Michael Richman presents "FOMAT" (fear of missing agent time): the idle time lost when an AI coding agent pauses on a question and waits for human input. He introduces Cmd+Ctrl, a system that pushes a notification when the agent needs input, allowing users to respond from a phone or watch and start new sessions remotely. The talk includes a demo of Claude Code running in a terminal mirrored in real time on an iPhone, and explains an open-source daemon layer that runs alongside agents (Claude Code, Cursor, Codex, Gemini CLI, and others) reporting to a shared control plane, plus a standup dashboard summarizing recent sessions. # Channel Identity Observations: Cmd+Ctrl (Michael Richman/Richmond) ## Speaker Self-Description (Explicit Claims) - **Role at Bitly**: The speaker introduces himself twice as leading teams at Bitly: > "My name is Michael Richmond... I lead several teams at Bitly, the link shortener" > "I run several engineering teams at Bitly. I also co-lead our AI coding tools strategy." - **Hands-on engineering leader**: He positions himself as both a manager and practitioner: "I run teams and I also write code. I co-wrote the Bitly MCP server. And I train our engineers on AI skills and best practices." - **Product creator**: He explicitly claims authorship of the showcased tool: > "I built a system called command and control in order to help me work with coding agents outside of the terminal or the IDE because I really needed it and nothing existed to solve it yet." - He notes the daemon layer is **open source**: "the daemon layer is open source, so you could plug it into any of your agent frameworks." ## Intended Audience (Observable Evidence) - **Developers and engineering leaders using agentic coding tools**. Evidence: the talk assumes familiarity with Claude Code, Codex, Cursor, Gemini, GitHub Copilot, Open Code, MCP servers, and terminal/IDE workflows. - **Conference/talk format**: The transcript shows live-presentation markers — "Thank you, everybody," "[applause]," video demos played in lieu of live demos, and references to other sessions: > "We saw this morning... Agent Craft, which is a gaming version of something similar" > "Matt Pocock alluded to this yesterday." - The audience is assumed to **experience agent babysitting pain directly**: "it's back and forth, it's babysitting... The cognitive load of managing multiple agent sessions is really high. And it is exhausting, as you all probably are aware." ## Claimed Scope of the Channel/Product Presentation - **Product scope — Cmd+Ctrl** is presented as a cross-platform agent orchestration tool: - "a way to get all of your coding agents in one place uh on your mobile device or really anywhere" - "It's on Android, it's on the web" - "monitor and interact with agent sessions and launch new sessions from anywhere. From your phone, from the web, even from your watch" - **Platform-agnostic claim**: "it's coding tool agnostic by design. It works with almost all of them." - **Single pane of glass**: "I needed a system that is a single pane of glass into all of my agent sessions. Regardless of which platform they're running on, regardless of what machine they are on." - Claimed feature set: push notifications, session subscription groups ("on my radar," "recent"), an "overview dashboard" with stand-up summaries, and starting sessions remotely. ## Demonstrated Presentation Patterns - **Demo-driven format**: The talk consists of multiple recorded video demos with walkthrough commentary ("Here's the first demo slide... This is starting a new session in the mobile app"), rather than abstract slides. - **Coining framing language**: The speaker invents/uses a term — "FOMAT: Fear of Missing Agent Time" — as a hook, and proposes a conceptual frame: "the new type of flow in the agentic world is more about agent choreography." - **Personal workflow anecdotes** as evidence: "I often start my day with prompts that I issue from bed, honestly." - **Community-engagement posture**: The talk ends with an explicit invitation to connect: "I'd love to hear about your workflows, your hacks, the pain points that you encounter... Here's where to find me on LinkedIn." - **Positioning awareness of competitors**: He contextualizes the tool against recent releases: "Anthropic recently released some ways to address this with remote control... it was just 2 days ago cursor came out with a solution in the space," and frames his tool humbly as "one solution" to a workflow problem. ## Uncertainty Notes - The speaker's surname appears as both "Richmond" (spoken, multiple times) and "Richman" (video title); the transcript is the spoken source and consistently uses "Richmond." - No curated metadata was supplied, so identity observations rest solely on title and transcript. # Delivery Observation: Michael Richman — "FOMAT: Fear of Missing Agent Time" ## Tone & Overall Style - **Conversational and self-aware**: The talk has an informal, joke-adjacent framing, built on a playful coined acronym. - **Hedging and verbal fillers are frequent**: "um," "uh," and restarts appear throughout, e.g. > "We all want to believe that our agents are low touch uh sorry, are low touch and high autonomy." - **Apologetic, real-time corrections**: He interrupts himself mid-flow: > "Did I go back? I went back, sorry. So like once I once I once again, my name is Michael Richmond." ## Recurring Phrases & Verbal Habits - **"The beauty is / the beauty of this"** — used repeatedly to pivot to benefits: - > "Now the beauty of command and control here is..." - > "And the beauty is I can go over here and resume the session" - > "and that is the beauty of command and control." - **"So..." as a connective** — opens many transitions: "So I built a system...," "So this is what it looks like on an iPhone app," "So, I hope you can see the the power here." - **"I want to demonstrate..."** — frames each demo segment: - > "I just want to demonstrate command and control." - > "I want to demonstrate another important feature of command and control" - **"And here's the thing / here's where..."** — used to refocus audience attention: - > "And at any given moment... And here's the thing. I don't know about you, but..." - > "And here's the thing. It is in those breaks that we often have our best ideas." - **Repetition of key terms**: "command and control" appears constantly; "wherever you are / from anywhere" recurs as a refrain — e.g. "It's all those things from wherever you are" and "wherever we might be and whenever that happens." ## Teaching Habits & Structure - **Relatable-scenario openings**: Defines the concept via everyday situations: > "It's being out on a walk and having an idea that you want to task your agent with and having to wait to get back to your dev machine." - **Rhetorical questions to the audience**: - > "So how do you know when an agent is stuck and needs a decision from you?" - > "How do you know to check in on an agent mid-task and that to find out that it's gone off the rails?" - **Self-intro repeated mid-talk** (likely due to a technical restart): "Once again, my name is Michael Richmond." - **Recorded demos instead of live demo**, with an explicit rationale: > "I was going to do live demo after I recorded these videos backups, I was like I'm going to show the videos." - **Deliberate disclaimer on demo simplicity**: > "the prompt doesn't matter cuz the point is that I'm issuing a prompt to my agent and I'm getting a response." - **Broadening move at the end**: Shifts from product to conceptual framing ("agent choreography," "the new flow"), citing others: > "Matt Pocock alluded to this yesterday. I don't know if you heard the Simon Wilson interview on Lenny's podcast last week." ## Notable Isolated Moments (Not Stable Patterns) - The **mid-talk restart** ("Did I go back?") is a single disruption, not a recurring habit. - The **candid personal detail** — "I often start my day with prompts that I issue from bed, honestly" — occurs once; cannot infer it's a habitual talking point from this transcript alone. - Attribution slips ("Cloud Code" for "Claude Code" late in the talk) appear once or twice; insufficient repetition to call a pattern. ## Vocabulary & Register - Tech jargon used freely without definition: "dev machine," "CLI," "daemon," "control plane," "cloud VM," "single pane of glass." - Casual register mixed with marketing-flavored phrasing: > "whatever your agent, you can reach it, and it can reach you." # Position Extraction: "FOMAT: Fear of Missing Agent Time" — Michael Richman, Cmd+Ctrl ## Speaker - **Michael Richman** (introduced as "Michael Richmond" in his own self-introductions), who says he leads several engineering teams at Bitly, co-leads Bitly's AI coding tools strategy, co-wrote the Bitly MCP server, and trains engineers on AI skills. ## Core Concept: FOMAT Richman defines **"fear of missing agent time" (FOMAT)** as the anxiety arising from agent workflows that require unpredictable human attention: - Having an idea on a walk but having to wait until returning to a dev machine to task an agent. - Returning to a desk to find an agent stopped after 2 minutes to ask a question and has been blocked since. ## Central Claims and Reasoning ### On agent autonomy - **Claim:** We all want to believe agents are low-touch, high-autonomy, but "the honest truth is that they are not yet, as much as we hype it." - **Reasoning:** Working with agents is "back and forth" and "babysitting," and one cannot predict when input will be needed. - **Qualification:** Especially true if interaction is limited to agents' native environments. ### On the growing problem window - **Reasoning:** Current coding tasks run roughly 5–45 minutes, so idle time is limited and one knows roughly when to check back. But as tasks extend to 5 hours or 5 days, users "can't just check back in a bit" — they need to know when the agent needs them and when it's done, from anywhere, at unpredictable times. ### On session management limits - **Claim:** He cannot keep track of more than two or three sessions at a time; at four or five, he loses track of state and which session needs attention. ## The Solution: Command and Control (Cmd+Ctrl) - **Origin:** He built it "because I really needed it and nothing existed to solve it yet." - **Context he acknowledges:** Anthropic recently released remote-control/teleportation mechanisms, and Cursor released a solution "just 2 days ago" — he presents Cmd+Ctrl as **one solution** among emerging options, not the only one. - **Referenced peer work:** He praised "Agent Craft" (shown that morning) as "a gaming version of something similar, which I thought was awesome." ### Capabilities demonstrated - **Interact from anywhere:** Resume and respond to sessions from phone, web, or watch; receive **push notifications** when subscribed sessions complete or need input. - **Start sessions remotely:** Launch new sessions with any configured agent (Claude Code, Codex, GitHub Copilot, Cursor, Gemini) from the mobile UI. - **Session management:** Sessions organized into subscribed (push), "on my radar," recent (last 24 hours), and the rest; supports thousands of sessions. - **Overview dashboard:** Provides a "stand-up summary" of recent sessions using their last several messages. ### Architecture - Per-agent-platform **daemons** monitor agent lifecycle (e.g., blocked, needs help) and communicate changes to a **control plane**, which aggregates all agents regardless of machine or framework; the UI talks to the control plane API. - **"Single pane of glass"** across platforms and machines — e.g., Claude Code on a Mac and Codex CLI in a cloud VM visible in one UI. - **Coding-tool agnostic by design**; the daemon layer is **open source** so it can plug into any agent framework. ## Broader Conceptual Positions ### New definition of flow - **Claim:** The old "flow" (hyper-focused solo coding) is being replaced by **"agent choreography"** — multiple parallel agents with the human moving between them, unblocking and redirecting — and the new flow comes from the elegance of that choreography and the results. ### Value of time away - **Claim:** The always-available-agent paradigm highlights the value and importance of time away from agents. - **Supporting references:** He cites **Matt Pocock** (alluded to "yesterday") and the **Simon Wilson interview on Lenny's podcast** ("last week") for the point that managing multiple agent sessions has high cognitive load and is exhausting. - **Reasoning:** Best ideas come during breaks; systems should make agents reachable during those breaks — that is how FOMAT is "truly" alleviated. ## Preserved Qualifications and Tensions - Richman repeatedly frames Cmd+Ctrl as "one solution" to a workflow problem, not the definitive one, amid a fast-moving landscape (Anthropic, Cursor, Agent Craft). - He notes the demos used "run-of-the-mill" prompts deliberately — the point was demonstrating the system, not exercising agent functionality. - The tension between wanting maximal agent autonomy and the reality of required human babysitting is presented as unresolved: "they are not yet, as much as we hype it." # Video Attribution & Provenance Record **Video ID:** `01a15ca9-4112-7b75-95ee-255843d24a16` **Title:** *Let's Talk About FOMAT: Fear of Missing Agent Time — Michael Richman, Cmd+Ctrl* ## Speakers & Roles | Speaker | Role | Evidence | |---|---|---| | **Michael Richman** (introduced verbally as "Michael Richmond"; title metadata spells "Richman") | **Creator / presenter**, lead of several engineering teams at **Bitly**; co-leads Bitly's AI coding tools strategy; co-wrote the Bitly MCP server | Self-introduction in transcript | - **Audience:** present, responds with applause; talk given at an unnamed conference/event ("We saw this morning… Agent Craft," "yesterday," "last week" references indicate a multi-day event). - No narrator, guest, or other identified speakers. ## Promotional Segments — Flagged - **Command and Control (Cmd+Ctrl):** The majority of the talk is a **demonstration/promotion of the speaker's own product** ("I built a system called command and control"), including three recorded video demos, architecture description, and a closing call to action ("I invite you to give Command and Control a try… Here's where to find it online"). - The **daemon layer** is stated to be **open source**. ## Referenced Sources & Third-Party Claims - **Anthropic:** "recently released some ways to address this with remote control and the teleportation mechanism" — third-party product claim, speaker's characterization. - **Cursor:** "just 2 days ago cursor came out with a solution in this space" — third-party product claim. - **Agent Craft:** described as "a gaming version of something similar," seen at the same event; speaker calls it "awesome." - **Matt Pocock:** "alluded to this yesterday" (event talk, regarding value of time away from agents). - **Simon Wilson interview on Lenny's podcast:** referenced as aired "last week," cited re: cognitive load of managing agent sessions. - **Tools mentioned:** Claude Code, Codex, Gemini, Cursor, GitHub Copilot, Open Code — referenced as agent platforms Command and Control supports. ## Availability & Limitations - **Comments:** no comment availability information supplied in metadata. - **Curated metadata:** none beyond title; identity spelling discrepancy ("Richman" vs. "Richmond") unresolved. - **Demo videos:** pre-recorded demos shown rather than live demo (speaker notes backup choice). - Event name, location, and links shown on-screen ("where to find it online," LinkedIn) are not present in the transcript text. \>\> Thank you, everybody. My name is Michael Richmond. Um I lead several teams at Bitly, the link shortener, but today I'm here to talk to you about FOMAT. Uh fear of missing agent time. You know FOMO, fear of missing out. You also know FOMAT, you just didn't have a name for it. Um What is fear of missing agent time? It's being out on a walk and having an idea that you want to task your agent with and having to wait to get back to your dev machine to actually do it. It is when you get up from your desk and you had an agent working 30 minutes ago chugging away and you get back and you realize that after 2 minutes it actually stopped to ask you a question. And it's been waiting there blocked the entire time. We all want to believe that our agents are low touch uh sorry, are low touch and high autonomy. But we all know the truth, right? It's back and forth, it's babysitting and you cannot predict when you're going to be needed for input. Right now coding tasks might typically take anywhere between 5 minutes or 45 minutes and you kind of know when to check back. There isn't that much time that's spent in agent idleness. But that window is only going to get longer. And the longer the agent waits for you, the more agent time that you have missed. If a task is running for 5 hours or eventually 5 days, you can't just check back in a bit. You need to know when it needs you and you need to know when it's done. And that might be whenever you are wherever you are. It may be whenever you can't predict it. You may not be at your dev machine. Did I go back? I went back, sorry. So like once I once I once again, my name is Michael Richmond. I run several engineering teams at Bitly. I also co-lead our AI coding tools strategy. Um I'm a really hands-on engineering leader. I run teams and I also write code. I co-wrote the Bitly MCP server. And I train our engineers on AI skills and best practices. I think about tools a lot. The tools that we use every day, how they work, whether they are effective for our workflows or not. And agentic coding has really changed the world of software in the last year and the road is very much being paved as we are driving on it. So I built a system called command and control in order to help me work with coding agents outside of the terminal or the IDE because I really needed it and nothing existed to solve it yet. Anthropic recently released some ways to address this with remote control and uh the teleportation mechanism and I think it was just 2 days ago cursor came out with a solution in the space. So I wrote command and control. One of the things that is nice about command and control and I'll show you it in a minute is it is a way to get all of your coding agents in one place uh on your mobile device or really anywhere. So this is what my setup looks like. I have multiple terminal windows. Each of these windows has multiple tabs. Here's Claude Code. Here's what Codex would look like here. Here's Gemini. Here's the cursor IDE. And at any given moment I might have multiple sessions running multiple agents across all of these in various states of completion. And here's the thing. I don't know about you, but I cannot keep track of more than two or three sessions at a time. As soon as I get to four or five, I don't know what session two is doing anymore. I don't know which one needs my attention and I have no idea which states of completion things are in. So how do you know when an agent is stuck and needs a decision from you? How do you know to check in on an agent mid-task and that to find out that it's gone off the rails? What if you want to start a new session and you're not at your dev machine? That's exactly why I built this system. So this is what it looks like on an iPhone app. It's on Android, it's on the web and it lets you monitor and interact with agent sessions and launch new sessions from anywhere. From your phone, from the web, even from your watch. I have a couple of video demos that I'm going to play and show you a few of the features of it. And the point here really is like this is a \[clears throat\] solution to a workflow problem, one solution. We saw this morning uh what was it called? Agent Craft, which is a gaming version of something similar, which I thought was awesome. So here's the first demo slide. Okay, here I am in the terminal. I'm going to start a Claude Code session and I'm going to issue a command that's pretty run-of-the-mill. I'm not actually exercising Claude Code functionality. I just want to demonstrate command and control. So if I come over here to my phone simulator, you'll see that I've got command and control app over here and what I've got here is my session. This is all of my sessions grouped by ones I want notifications for and ones that I want to keep my eye on and recent ones. And here you'll see the one we just issued here 27 seconds ago. Let's get out of this session over here and what you'll see here is the response I got from the agent is the same one because it is the same session. Now the beauty of command and control here is that let's say I want to subscribe to this particular session for notifications and I'm going to issue a um response to this one. I'm going to say sleep for 1 second and say hello. And as soon as I hit this, I'm going to leave the agents working. I'm I left the app cuz what I want to demonstrate here is the push notification that I'm going to get once it actually completes. And there it is. So I can click right into that guy and I got the hello. Now if I come back over to my session and I resume this guy my response is right there with the agent response as well. The beauty of this is that I don't have to stay in my terminal. I can walk away with my phone, get notified when there are answers and respond right from there. So that's one basic feature of command and control, interacting with sessions from anywhere. Let's see another one. This is starting a new session in the mobile app. I was going to do live demo after I recorded these videos backups, I was like I'm going to show the videos. So here's the next one. I want to demonstrate another important feature of command and control and that is that I can start a new session right from the command and control UI. I can pick any configured agent that I've got here. I'm going to stick with Claude Code, but you see I've got Codex and GitHub Copilot and Cursor here. I'm going to stick with Claude Code and I'm going to switch my directory to a testing directory and I'm going to just ask it what time is it? Now the reason I'm showing you a pretty simple prompt, the prompt doesn't matter cuz the point is that I'm issuing a prompt to my agent and I'm getting a response. Now you can see I'm working late at night here. And the beauty is I can go over here and resume the session and here's my session right here that I started from command and control. I can go into it here and pick up where I left off. And if I issue a command here, what is the mm date tomorrow, let's say. What I will see over here is the same conversation and that is the beauty of command and control. I often start my day with prompts that I issue from bed, honestly, and start up a bunch of sessions and resume them either in the CLI or I continue them right on my phone. I hope you're starting to see the power of command and control here. And like I said, this applies to any of the coding agents that I've got configured on my machine. Now to the problem of keeping track of sessions. This third video and then I'll talk a little bit more about the importance of this is uh session management. Now I mentioned how hard it is to keep track of all the sessions you've got going. I mean if you just look at the number of sessions I've got here, um there are a lot and I want to do revisit the different sections that are available in command and control. So as I mentioned, you can subscribe for push notifications. That's this top section here. The on my radar section is ones that I just want to keep my eye on, but I might not want to have be as chatty as push notifications for every message. Then there's a recent section here, which is basically the last 24 hours, and then the rest. Now, you can see there are thousands of sessions here. I couldn't possibly keep track of them all, but here they all are organized for me. Another useful feature in Command and Control is what is referred to as the overview dashboard. One of the really nice features of this one is you can get a kind of stand-up summary of the most recent sessions. And this is just using the last several messages to kind of give you an overview of what's been going on for each of those. So, I hope you can see the the power here, and I think this is the kind of thing that we need in our new world of agent orchestration. This is a number of things. This is interacting with your agent sessions or starting new sessions from wherever you are. It is session management. It is notifications, so you know when your agent needs you, and you don't have to guess. And it's also all of the coding agents that you might be using in one place. It's all those things from wherever you are. A little bit about the architecture of this, which you might be curious about. So, the each agent platform, Cloud Code, Cursor, Codex, Gemini, Open Code, they have a Command and Control daemon that runs alongside. They talk to a control plane layer. They monitor life cycle of the agent. When things change, it's blocked, it needs your help. It communicates up to the control plane layer, and then the UI talks back to that API layer and notifies you of things. The control plane aggregates all of the agents, regardless of where they're running or what framework they're running on. And so, this could be your dev machine, this could be a cloud VM, or it could be both. And this is an important point that I want to emphasize. I needed a system that is a single pane of glass into all of my agent sessions. Regardless of which platform they're running on, regardless of what machine they are on. I might have Cloud Code running on my Mac and Codex CLI running in a cloud VM, and all of the sessions from both of those are available via a single UI. And like I said, it's coding tool agnostic by design. It works with almost all of them. I will also add that the daemon layer is open source, so you could plug it into any of your agent frameworks that you're working on, and then access it through the the single UI today. So, whatever your agent, you can reach it, and it can reach you. And this brings me to the point of like we all want our agents to be maximally autonomous, right? And the honest truth is that they are not yet, as much as we hype it. And especially not if you're limited to how you can interact with them to their native environments. This is one solution that addresses that problem. And I want to talk about a little bit of a broader concept here that this is related to. And that is that just in the last year, the agentic coding workflow has completely transformed what software development is. It is transformed how we work, and it is also transformed how we enjoy how we work. So, you know the old the concept of flow, which is like being totally in the zone, locked into your code, hyper-focused on a single thing. You and your code solving a problem. And I think that the new type of flow in the agentic world is more about agent choreography. Multiple agents working in parallel with you moving between them, unblocking one, redirecting another. And the new flow comes from the elegance of that choreography and the results on the other side. So, then maybe that some of that fear of missing agent time can be alleviated. Another thing I really want to note here is that this paradigm of the always available agent is actually highlighting the value and importance of time away from your agents. Matt Pocock alluded to this yesterday. I don't know if you heard the Simon Wilson interview on Lenny's podcast last week. The cognitive load of managing multiple agent sessions is really high. And it is exhausting, as you all probably are aware. You need a break. And here's the thing. It is in those breaks that we often have our best ideas. We need systems that make it possible to reach our agents during those breaks, wherever we might be and whenever that happens. And that is how we truly alleviate the fear of missing agent time. Once again, my name is Michael Richmond. I'd love to hear about your workflows, your hacks, the pain points that you encounter. I invite you to give Command and Control a try if you're interested. Here's where to find it online, and here's where to find me on LinkedIn. I'd love to connect and continue the conversation. Thank you. \>\> \[applause\]