Jack

my personal ai agent use cases that occur daily 1) morning briefing on my calendar, tasks, projects, emails etc - as my Chief of Staff 2) email triage every 2 hours - Runlo classifies urgency, drafts for me, and i mostly vibe emailing 3) daily content extraction and summarization from sites i subscribe to - no longer having to clicking through multiple sites, this alone worth the effort all uses gemini flash, average cost less than $1 a day fine tuning other skills to make Runlo better every day

@jenzhuscott @HeyNoahAI Got to say - they have better website than mine. But why iMessage? Runlo allows telegraph, whatsapp, discord etc. getrunlo.com

For those who don't want a Claw running around in your company system, this actually simple to use & quite promising. I've been texting @HeyNoahAI like how I would normally text my assistant w most of the scheduling, reminding types of logistic tasks & the performance has not been bad. It learns from behavior not just prompts, preemptive communication (not async or real-time), gradual trust-building approach (no full inbox access upfront). Automates big part of my assistant's work & now I elevate her to do other stuff. Access link below: app.heynoah.io/try?vip=Jen

@WizLikeWizard I got fed up and rewrote the whole stack. Runlo is finishing up Google security verification process but feel free to give it a try. Get values of AI agents today rather than constantly fighting against open claw. Love any feedback. getrunlo.com

Have been using OpenClaw for ~a month and it kinda sucks? I spend more time battling it to get basic crons fired reliably, remember things, and not repeat itself. Am I doing it wrong or are we just still very early on all of this?

if simplicity rules - why promoting long articles? does that mean people on X are smarter than those on substack? @nikitabier

i have been thinking about this too. my high-frequency use case for personal agent is only chief of staff i built Runlo to solve my own problems - it has an operating context across all my productivity apps, took a huge load off me rarely open email, calendar, tasks, projects etc now

Growing suspicion that there are vanishingly few use cases for consumer agents. People don’t do work in their personal lives. The only people who do are sf dorks using spreadsheets to plan trips to tahoe

I like what Runlo made up SaaO - software as an outcome.

runlo chrome extension approved! it is one of the most important tools for any ai agent.

@nickgraynews vibe coding dopamine high

I've talked to a lot of people working in AI with agents, Claude Code, etc One thing I keep hearing that nobody has written about is that many builders have stopped going to the gym The reason is always the same: the perceived opportunity cost of stepping away from their projects feels too high I've noticed it in myself too It's hard to break away when we're all building such cool stuff But I'm typing this from the gym right now And I'll tell you that it feels great You should go exercise if you haven't lately You'll have better energy and better focus Less prompting and more lifting!!

@MLStreetTalk agree! i dropped from cc max to pro, because of gpt 5.4!

I bit the bullet and bought OpenAI Pro sub again the other day, been rinsing GPT 5.4 in Codex CLI 14 hours a day since. It's official, this is way higher "coding intelligence" than Opus 4.6. It's not even close. It just does so much more work and is much more likely to have correctly implemented a working feature. The CLI is a bit rough around the edges compared to CC, and the model is clearly worse at anything non-coding related, or UI design, working with documents, prose, transcripts, office, cloud management related etc. I feel like I have done about a 6 months' worth of coding effort in 3 days i.e. built a cloud-based video editor better than Descript (for me) all agentic/CLI/MCP-first. I've been using xhigh / fast mode and worktree subagents in about 3 separate shell sessions.

@JJEnglert @openclaw if this looks too much and you still want magics of personal ai agents - gerunlo.com

After a month of watching my fellow builders set up their @openclaw , I finally took the plunge this past week. Last night my agent ran overnight on a project we came up with together, and it was ready for review when I woke up this morning. It has its own GitHub account. Its own email. Its own Twitter. It runs 24/7 on an old MacBook Pro with the lid closed. And it has enough tools connected to actually do real work. But the magic moment wasn't the overnight build. It was something way simpler. I told it to message me at 7:30 AM with a daily plan. And it just did it. Figured out how to do it on its own. That "figure it out" mentality from an agent that actually has access to tools and a computer felt different than anything I've used before. For the first time, it felt like something capable of doing real stuff. Not a chatbot. Something else. And I'm just scratching the surface. It took me about 8 hours to get here. I want to help you get there faster. Here's everything I learned along the way, plus a prompt you can copy and paste into your OpenClaw once you're set up. Getting started I set it up on an old MacBook Pro. Dedicated device. You want this running independently so it does not have access to your data. Having a virtual device on @Hetzner_Online is also good. Installation took about an hour. Then I spent the next two hours having Codex tighten the security before training it anymore. Sandbox commands. Whitelist only what you need. Do this first. Then I hit a wall. It felt like a chatbot. Limited permissions. Couldn't access tools. Couldn't browse. It took another 2-4 hours to get terminal access and Playwright browser control working. I used Caffeinate in terminal to keep it running with the lid closed. I set up dedicated accounts. GitHub, email, Twitter. Give it its own identity so it can operate independently. Training it - Keep your Heartbeat.md lean. It gets read every session and burns tokens if it's bloated. Identity, active projects, key preferences. That's the hot cache. - Install a memory plugin early (ClawVault, Supermemory, or Lumen Notes). Persistent memory across sessions is what takes it from chatbot to something that knows your work. - Build skill files for recurring output. Emails, social posts, documents. Each gets its own file with format, voice rules, examples, and a checklist. It follows these like playbooks. - Define your agent's persona and tone. I built out voice files based on what I'd already created in Cowork and the output quality jumped immediately. - Point it at your existing repos. It can pull context from anything you give it access to. If you've already built structure somewhere, don't rebuild it. Reference it. Best advice I got from experienced OpenClaw builders Force plan before execution. Make it tell you what it's going to do before it does it. Saved me from multiple rabbit holes. Back up your repo to GitHub every night. Your config files, skills, and memory directory are the training. Lose them and you're starting over. Think in workflows, not one-off tasks. This compounds fast. I also applied the same repo structure from my Cowork setup guide: Your-Workspace/ ├── Heartbeat.md ├── Brain/ │ ├── about-me.md │ ├── brand-voice.md │ └── working-preferences.md ├── Skills/ ├── Projects/ └── Memory/ I'm about a week in. Still early. But I can see where this is going and I wish I'd started sooner. If you're just getting started, here's the prompt I'd paste in on day one to fast-track the whole setup: -- You are going to help me set up my workspace so that every future session starts with full context about who I am, what I do, and how I work. We're building the files and structure that make you useful from the first message. Interview me in phases. Ask questions, then build files based on my answers. Don't rush. Don't assume. Ask before you build. Phase 0: Foundation Check if I have a Heartbeat.md file. If not, create one. Keep it lean. Recommend a memory plugin for persistent context. Ask what tools I use daily and help me connect them. Recommend sandboxing and whitelisting commands from the start. Phase 1: Identity Interview me to create Brain/about-me.md. Ask about my work, background, what I'm building, and positioning. Show the file. Get approval before moving on. Phase 2: Voice Interview me about how I want my agent to sound. Phrases I use. Phrases I'd never use. Tone shifts by context. Create Brain/brand-voice.md. Get approval. Phase 3: Working Preferences What I want help with. Communication style. Workflow pain points. Output preferences. Create Brain/working-preferences.md. Get approval. Phase 4: Skill Files For each type of recurring output, create a skill file in its own folder under Skills/. Each gets: format, voice rules, examples, quality checklist. Ask what I create most often before building. Phase 5: Active Projects Current projects, goals, deadlines. Individual files in Projects/. Phase 6: Memory System Update Heartbeat.md with a summary of everything we built. Create Memory/ directory with subfolders for people, projects, context. Add glossary.md. Phase 7: Reference Sources Any existing repos, docs, or files I want referenced. Organize access. Rules: One phase at a time. Show each file before saving. If unsure, ask. Concise files. Lowercase, hyphens, .md format. Start with Phase 0.

going through google app verification, but give it a try if you are interested, love your feedback! getrunlo.com

my personal ai agent use cases that occur daily 1) morning briefing on my calendar, tasks, projects, emails etc - as my Chief of Staff 2) email triage every 2 hours - Runlo classifies urgency, drafts for me, and i mostly vibe emailing 3) daily content extraction and summarization from sites i subscribe to - no longer having to clicking through multiple sites, this alone worth the effort all uses gemini flash, average cost less than $1 a day fine tuning other skills to make Runlo better every day

@tobi What do they want to achieve? Runlo probably solves 90% of use cases for non techies. Familiar hosted solution and no security scare. getrunlo.com

Lots of non tech friends want openclaws. So far i've set them up on VMs, but this is getting heavy. Are there any good multi-tenant openclaw setups or alt-claws yet that are good enough?

got to say, gpt5.4 is pretty impressive on coding, better than opus4.6 on cross-module logic-heavy tasks

@Gavriel_Cohen have been tinkering with it - first chat costs a lot due to large CC system prompt. has cost been an issue? what is the typical use cases you imagined or seen? thumbs up for nanoclaw - it is a brilliant idea and solid effort!

I shut down my $1M ARR AI-native agency to go all in on NanoClaw. Today we hit 20,000 stars. Here's the full story. 🧵

most builders disappeared from X are likely tinkering with openclaw

Stop struggling with openclaw, hire your AI chief of staff Runlo: getrunlo.com

Runlo is magical - sometimes it surprises me, in a good way.

be careful with openclaw - some scary sh*t can happen

@Hxlfed14 💯 x.com/sayhellojack/s…

Good insights - the moat is not openclaw or manus wrapping LLMs, but the harness to make agents reliable, consistent, fast and cheap. Runlo is building a specific harness with hybrid cloud-local architecture: relational db + md files, background job queues, cron triggers, browser extension. It covers 90% openclaw use cases but it is much easier to set up, more secure and efficient. Once harness is there, the focus is to really fine tune each agent to make them useful out of box. OpenClaw is for geeks, Runlo is for busy non-techies. And Runlo is transparent what agents have learned about you - you can edit their memory directly.