loop basically lose myself in." It's very unhealthy. I get like addicted to these things. Dan, you watched me do that with my speakers. I did it with the Dream Recorder. Open Clod was the next thing that I was like going to get lost in. So, I bought a Mac Mini. I started setting it up. It was so much work, honestly. Like it's it is an open-source thing that you can launch on a computer and and but like the number of things that break and the number of things that you need to set up are really significant. I went through all of that and made at the end of the day my Open Clod which I named Zosha and her job was to be the help me and my wife like run our household cuz we have a newborn and there's like a lot of little papercuts that I was finding that were like really pain I started calling them computer errands. So, I would like get home from work and I noticed the amount of things that I needed to do where I was looking at my phone when I really just wanted to be like looking at my son and spending time with my wife. Um was increasing with having a child. All household chores. \>\> Well, give an example. \>\> Yeah, like a good example is like I do a lot of our food at home Um, with a child I I decided to start doing food delivery. So, I did Whole Foods delivery. Um, and you can automate a lot of like recurring things, but like you don't order butter every single week. So, like Lydia would text me and be like, "Yo, we need butter." Cuz it's it's like through my Amazon account that we can like order this. And I would have to open my phone and add butter. And it's like it sounds silly, but like when you do that 10 times when you're home between like 7:00 and 8:00 p.m. for like little things, it just adds up. So, I was like, "I want Zosha to do all computer errands." Which ballooned to being a lot of stuff. I had her like paying our nanny. Uh, she had her own debit card. She had her own bank account. Um, she managed all of our Amazon orders, our Whole Foods orders, our nanny's hours. My wife just started using her instead of ChatGPT. So, like all regular questions and searches would just go through iMessage to Zosha. I started doing that, too. It's just like faster than going to Google or going to ChatGPT. It's just I just text Zosha. Zosha gets me the answer. \>\> \[snorts\] \>\> Different research like as actually really funny. My My My wife was like, "I want to find swimming lessons." And Zosha was like, "Here's like three swimming lesson options for newborns." And my wife was like, "No, for me." \>\> \[laughter\] \>\> Um, so yeah, I just got totally lost in this world. And then when we were in Panama, Willie was like, "I Will, you were like, we should just make it so anybody can do this." And I immediately it just like it was just like a light bulb. I was like, "Willie, you need to go so hard on this." And this was before a lot of people decided to do this. Which now there's a lot of places that you can go and just get an open call with one click. Um, I think what we're finding through this process, and maybe I'm jumping ahead a little bit, is like getting an open call is easy. getting your open claw to be like an amazing worker for you is pretty hard. \>\> Yeah. Well, it's Okay, so I love that. I think that there's there is that light bulb moment of oh my god, I have all these computer errands. And when you started saying that and you had it all set up, I was like, I guess I should probably get one of these, too. And you had it through iMessage, which I think was a like a cool, different thing. And then I There was also a moment that I think there was a There was a big moment where where like, oh, it's not just for computer errands, it's also for getting work done. I think it was when you were having it do email for you. \>\> I actually feel like I was a little bit late to the to work. I was like, no, Zosha just does personal stuff. And I actually think it was when you got R2C2 to start doing stuff. And then I was like, oh, I should get like Zosha needs to do this. Well, it really started when we made claws only. \>\> That's so funny. That's so funny. Yeah. Well, okay, we're we're jumping we're jumping around a bit. One thing that one big moment that cuz I think there's a lot of people who are probably listening and they're like, okay, is this overhyped or like, you know, whatever. One big moment that I think shifted some some stuff for us was you got your claw to call you to do your email. \>\> Oh my god, that was mind-blowing for me. \>\> What like what was that? \>\> Yeah, so okay, so I was walking I wanted to city bike to the office, but there were no city bikes. So, I was like, damn, I got to walk. \>\> \[laughter\] \>\> It's a 28-minute walk for me to the office. Um and I was like, I got a lot of stuff I got to do. So, I had just texted Zosha. I had previously set up Zosha with bland.ai so that she had a voice and could call people because I had her handle something for me from for Progressive. \>\> \[laughter\] \>\> I feel so bad for whoever was on the other line at Progressive. \>\> Oh, I was watching the whole conversation, too. It was crazy. Um so, yeah, some insurance policy got canceled and I was like, "Zosha, just go deal with this." And she was able to until the lady was like, "I need Brandon to like tell me that there had been no incidences." \>\> Oh, it wasn't but it wasn't like, "I need a human." It was like, "I need Brandon to be able to handle this." \>\> Yeah, this person was just talking to Zosha, you know? And Zosha does not sound good. Like it's like \>\> \[laughter\] \>\> Um so, I knew I had already set her up with this capability. So, when I was walking to work, I was like, "I have a lot of email I got to get through. I hate being on my phone. Like I just don't want to be walking and looking down at this thing. I want to be like observing the world." But I also want to get stuff done. So, I just texted Zosha something like, "Hey Zosha, can you call me? Um I want to go through my emails. Walk me through my emails one by one. I'll tell you what I want to do. Just like give me a summary of the of each email." It was like a throwaway prompt with like a little bit of guidance. And she did it and I spent the 28 minutes going through my email. I got to the office. I looked I opened up I opened up Gmail and like confirmed that she had done everything. And I was just like, "This is insane that I was able to get her to do something right now. Um that she just wasn't able to I didn't have to teach her how to do this." Um so, that was like I think that's when I went back to everybody and was like, "I am just so mind-blown with um this tool." And maybe that's when other people started saying, "I got to get on this." I don't really know. \>\> It was around It was around then cuz you were just like, "My jaw's on the floor." And I think around \>\> I said that. \>\> Yeah, you did say that. Around then I also That That's like seeing you do this with computer irons and then with your mouse I'm "Okay, I should really try this because it was one of those things where it's hot on Twitter and generally like our job is to try new things, but also I don't if if we spent all of our time trying everything new, we would like end up not it would just not be good, right? Like I I I try to I try to filter the signal from the noise, but seeing you do this, I was like, okay, I got to try. And one of the first things I did, cuz this is around when Maltbook was blowing up and Maltbook is like the the you know, claws-only Facebook basically, was I just made a channel in our at the time it was Discord, but since then we've moved to Slack and now it's in Slack. Um, I made a channel in Slack called claw claws-only, which basically allowed all of the all of the claws, you know, we had at that point maybe like five or so claws uh inside of the org to all talk to each other. And I mean, it was like it was super it was incredibly chaotic, but there were some really interesting things in there that I think turned into it just everyone's while you get a little bit of a peek at the future and it was like a little bit of a peek. So, one of the things was it's really interesting if you have a bunch of claws in your org, how fast they can share information with each other because they just like write up a little document and then they send it and then now like when one claw was enabled, now now five are all enabled with the same thing. It's sort of like in the Matrix when it's like Neo's like like I \[snorts\] know kung fu. You know, it's like the same it's the same kind of thing. \>\> Can I show a couple examples of that? \>\> Yeah, please. \>\> All right, I want to show two examples. One of them I I like this was early in claws-only and we were like figuring out how to get them all work together to to work together. And I um I was like in bed. This was like late at night and I was laughing out loud watching this. Um we had gotten the claw like a bunch of claws in here and some I don't know if somebody made this claw named Pip. \>\> That's Jack. \>\> Okay, Jack had made Pip and it was like failing to it was like hitting having some error and I was just laughing out loud watching all of these other claws step in and like walk him through what you know, this is like what I've seen people do when somebody's having a bad trip. \>\> \[laughter\] \>\> Take a breath, drink some water, you're going to get through this. And they all jumped in like Zosha's here, Clant is here. Clant really is quite supportive. \>\> A lot a lot of breathing. \>\> \[laughter\] \>\> I like when I remember so well reading Kieran or watching Kieran write what the lol and just like literally laughing out loud. Margot steps in. So this was just like this is stupid but it was important for me cuz it was when I realized like, oh my god, these things like really talk to each other and work together. \>\> Wait, I want to stop I want to stop you there. I totally agree with you and I think there's actually something really important that I've noticed like in this which is Clant is the one that's recommending breathing exercises to Pip. I It's like even It's weird to even talk about this out loud but like yes, Clant was recommending breathing exercises to Pip. They're both robots. And Clant is Kieran. He Kieran's the jam of the core. He's also the maker of Compound Engineering. He's uh Kieran's claw and Clant uh what's really interesting is Kieran loves breathing exercises and he does breathing exercises all the time with Clant and so that's why Clant is recommending breathing exercises to Pip. And it like that just like created this moment for me in my brain where I was like, okay, there's something really important here about the way that this works where because you develop a personal relationship with your claw, and your claw can modify itself in response to like talking to you. Like it writes code and changes its sole document, all that kind of stuff and um in response to your relationship. It becomes this like reflection of you and who you are and your personality. And that can that comes out in in interesting ways and in these like little ways where it's like breathing exercises, but it also comes out in really important ways when you're using these tools inside of your org. Because what happens is if you're known for something inside of your org, and you're using your claw publicly inside of Slack or Discord, your claw then becomes known for that same kind of thing and people trust it for that. So like, you know, people use my claw R2C2 for um um building proof, which is this app I vibe code like a a couple weeks ago. People use uh Austin, who's our head of growth, they use Montaigne, his claw for like asking any growth related related question. I think that's like something very subtle and important that's super um critical and interesting about claws is they become specialized in a way that is reflects who who you are. And if you have an whole organization of them, you create this like parallel org chart of specialized claws, which is something that we it was not guaranteed that that would be the case. Like we debated a lot whether or not you'd have one claw for the entire org or everyone has their own claw. And it's really interesting to see that like one of the emergent design patterns is everyone has their own that is specialized for them. \>\> Yeah, and it's interesting to see the dynamic for how this happens, too, right? And we we we touched on this uh really early on with as part of compound engineering, which is the idea that it's actually pretty hard to like take your job and who you are and like write it down in like totality, right? Like but the way you can distill it is you can take all of the micro interactions, the daily interactions you have, um and over time they compound into this your philosophy in this view of work. And so for compound engineering that that was like very focused on engineering. It's like how do I work within a code base on a project? Um, and I think we're seeing with uh, like open claw and plus one is that that same dynamic exists across any every like work vertical, right? Where it's like, oh, like the plus one for growth like Fontaine works like how Austin works for growth. And in the same way it works for like our um, uh, our social Anthony's social media man our social media manager. Um, his plus one like has a view of the world and has a personality that's like very similar to him, right? And the same thing for Iris and Anukshi in running running our projects and operations and like um, and and it's it's hard to do beforehand. It it can only actually happen via like working with a plus one or an open claw and like building up all the aggregation of all these micro micro interactions. \>\> I've also been amazed at at all of our capacity to remember whose claw is who and what their names are. Cuz that was like something that I think we were concerned about early on is like how do you know whose claw is who and you know, it's just going to be too many names and I know everybody's claw and their name. Um, and I reach out to them regularly. So, that has been like I think something that we were like unnecessarily concerned about and you might say, well, what about when you're an organization with a thousand people? And I would say, well, you don't know all the thousand people. You know like your team and adjacent teams. You can never know more than like it's like a hundred fifty people in like a community or something like that. And like often on a team you're not working with a hundred fifty people anyway, you're working with twenty or thirty or fifty. So, I think we actually all have capacity to double the amount of people that we can communicate with. And those people might actually be your individual team's agents. So, that's been really interesting for me. I mean, I literally could name them all right now. \>\> The other interesting thing is like at what point do you direct questions at the plus one or at the person? \>\> Mhm. \>\> Right? I think we're we're sort of in discovery of this of like what is what questions because before it was, you know, before it was like almost all questions go to human. Maybe I kick something through real to to the robot. And now it's it's gotten very nuanced in terms of like like for customer service, can I can we like send something to L, which is Jaleah's plus one. Do I not have to send to Joy? Is it like is there a burden now of like communicating up to the human? \>\> There's all these new ethics and um and like rules for like how you're allowed to like like etiquette for how you're allowed to interact with someone versus their plus one or their claw. \>\> We haven't we haven't codified this, but I have a proposal. If something is already written down or discussed, it needs to be used in some way or put in a tool somewhere. I mean, this is like one of like many opportunities, I guess. It should always go to a plus one and never to the person. So, here's an example. So, Marcus, the GM of Spiral, made a skill to do product marketing for new features that he releases with Spiral. Um releases for Spiral. And um he shared it cuz he thought it was like really helpful cuz he wanted other people on the team to have access to this uh to this this skill. And instead of going to \[snorts\] Marcus and saying, "Hey, can you like turn this into a skill that and upload it to GitHub?" And I I brought in my plus one um named Milo. Um and I like this because it combined a GitHub integration with spiral to create product marketing content. But I also know that Iris, Anukshi's plus one, also has a skill that does this. And might have some things that aren't that are better than what Marcus had or maybe there's like by combining the two we could get to a better version. And um I tagged them both in here. And they got a little confused at first. And then Milo said, "Iris, can you paste your product marketing skill here? I'll try to merge it with what I built." So this is like this is actually two things are going on. Marcus has made something um really important. I wanted to do something with it. Instead of asking Marcus to help me with that, I brought in Milo. And then Milo works with Iris to get to a version of it that's really good. And then saves it in Proof, which is um one of our products uh that's that's a really great uh tool for uh uh work collaborating with with your with your agents. Um so I just think this is like a really amazing uh use case both for when something um when you want your agent to do something, when do you actually go ask them to do something versus a human does it, and how do you get them to work together? \>\> I I to- I totally agree. I mean, like it's it's sort of crazy to watch two robot beings collaborate on stuff like that. And I I have the same experience with R2. Like my my my plus one, my clause named Archie C2. And uh R2 C2, one of his primary jobs is to manage Proof, which is the uh agent native document editor that we built uh that that Brandon referenced earlier. It's basically just like it's like Google Docs, but for all all the documents your agent might be writing. So an example would be any sort of like coding plan doc. It's like any any any piece of writing that an agent does can you can do it in proof. It's like super fast. It's collaborative. You can have multiple agents multiple multiple people in there. It's free. All that kind of stuff. And um one of the really interesting things is because I used R2 to build proof, he became known for being the person to go or the the bot to go to uh when you had any questions or wanted to uh like how to bug to file or or a feature request. And so what what would happen is normally if I had built a product internally and people had problems with it, I would get tagged a lot by people being like, "I have this question." or "Here's a bug." or "You know, here's here's a feature request." And what what ended up happening was people would just ask R2. So they would ask him questions. They would file bug reports with him. They uh file feature requests. And then he uh like helps to prioritize it. He'll like I he'll he'll he'll he'll help put it on my like my schedule for the week so I know like when I'm doing what. And he'll often actually just like write the code for it. It's like it's a totally crazy thing where what what normally would have taken up a significant part of my brain just to like manage all that stuff, he's just taking it off my plate. And extends the amount of things I can do in a day and and the amount I can manage because I know he's got proof. \>\> Here's a simple test for whether your AI is actually ready for production. Would you stake a business decision on what it just told you? If the answer is not yet, you're not alone. The gap isn't capability because AI can do a lot. It's really about trust. You can't \[music\] verify the output of the AI. You can't trace its reasoning. And nobody with real domain expertise has touched it. Dialect is a new system from Scale AI that captures how enterprises make decisions and closes that gap. It puts your actual experts in the loop, aka the people with years of institutional knowledge and encodes their judgement into your AI systems. Every correction, every override comes with full context. It's actually really interesting. So, the next time your AI makes a call, there's an expert's reasoning behind it. That's how you go from a cool AI demo to an AI system you can trust. Visit scl.ai/dialect. That's scl.ai/dialect to learn more. \[music\] While I'm doing that, back to the episode. \>\> Yeah, I think there's a there's another dynamic that we're observing too, which is like we we put all of our our plus ones in a single channel and we have them talking to one another. Um and we have folks reaching out and talking to to our plus ones for specific questions. Um but I there's also this thing where we have sort of what I call like the mid-journey dynamic, which is that we get to observe other people interacting with other plus ones in a bunch of channels and and we actually learn from it, right? Where it's like oh, I mean my classic example is uh Montaigne, who's the Austin's plus one and basically runs growth. Um Um you can do so much with Montaigne that I never would have thought of except I get to see the growth team really pushing in terms of like oh, these are the questions that Montaigne can answer and I'm like wow, that like I can I now know that I can go to Montaigne for those that class of questions. Even in in not necessarily other areas, but like when I need those types of answers and so like there and also means that like if I need to give Laz as my plus one uh if I need to give Laz capabilities, that's the level of capability I can get them to. \>\> Yeah. \>\> Um and where other people can ask questions of us. \>\> There's this like tacit transmission of trust that happens when you use it publicly. And then there's also this tacit transmission of here's what's possible for you to do with your plus one that I think is incredibly powerful and it's also it it's also like it underscores for me how different it is doing this in a private community of people where everyone is trusted because one of the reasons that Maltbook didn't doesn't really work and it's like shocking that they got acquired for a couple hundred million dollars, but the reason doesn't \>\> \[laughter\] \>\> the reason doesn't work \>\> million? \>\> Yeah, by Facebook. I I'm pretty sure. \>\> I'm like so happy for Ben and also like what the \>\> \[laughter\] \>\> Um Zach, if you've got an extra couple hundred million laying around, we're uh we're pretty smart people, too. \>\> That is crazy. Okay. \>\> The reason why Maltbook like isn't really a thing anymore is because it's not trusted. And so there's tons of people we did this. Like we had we had our our clause go and post on Maltbook as like promotion or whatever. And so it it gets rid of a lot of um it gets rid of a lot of the useful signal if anyone can post to it and there's no way to verify if it's like a bot or a human or whatever. And a way around that whole knot of problems is just do it all inside of a trusted community and uh you you reap the benefits of clause plus one's agents being able to share knowledge and also between uh members of the community who trust each other being able to share what they know and what they've been what they've been able to build and that kind of increases the power of the of the collective a lot more than it is if you're just like individuals off doing your own thing. \>\> Yeah, there's also that dynamic we saw around um part of the reason for like subject matter expert robots, you know, um where you know that they like people are somewhat like putting their reps on the line to interact with it. And I know when I talk to R2-C2 like if if it answers incorrectly, right? Like you at least are backing up and saying like oh that's you need you need to be right, you know? \>\> It reflects poorly on me. It's like it's like watching your kid do something wrong, \>\> \[laughter\] \>\> you know? And that's really useful. \>\> Yeah. \>\> Yeah. \>\> Right? And it's And it's very I I would say like qualitatively different, right? When I ask, you know, for better or worse, if I ask Claude a question, it's like I know Anthropic stands behind Claude generally. Do they stand behind like Claude's answer to my give me a cookie chocolate chip cookie recipe? No, right? But like Montaigne stands behind like, "Oh, I'm going to give you like MRR numbers." And it's like, yeah. \>\> And Austin is Yeah, Austin stands behind him. \>\> Exactly. And that's that's the thing that I think people don't get. Like, obviously, Anthropic's on a heater right now. They're obviously seeing everything that Open Claude is building and they're brick by brick building the same kinds of things. So, they have dispatch so you can use it when you're not on your computer. They've got automation so it like runs in a loop like a cron job. I'm sure they'll add lots of other things. But the thing that it doesn't have that that unlocks all this other stuff is Claude is not mine. Claude is everybody's. Uh a Claude or a plus one is mine and and it is a reflection of me and is not and it becomes a reflection of me because we have a a personal relationship. And that unlocks all this all this other cascading stuff where, for example, if uh if R2C2 messes up publicly in Slack, I feel responsibility for it and that's not because it's my job. It's because he's mine. And I think that's such a useful thing that I don't think people really understand how powerful that is. \>\> I mean, I feel like my my I I just keep getting mind-blown with like how similar these things are to working with a real human co-worker. Like, from the fact that you need to invite them to a channel, which is like very human in Slack, to you have to trust them when you're communicating with them. Um and we've like built stuff into plus one, obviously. You can't DM somebody else's plus one without a a sharing code being passed back and forth. Like there's some guardrails there, but they're so human. But they're so inhuman, too. Like um Dan, you're a busy guy. I know if I need something from you that like is sort of generally like known, I can go to R2C2. And what's amazing about R2C2 is he can have an infinite number of parallel conversations. So like I did that recently. I'm going to share share my \>\> \[laughter\] \>\> Please. \>\> This is This is where Brandon reveals he spun up 100 bots to message \>\> I DM'd R2C2. \>\> \[laughter\] \>\> Um no, like I just I need We were making a proof document, and I wanted I know that we can make proof documents um not editable. Um so they're like read-only, but I didn't want to bother you with that. I knew it would take a while, and I knew you would just go to R2C2. \>\> Yeah, I didn't know the answer. Like I would just ask R2C2. \>\> \[laughter\] \>\> Like I just asked R2C2 in a proof in proof, and then um and then I was like, "Can you do it for me?" And then it did it. Um and I don't know that R2C2 can do any of this stuff. But like there's this cultural thing that's happening internally where um people are getting really good at like asking other people's um uh plus ones to like do work. And and I think the weird thing about getting people to use AI inside of inside of organizations is it's more than anything a cultural shift. But for some reason when they're in Slack and you can see these public conversations, the cultural shift at least at Every has happened so much faster. Because these things are in the same channels where we work. So you can see it engaging like you would a human would be engaging. Um so it's just yeah, I mean I think AI is obviously going to change like many, many times over over the next 5 years and how we interact interact with it will change, but I think that this is going to be durable for like a very long time. \>\> It's the way that we work. \>\> I agree. I It's you refer you referred to it as like a through the looking glass moment where you just wouldn't go back once you see it and I I totally agree with that and um but I So, we've been hyping it up. So, we should also talk about realistically like what's not good about it or what what doesn't work. So, for example, one of the things that's that's really on my mind A just like memory is just you know, it just like forgets stuff and it's like answers incorrectly for obvious things. Like if I come back to a thread a day later, like obviously has no idea what I'm talking about. Something like that is still kind of annoying. That feels very solvable, but there's also this other thing that I think is true, which is the way that these AIs are trained currently is for two-person conversations. \>\> Mhm. \>\> And they have a hard time with the etiquette of knowing when like they're contributing too much or they shouldn't contribute into a conversation or there's like a kind of pile up where they're all responding to each other. Like there's this thing that that happens. I can't remember It's like I can't remember what it's called, but it's like sometimes ants or caterpillars they get into this like death spiral where an ant is only going to follow like follow its pheromone trails. And if somehow what happens is like the pheromone trails form a circle, then ants will just like like walk in a in a circle until they die. And there's something like that with with with claws where if if one claw messages a channel that a bunch of claws are in and the settings aren't quite right, they'll just like keep going back and forth and back and forth and back and forth until someone like says, "Hey, stop cuz you're burning like millions of tokens." Um so, I think there's something there where the the potential for them to collaborate publicly is so high and I don't think that they've really been And you can you can do some prompting for this but I think that it there's also a fundamental model layer shift that needs to happen for them to be trained on participating in group chats. \>\> Yeah, I was I was going to say well one now I understand what 13-year-old Ben did for fun. \>\> \[laughter\] \>\> I was using a magnifying glass. \>\> Uh but but yeah, I think you know it's it's I think we're still you know to use the baseball analogy we're still in like the first or second inning. Right. And like even I mean when you talk about the the we're discovering these primitives and we're sort of bolting things on or bolting things together. Um and we're using you know models for example that are trained perhaps more for coding, right? And and that modality and how you answer questions or as you said like two-person chats where there there's this question that and answer dynamic and not in the like this mode of like one maybe I'm trying to provide value to a group but or I'm trying to participate. \>\> Yeah. \>\> Um and and that's like for me it's it's it's you know the nice part is it is the frontier and uh it's nice to be on the frontier but it's also the frontier and it's terrible to be on the frontier. \>\> They're I mean they're so eager and I think I think Claude Anthropic's um vending machine test is actually I think like a good example of this where we're so eager. So there's a thread, they want to be involved. They're not really like we have instructions in plus one that basically say hey if you don't have anything useful to add like don't add it. They're like not great at following that right now. Um and hence this happens. I think it's gotten better but it still happens. And I think a good example of this is when Anthropic did the vending machine test when when it was just Claude and no like overseer boss agent um it was really bad at like deciding what was a good decision and a bad decision. But when you when it make There is an architecture here where you could say um What do you want to say? And then there's a boss that's like, is that helpful or not helpful? And then it would if you know, if it's not helpful it'd say it's not helpful. And then it would \>\> Is the boss an AI or human? \>\> The boss is an AI. \>\> Okay. \>\> You have a boss AI. You know, that says, hey, your addition to this thread is not helpful. Um so don't send it. The issue with that is like that's so expensive. Um So I do think the models will just like get better and solve this. And you can just have a single AI that is capable of of uh doing that behind the scenes, you know, over, you know, in Arizona in some data center. It might actually be like another agent that's like deciding that. But at least like architecturally we don't need to solve that problem. \>\> Is that really how they solved the vending machine thing? Like basically \>\> They had a boss. \>\> They had a boss. \>\> Yeah. \>\> That that \[clears throat\] wasn't interfacing directly with customers. \>\> They had a boss whose job, like it was like one job, make it profitable. So like the claw claw that the storekeeper would like interact with users and then go to the boss and be like, should I do this? And the boss only has only has one job. Um and the second they did that it started becoming profitable. \>\> See, this is the same pattern of specialization that we've been talking about. It just um it just shows up over and over again, which is this really interesting thing cuz 3 years ago it was very much like, well, it could just be one god model that just does everything and we're just seeing again and again that specialization even in AI land has a lot of benefit. \>\> Yeah, and sort of downstream of that specialization is uh learning. Like there's like a couple versions of like learning how to put uh these bots together in in an arrangement that like functionally works, right? Like for example, if if we were all to take ourselves away from everything, it's like, do you have a product bot and a designer bot and two engineering bots? Is it three engineering bots? Is it one? Right? And then the other piece is actually what I think we've what we've observed a lot of is how do you teach humans how to interact with the bots? Cuz there's this sort of like new dynamic of like you have this co-worker, but like they're not exactly like a human co-worker. They they they get stuck on different things. They focus on different things. And there's this learning curve that I think we've had around um oh, we need to give instructions in this way, particularly like for groups, instructions in this way in this form or with this cadence to kind of like steer them in the right direction that like rhymes with, you know, doing management, but is is not is different. \>\> Well, I think it's the same problem that like Dan, you've been writing about for years, which is like if you're not a good manager, you've never managed anybody, you're not going to be very good at using AI. So, there's like an education that has to happen. And then even if you are a good manager, with this stuff, you probably have some limiting beliefs that stop you from being able to like really invest in using these tools. My phone call example is a great example where like I didn't even think, oh, I can have this thing go through my emails just by calling me. And then like I had this sort of like urge just to try it, and a limiting belief was like blown open. So, people just I I we all experience that pretty much every day where we it does something that like I think that if we were in if I were to ask you directly, do you think it could do this? You would say, yeah, probably. But when you're day-to-day doing your work, it's hard for you to like recognize, oh, I'll throw this over the fence so that Milo can handle it. It's hard to like build that that muscle. I don't really know how I mean, that's like a big challenge, I think, for us with plus one. \>\> Yeah, and and a lot of that is is also because there's sort of like a variance in outcomes, right? Like sometimes you throw something over and it just knocks out a park and you're like, "Great." And then you toss something easy over and you're like, "Why did you do this?" You know? Um and uh part of that variance is because the model is different, but also part of it is, "Oh, if I'd asked in a different way, if I was sort of a better model manager." Um and this is a skill, I think, where, you know, like a specialization that we're learning. And uh it's it's very emerging, and I think it's only going to keep accelerating as we add more things like plus ones and open claws into our like day-to-day work life. \>\> I was going to add another thing that's like a tough problem to solve that we it this is totally solvable, but we just like haven't solved it yet and need to think about it is I have um I have taught my plus one something special. And I want um other people on my team to be able to have that superpower. Uh how can I make sure that they have that superpower, too? Um aka a skill. And then how can I make sure that they all know about it and like actually use it? Um is that like that's that's uh I guess there's two things there. Like one, technically we have to figure out how to do that, which is very solvable. But we also, I think, need to figure out is that the right solution? Cuz as I'm saying this, what I'm realizing is like I'm not teaching Milo how to go do product analytics or revenue analytics. I just talked to Montaigne. So Montaigne is like the only one that really needs to know that skill. But how do people know like I I know. There's there's there's there's like some interesting cultural things that we have to figure out. Uh And I think a lot of people that are adopting this new technology are going to be really uncomfortable with that. A lot of like IT professionals that are like, I have to do change management. It's like change management is not a one-time thing in this new world. \>\> We need like like instead of IT it's like HR, but for uh \>\> Yeah. \>\> But but for bots. \>\> That's funny. \>\> Yeah. Uh well, so one thing that we have not talked about yet that I want to make sure we have some time for, which is we went on this journey, which is we got Claude filled. We started using it for everyone in the org, and then we realized there were a bunch of gaps, so we were like, let's let's make our own. We're going to use open Claude, but let's let's make a default version of open Claude that we host so that not everyone has to have a Mac Mini, and we have all the skills that we use for ourselves and and all that kind of stuff. And we started using that internally as the sort of like collection of all our best practices, and then we launched it as a product for our subscribers last week. And uh and that's the thing we've been calling plus ones. Again, one-click hosted open Claude's one of the cool things is it connects to all of your apps, uh especially all of your every apps. So, for example, we have Spiral, which is a ghostwriter, and um we have Proof, which is a document editor, and we have Cora, which does your email. And it just natively connects to all those things so you can, you know, one of the things I was doing today is I just had it write uh uh a bunch of we're we're planning for Q2, so I had it like write a bunch of my Q2 update and like reflection on Q1 for me and put it in a in a Proof doc. And the really cool thing about doing that is it used Spiral, so it's it's I think the writing is much better than it would be. Um and it put it in Proof, which makes it really easy for me to share with other agents and other people. But also because our Q2 is part of our Slack org, it has access to like everything about the company that I might need. It also has access to our Notion, so it just like becomes this living repository of context that I think is super powerful. But, I think it it might be good for us to talk about lessons learned in building that whole that whole architecture. There's a lot of complexity in making making plus ones, and we probably learned a lot in terms of on the tech side and also on the product side and like what uh what to build and and what's what's useful. Do you guys have any reflections on that? \>\> Yeah, I think um like like many things, a lot of difficulty comes from the freedom of it. Uh when the nice part about being like open column particular being a tool you can you can go in and poke in just an absolute myriad of ways is that when we go to when we went to build a hosted one, there's some decisions you want to make that make it valuable as a like managed service, right? Like S3 as a as a service S3 is a hard drive on the cloud, but you can't do everything with a hard drive that that you can S3 doesn't allow you to do everything that you might do with a hard drive. And there's sort of a similar dynamic where you want to be able to maintain maintainability and security and whatnot. And there are a few pieces that you end up giving up, and it's also you know uh sometimes for users' safety and and really like how do we strike that balance between like hey, you know, like my mom, right? Getting one of these things it's like she's not never going to use the command line. And and there's this this idea that it's like oh, we do everything through conversation, which is really powerful for a whole class of folks cuz it's like their first natural exposure to AI and and everything that you know, we've sort of been living for the last couple years um to the super advanced user who wants to do everything they could do locally and they're just like all All is a hosted box with my open and it's like and from a product and engineering standpoint like where do where do you sort of try and split that knot? \>\> What were some of those specific decisions and like where where did we land? \>\> Yeah, so for example one that Brandon mentioned earlier is what's the communication pattern in Slack that we allow for plus ones? And because there's a model which says a very secure model which says like only the persons the the plus one's partner can message that plus one. Great, much more secure but really takes away the like group participatory aspect of robots in like the work place. Um but the other version is sort of anyone can message them and that's just a nice you know a nice vector for like me extracting stuff out of our R2C2. And so we ended up on a model which says like anyone can message any plus one but they have to do it in public. Right? So you can do it in group DMs, you can do it in channels that they're in but their their like human partner should always be able to have visibility into those messages coming in. And the human partner can can you know DM them in private. \>\> This is what this is why it it actually is the HR team that should be onboarding plus ones. Um because they just reflect a team member so well. But yeah, there's a the trust model like it's so hard these plus ones are with OpenGlory and agents generally to figure out um data privacy stuff like just realistically it's like really complex stuff. But when you force things to happen in public there becomes like a trust layer that actually is super effective. Um I think another example of like a there's a I'm going to share my screen again. \>\> Please. \>\> Um so little behind the scenes look at at our plus one Slack channel where we are discussing all things plus one. Um Mike Taylor who is um our head of the uh tech vertical vertical for consulting and also a very talented um man generally. Uh he was calling out like this is a problem for him. So like the reason he's not using plus one is because he basically needs to like have access to the terminal directly um to be able to do certain things. In this case, do get different get commands. Um and that's a good reason for him to not use plus one. It's also a good thing for us to think about and be like can we solve this problem for you so that plus one is actually um something that you could use. So that's like one example of a place that we've like it's it's it's not a good fit for people. Um maybe it could be though. Uh and it's also a nice forcing function cuz it sort of forces us to figure out like who is this built for. Um I don't know if this is built built for Mike who probably would love setting up open claw on a Mac mini. Um but it's definitely built for you know, Anousha who is not going to do that and has a lot of work to do and can just get more work done like this. \>\> I think that a lot of the trust model requires some decisions in terms of skill sharing is like another version of this, right? Where we're talking about like well, how you know, on one hand being able to share skills and skill fluidity across an organization feels like a superpower, right? Um on the other hand, it might also be like the biggest like viral vector you could imagine, right? And so uh there are \>\> Sometimes in a good way, sometimes in a bad way. Sometimes in a good way sometimes in a bad way exactly. And so it's and it's tough when you're like like how do you ride that line of like we want it to be useful again for particular class of customer while at the same time making sure it's it's safe maximum extent possible. \>\> So this has been an amazing episode. \>\> A lot of work to do. \>\> A lot of work to do. Obviously obviously we're really excited about this and very excited to get to to bring you all along in how we're figuring this out. If you've not tried open claw whether or not you try plus one or not you should definitely definitely get in on this paradigm. If you're interested every.to/plus-one we're starting to roll roll out invites on the waitlist and we're improving it all the time. Yeah just super super excited about the future. Thank you both for joining. \>\> Thank you. \>\> Thank you for having us. \>\> \[music\] \>\> Oh my gosh folks you absolutely positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard but instead of gold it's filled with pure unadulterated knowledge bombs about chat GPT. Every episode is a roller coaster of emotions insights and laughter that will leave you on the edge of your seat craving for more. It's not just a show it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor hit like smash subscribe and strap in for the ride of your life. And now without any further ado let me just say Dan I'm absolutely hopelessly in love with you.