Sam Whisker

I’m just trying to offer an opinion on why they might do it. Like if you look at a few of the so called big accounts ai has slowed their original business they became known for and they have had to diversify Truth is I actually built a product off the back of the apple failure and sold it 2 years ago so in many ways I agree with what you are saying as I had 1 product that I focused on and built and sold

Building a startup and relying on one 3rd party like X API is a huge risk. And I would not suggest anybody do something like this. The thing that you said about spreading risk, I will never agree with, because if you have 10 products that make $100, that's not real money. The goal is to take one and grow it, because growth/brand/marketing compounds. I have never seen a person who actually puts their attention to all the products they have; they usually neglect the previous ones and work mostly on the last one.

I make $92k MRR with one SaaS. I will absolutely never understand people who keep building new products nonstop. Like, their whole profile is filled with domains. Maybe it would have worked a few years ago, but today? Brand is everything. I spend any little time I have working on marketing for Postiz: SEO / Articles on X / YouTube videos / Collaborations, etc. People think SaaS is a slot machine. With the number of new products shipping every day, creating many of them is just pure slop. > It decreases trust with existing customers > Destroy your reputation > Prevents you from learning how to really grow a company If I see a person who ships non-stop products, I will never buy. Why do I need to invest so much time in something that's going to be abandoned the next day?

Sorry I ment my product relied on deploying a certain type of app that Apple stopped you being allowed to deploy. So it would be like X saying you can’t use our API anymore. But yeah I think when you are the likes of the “big accounts” with multiple products they are just spreading risk and panning for gold

@samWhisker Maybe you have built a risky product, I have created many products before in my life and comeptition never stopped me

@AlessandroLavis talkflow

$125k+/month ads now look like clips like this not product demos not influencer shoutouts not polished commercials just a guy on a mic dropping a strong hook one line that makes you stop instantly “get results at home…” “no one tells you this…” then a short explanation that feels personal the product slips into the conversation naturally it feels like a podcast moment not something trying to sell you that’s why people keep watching ai now generates the host, setup, lighting, and scripts same format different hooks endless variations rt + comment “talkflow” and i’ll send the breakdown (follow for dm)

@FynCas UGC

Nano Banana + MakeUGC + Veo3 = AI UGC at scale. - Analyze niche. - Study 1,000+ winning ads. - Generate scripts, avatars & videos. No ghost creators. No wasted samples. 5/15 minutes. Production-ready. $20k/month agencies can’t compete. Comment “UGC” for the workflow. (must be following)

@matt_gray_ Clone

Once you clone yourself with AI everything changes Most founders get stuck bc every decision goes through you My Clone Yourself Checklist shows you which decisions to systematize 1st so your team runs without you Comment CLONE and I'll share it. Follow me first or I can't DM you

@spwfeijen UGC

Met a 19-year-old doing $228K/month in ecom. He’s not running ads the way you think. MakeUGC + VEO 3.1 are generating 350+ videos per hour. - UGC cost: $1 - Production time: minutes - Scale: instant (15× overnight) No shoots. No freelancers. No delays. Cinematic lighting. Human-like motion. Perfect pacing. This isn’t theory — campaigns are already scaling. RT + comment “UGC” and I’ll DM the workflow. (Must be following)

@maverickecom SYSTEM

Clawdbot + Kling = 550 videos per day No actors. No products in hand. No ghost creators. No missed deadlines. Just viral TikTok Shop sales — 24/7. Here’s the crazy part: This system produces 550+ cinematic, product-ready ads per day from a single prompt. Here’s the full pipeline: → AI generates a realistic UGC persona — face, voice, personality → Arcads clones a natural voiceover in seconds → CapCut auto-edits: captions, pacing, hooks — done → our phone farm method pushes every finished video straight to TikTok Shop → Cruva Social 1 identifies which hooks are already winning in your niche before you film anything The result: 500+ videos a month, per brand, at a fraction of what one UGC creator used to cost. Most brands are still paying $300–500 per video. Testing 10 hooks takes $5,000 and three weeks. With this system, you test 100 hooks in the same timeframe. The ones that win get scaled. Automatically. AI is the new creative director. TikTok doesn’t reward the best video. It rewards the brand that shows up the most — with content that converts. Static agencies are dead. Creator dependency is a liability… and it’s soooo 2025. No more waiting on creators. No more $500 videos that flop after 200 views. The brands that automate content at scale will be the biggest winners of 2026. If you want the full breakdown: Like & comment “SYSTEM” I’ll send you the complete workflow, every prompt, and a step-by-step walkthrough. Free. (Follow first so I can DM.)

@dev_manoj_shah Claude

I rebuilt my viral TikTok AI agent with Claude Code in 37 minutes 🤯 A full research-to-brief pipeline that scrapes TikTok, analyzes videos with AI, and generates creative briefs for your clients. All inside Claude Code + Replit. Perfect for creative agencies and DTC brands who want to turn competitor research into briefs without the manual grind. Look, all e-commerce brands & agencies should have at least one person on their team who is their "AI expert" & can vibe-code apps & workflows like this. Here's what the Claude Code version of my TikTok Agent does: → Search TikTok by keyword, date range, and video count → Pull engagement metrics, captions, and thumbnails → Gemini actually watches the video and analyzes the hook → AI scrapes comments for common questions and insights → Generate a full creative brief based on your template + brand bible No watching videos manually. No copying notes into docs. No rewriting briefs from scratch. What you control: - Multiple client projects with separate brand bibles - Your own creative brief template - Which videos to analyze and brief - Full customization through Replit's AI agent Research → Analysis → Brief. One workflow, running a custom, mini-SaaS inside your company I recorded a full walkthrough showing exactly how I built this from scratch. Want the full tutorial? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

@oliverhenry This looks unbelievable. Do you have any tutorials or walk thoughts on how you got these views? A step by step guide on how to set up and use would be priceless (and would force me to buy!!)

A lot of people giving up on Openclaw. Must be a skill issue. Larry continues to save me hours a week. You need to think of your agent as a right hand man, replacing tasks you don’t want to do. Rather than just another bot.

I’ve started moving away from one-off prompts and towards a more agent-based way of working. That’s probably been the biggest shift in how I use AI recently. For a long time, the default was simple: open a model, ask a question, get an answer. Helpful, yes. But the more I build, the less I think the real value is in isolated prompts. The interesting part is what happens when AI becomes part of an actual workflow. When you start thinking about: - role - context - memory - tools - handoffs - structure …it becomes much more than a clever answer box. That’s the direction I’m working towards now: building an AI team around the business, where different agents can support different types of work, each with the right role, the right context, and eventually the ability to plug into a shared AI brain. I’m more interested in creating a system where agents can come on and off as needed, operate with real business context, and become part of a more useful way to build. It’s still early. Still a bit messy. Still evolving. But it already feels like a much more serious way to use AI than starting from scratch in a blank chat every time. I think the next phase isn’t just better prompts. It’s building the team, the context, and the system around them. The important part for me is that this should stay framework agnostic. I’m not interested in building something locked to one tool, one model, or one way of working.

I know I can't be the only one but the update has completely nuked all my agents and they all say, "Let me check that for you" or "Yes let me check X" but then never actually check it and respond to a second message. It must be me though because surely everyone's seeing this problem with the latest update. Anybody seen any workarounds?

@jumperz I’m using Discord and it has been superb. After the latest update I ask them a question and they all say “let’s check that for you” but never get back to me so that must be a discord problem? Anyone else seeing this?

discord literally got a 200% boost from everything that shipped recently.. so, besides discrawl that the openclaw founder made, this new openclaw update is massive if you're running your swarm on discord >context engine plugins agents compress old messages to fit new ones in, problem is they would forget what they were working on..now you can plug in custom memory engines that keep everything, an agent in a 200 message thread still remembers message 1 >persistent channel bindings you could bind a coding agent to a discord channel, but it died on every restart, now it acutally sticks and your channel is permanently linked to that agent, you dont need a re-setup. >sub-workers inherit the parent configuration when your agent needs help, it can spin up a worker, before, that worker had no idea who it was or how to act, now it inherits everything using same voice rules and context and the output actually sounds like it came from the same agent >non-blocking messages if you had multiple agents in a server and one was busy thinking for 2 minutes and every other message just waited... now they all run in parallel. ask 3 agents something at the same time, get 3 answers at the same time. (this applies to multi-agent setups sharing one bot, if you're running a single agent, you won't notice a difference) on top of that: the bot actually shows online with a green dot instead of looking dead, voice messages finally work, and a ton of other polish across.. for whoever just getting started: discord setup takes a bit of work upfront but once it's running, nothing else comes close.. the margin just keeps getting bigger between telegram, slack and any other orchestration layer..

Have four agents sped up my workflow, or have they just added friction and complications to my daily workflow??? I know everyone's doing it, but here's mine. Mark: Research Marketing Expert. I ask him all my marketing and research questions,. Claudia is my PA. She emails, has calendar entries, but mainly I give her tickets for Dev To Do. She formats them and adds them to my Kanban. Gumbo is where the magic happens. I check the ticket, move it into do. Gumbo picks it up, invokes Claude codes, monitors the ticket, and pushes the PR ready for me to review. Then, when I'm happy, I merge and complete the task. Big Dog. It's just orchestrating everything. So four agents have not necessarily sped my workflow up, but I now am in the mindset of having a team and triaging work out instead of me just trying to do everything at once.

OpenClaw Pro Tip 2 Put all your project information that you have your agents working on into a Google Drive document and give them all access to the shared document. Use this as an external brain so they know everything about your customer and everything about the project, easy for you to update and easy for them to consume. You get agents with full knowledge of projects and full knowledge of customers, easily updatable access from anywhere.

pro open claw tip... Your agents need to be orchestrators and use tools as opposed to doing the “things” themselves. By this I mean don't have an agent who codes; have an agent who can run Claude Code and manage the process. That means context window stays low and you get the benefit of Claude Code.

Currently have agents in OpenClaw that are using Kimi as their brain, but they are setting off Claude code to code my dev tasks. I'm getting the benefit of being able to use Claude for my dev but use Kimi for the brain as it's cheap. Anyone else doing this, and how are they finding it?

So, having a bit of a dev day today, flying through tasks. Really do think this team structure I've set up in OpenClaw is really, really helping me. I have two to three projects where I'm creating branches for. Working on one more project that I'm just committing to main at the minute, but regardless, OpenClaw is doing a decent job.

@Shpigford @openclaw Yeah, I think so. There's a few bits that I've used it for, and I'm getting some really good results. Feels natural, good responses. I would try it out definitely.

is the brave api worth the few bucks to enable web searching in @openclaw? (vs just using automated web browsing)

I feel completely drained at the setup process of OpenClaw. This was me last week. Now I have it set up and running and behaving. The light bulb moment has hit, but the banging your head against the wall to get it working is enough to make you want to stop over and over and over again. But once it's working, it's smooth. My one comment would be the breakthrough moment was having it on a Mac Mini.