پن کیا گیا ٹویٹ
Building agents. Figuring out which ones actually matter. Some experiments work, some don’t. It wasn’t that long ago we were begging APIs for json output.
English
Will White
125 posts
Will White
@willwhite
living in the colorado mountains, building with ai, prev tandem concepts (sold), peloton (a long time ago)
شامل ہوئے Şubat 2026
86 فالونگ16 فالوورز
Every day I turn down companies offering me $100k+ to build them AI infrastructure.
They know they lack the expertise, but they don’t want to blow their cash hiring engineers that will drain them.
They’d rather pay someone a bag to:
- Build it in 1-3 months
- Save them 5-6 figures/mo
You could literally spin up a new business and build everything under this service.
That’s how big this opportunity is.
Damian Player@damianplayer
the biggest AI opportunity right now is mid-market companies ($5M-$50M+ revenue): • too big for cookie-cutter solutions • too small for enterprise consulting • drowning in manual workflows • have budget but zero AI expertise (most companies) they’re stuck with serious cash but frozen by AI paralysis. markets open to those with balls & a cold email sequence.
English
@petergyang Had to switch to Claude for consistency, even though I wanted openclaw to work more. If you’re servicing customers I just dont think openclaw is reliable enough
English
People who use both OpenClaw and Claude Code - what do you use each one for and why?
Let us know in the replies. Really curious.
Peter Yang@petergyang
My personal experience on the drawbacks of using Claude Code vs. OpenClaw as a personal assistant from my phone: Claude Code - Doesn't have dangerously skip permissions via remote control. Also remote control doesn't feel super reliable - Doesn't have voice replies so doesn't feel as personal OpenClaw - Tends to forget things randomly still
English
@APompliano Number 8 is so true. It’s almost making bigger companies worse. Just slop memos and prds being shoved around that never get revisited
English
Here are 13 things learned after making a big push to integrate AI into our companies:
1. We haven’t replaced a single external SaaS tool with something we built internally.
2. We have refrained from hiring numerous entry level jobs because AI can do the work faster/better/cheaper.
3. The automation provided by AI highlights how much time every person was wasting on tedious tasks daily.
4. Each company is capturing more revenue and each employee is becoming more productive.
5. There is still a bit of apprehension in giving agents full control of machines or systems.
6. There has been no obvious trend in age, gender, or role for those who adopt AI the fastest. More of a mindset than anything.
7. Many non-technical people have started to create software tools or products, which has changed the speed of execution across the companies.
8. One downside is the AI slop across written documents/memos. If humans don’t review the content, it is painful to read and I worry critical thinking gets lost.
9. The implementations of AI are incredible once you get them done, but it is much more difficult to build/implement than most people want to communicate online. Persistence needed!
10. We have walked away from numerous potential small acquisitions because we realized we could build the product ourselves for a fraction of the cost.
11. Our best engineers are invincible now. They produce high quality products at warp speed. Forget 10x engineers, they are 1,000x engineers now.
12. The adoption of AI starts at the top. If the company leader is not constantly asking “how do we automate this?,” it is harder to drive internal change.
13. I am personally working harder than I have in a long time and having more fun than ever. It feels like a moment in time that has to be seized.
Overall, I believe AI is underestimated, not overestimated. The worries about SaaS software are probably overblown. The labor market impact is very real and only accelerating.
Businesses are fundamentally changing. Start paying attention!
English
OpenClaw and Hermes agent on the right, Crimson Desert on the left
Multiple agents autonomously building businesses while I play the sickest video game ever made
This is the future
Your AI employees go out and create value while you enjoy the finer things in life
I love 2026
English
@Voxyz_ai I’ve just started system crons with a .py file.. took me a minute but crons were never broken
English
cron is the quietest failure point in openclaw.
no errors, no alerts. you think the 7am daily briefing is running.
it stopped two days ago. you don't check, you never know.
so on top of gateway maintenance, i added a second automation just for cron.
this one does 4 things:
1. SSH in, discover all jobs dynamically, classify recurring vs one-shot
2. separate real failures from normal behavior (quiet-hours skip, retry backoff, one-shot auto-delete are not failures)
3. smallest safe repair only. restart gateway, fix residue, re-enable accidentally disabled jobs. never touch schedules, prompts, or secrets
4. incidents get an alert. warnings get logged. same issue doesn't alert twice
full prompt (sanitized, replace with your own server address):
Maintain OpenClaw cron reliability with a single conservative automation. Read local docs before making any claims about commands or fixes. SSH to your server on its configured SSH port. Use the live service owner’s OpenClaw context as cron truth, backed by system service status and recent journal logs. Run openclaw status, openclaw gateway status, openclaw cron status --json, openclaw cron list --all --json, inspect recent cron runs, and discover jobs dynamically from the machine. Treat cron disabled, missing next wake, timer tick failures, unhealthy gateway runtime, or multiple recurring jobs failing together as incidents. Do not misclassify retry backoff, one-shot auto-delete, one-shot terminal disable, quiet-hours skips, duplicate delivery suppression, or intentionally paused jobs as scheduler failures. Apply only the smallest safe non-destructive repair such as restarting the gateway, running safe diagnostics, repairing the canonical symlink, fixing accidental root-owned residue, or re-enabling a recurring job only when strong evidence shows accidental disable. If a warning becomes chronic, alert once; otherwise alert only for incidents, and use automation memory to avoid repeat alerts for unchanged issues. If a significant issue is found, first write an incident markdown with severity, impact, evidence, repair attempted, current status, and next action, then send a short alert through the existing notification path. On Sunday morning, also run drift checks for backups, root-owned residue, and recent journal error patterns. Leave one inbox summary with healthy state, repaired issues, incidents, alerts sent, warnings, intentionally paused jobs, and blockers requiring human judgment. Never expose secrets, never weaken auth or access policy.
gateway maintenance checks if the system is alive.
cron maintenance makes sure everything keeps running while you're not looking.
Vox@Voxyz_ai
dead simple way to maintain openclaw. bugs, oauth expiring, worried it breaks while you're away. install codex app. set an automation. it checks and fixes your gateway on a schedule. new problem? fix once, add to prompt, never again. my prompt does these things: 1. SSH into the VPS, run four health checks 2. if something's wrong, apply the smallest safe non-destructive fix. no touching auth, no touching secrets 3. if it can't fix it or it's serious, write an incident report and send me a notification on telegram 4. on sundays, run a drift check for backups, root-owned residue, and journal error patterns the powerful thing about codex is that its login session can be shared directly with openclaw. oauth expiring? codex just renews it. solving this with other agents would be a much bigger problem. what you end up with is a maintenance expert that gets smarter over time. every new problem you solve gets added to the prompt, so it knows how to handle it next time. token cost is low too, each run takes about a minute. full prompt (sanitized, replace with your own server address): Maintain the OpenClaw gateway with a single conservative automation. Read local docs before making any claims about commands or fixes. SSH to your-server on port 22. Treat systemctl and journalctl as supervisor truth. Run openclaw status --deep, openclaw channels status --probe, openclaw cron status, and openclaw models status --check. Apply only the smallest safe non-destructive repair such as restarting openclaw-gateway.service, running openclaw doctor, repairing symlinks, or fixing accidental root-owned residue. If a significant issue is found, first write an incident markdown file with severity, impact, evidence, repair attempted, current status, and next action. Then deliver a short alert summary through your preferred notification channel. On Sunday morning, also run weekly drift checks for backups, root-owned residue, and recent journal error patterns. Leave one inbox summary that separates healthy state, repaired issues, incidents, alerts sent, and blockers requiring human judgment. Never expose secrets, never weaken auth or access policy.
English
@dotta @ScottSparkwave how do you handle agent hand off efficiently? Seems like that is something that doesn’t work right out of the box…
English
Take a look at how Scott runs his business with 8 agents and Paperclip
📎📎📎
Scott Sparkwave@ScottSparkwave
English
Every time I watch an OpenClaw influencer video I go a little greyer. What are they doing that I'm not???
I will pay $10,000 in Bitcoin to observe @AlexFinn using OpenClaw for 1 day.
BUT if he spends 50% of his time doing tech support, he owes me $5,000.
What do you say Alex?
English
I generated this vertical property listing video in 15 minutes for $7.
Realtors struggle to keep up with the amount of content they need to post across socials to effectively promote their listings.
This is the solution. Photos in, incredible marketing videos out. Compatible instantly across vertical video (mobile), desktop, facebook ads etc.
Turns out, all they need is AI!
Comment "CALICO" and I'll send you the tool I'm using to generate these.
(must be following so I can dm)
English
@thekitze Do you do OpenAI max and can run codex and openclaw all the time on that one sub?
English
the Codex app is a trillion and one time better than the codex cli and any other cli as a matter of fact. fuck tui, gimme ui all day every day
English
@thomasdevos69 build openclaw like you are building software, dont make openclaw build openclaw. keep openclaw focused on its objective.
English
Quick question for anyone building with AI agents:
What's the one thing you wish someone had told you before you started?
(Genuinely curious — building a resource around this)
#ClawPulse #AI #OpenClaw #AINews
English
what do i need to know before i set @its_avareed to start her own business?
English
Working with some company’s where I think AI actually makes them worse. Just employees shooting half baked AI generated docs back and forth pretending to be productive
English
@dotta @chooseliberty Do you think people are over indexing on openclaw when using paper clip and not using basic agents enough?
English
BRAVO @dotta well done, this is exactly what I was hoping for!!!
Download Paperclip so you can have better team visibility on your Openclaw multi-agent setup :)
👇🏻
paperclip.ing
English
13,500 GitHub ⭐ in just a few days for a newly open-sourced project. 🤯
And for good reason.
Paperclip by @dotta isn't just another AI wrapper,
it's a powerful Node.js backend and React dashboard designed to tame the wild west of AI agents.
You need Paperclip if you:
🧠 Have 20 Claude tabs open and can't remember who is doing what.
🤖 Rely on different types of agents (Codex, OpenClaw) and need them to collaborate.
📈 Want agents working for you 24/7 with fully auditable work and costs.
🚀 Want to build an autonomous business, not spend your days managing pull requests.
Here is why the entire dev timeline is obsessed with it right now:
→ It forces structure: Budgets, org charts, and goal alignments are built right in.
→ Deep integration: It coordinates tasks atomically with models like OpenClaw.
→ Removes the mental load: You manage the vision, the agents handle the execution.
Any agent, any runtime, with seamless coordination and zero lock-in. 🔥
Also an MIT-licensed, fully open-source project that's moving incredibly fast with a great Discord community.
Link to the repo in 🧵↓
English
@RoxCodes You're looking for Paperclip
dotta@dotta
We just open-sourced Paperclip: the orchestration layer for zero-human companies It's everything you need to run an autonomous business: org charts, goal alignment, task ownership, budgets, agent templates Just run `npx paperclipai onboard` github.com/paperclipai/pa… More 👇
English
Watching this one closely, who's tried it? Like it?
dotta@dotta
Paperclip v0.3.0 just dropped 👨💻 Cursor, OpenCode, and Pi adapters 🦞 OpenClaw Onboarding is way easier 📥 New Inbox ... and tons more This release comes from 25+ (!!) contributors in just the last couple of days. It's time to clip and we're not slowing down 📎📎📎
English
Still early, but this framing is starting to click for me.
The real product question isn’t “which model do I use?”
It’s: what layer should humans interact with, and what layer should keep the company from turning into chaos?
English
The bridge bot is the important piece.
Its job isn’t just forwarding messages.
It has to decide:
is this just chat?
is this actionable work?
does this need approval?
should this become a task?
who should own it?
English
English