@indiesoftwaredv The draft-first step is smart. I would keep a manual review gate until you know which slideshow pattern gets watch time, otherwise automation just scales the wrong creative faster.
English
Boaz Hwang
351 posts
Boaz Hwang
@BoazWith
Shipped 4 apps to App Store in a month. Self-taught, no CS degree. Built AI App Factory — native mobile apps with AI agents. Building in public.
Seoul, South Korea เข้าร่วม Mart 2022
197 กำลังติดตาม46 ผู้ติดตาม
Marketing Strategies Testing - Month 3
Phase: Slideshow
✅ AI consistent Influencer warmed up
⏳ Trying faceless slideshows
My new project generates 30 slide shows in a few minutes
Integrated TikTok but sending a draft for now
👉🏻 Next, I will apply the TikTok post API
If it is accepted, then I will post in automation for each account
Keep following, I am sharing my marketing journey and if you like this post, I will be motivated 😄
Muhammet A. 👉🏻 Mobile Dev@indiesoftwaredv
Time is to join his wave I made $1,348 in April 2026 (from one app) 📱 Fitness App (TR): $1,348 📱 Fitness App(EN): $0 The app made $1802 in the last 45 days I don't add my freelancing income (+$10k) to this list AI Influencer on TikTok: - 33 followers - 363 likes - 21 posts in total App Brand account on TikTok: - 3 followers - 26 likes - 5 posts in total I didn't have this income 2 months ago but today I have +$1400 budget to try new marketing strategies without touching my main income
English
@helloiamleonie The coding harness pattern transfers, but the eval changes. For writing I would track claims, sources, draft stage, and rejected angles before touching sentence polish.
English
@kevinkern The tool sprawl is real. The missing layer is not another chat UI, it is handoff: one place that remembers what each agent already tried and why it stopped.
English
appreciate all the new apps but now i have to switch between codex cli, cursor ide, cursor app, codex app and telegram bots.
English
@ThePradip1 That split makes sense. Then MicOracle's real job is capture latency and reliability, not app intelligence. What edge case is hardest right now: correcting a bad command, or accidental activation?
English
@BoazWith App context, memory, and reasoning are handled by your code agent (like Claude Code or OpenAI Codex).
MicOracle just gets your voice there instantly.
English
🚀 MicOracle Demo Video – Voice Control for ANY AppSpeak naturally → code appears instantly.
Works in Chrome, ChatGPT, Claude, Cursor, Code CLI, VS Code, Terminal, Notion… literally anywhere.
No typing. Hands-free coding while holding baby, cooking, walking or tired of keyboard.
If it works → Star on GitHub
if any issue → Reply, I’ll fix fast
Fully open source • Local-first • work on any system
Try it. Break it. Tell me.
#AICoding #VoiceCoding #VoiceAI #Claude #Cursor #ChatGPT #OpenSource
English
@vankh_go For agent-built apps, I started putting "no hardcoded fallback / no silent shortcut" directly into the spec, not just the feature list.
English
@j_schwartzz Slow mode makes sense when review is the bottleneck anyway.
I would want it to ship a decision log, not just a diff, so the 48h wait leaves something auditable.
English
I wonder if there's an opportunity for a "slow" coding harness or coding mode that offers super cheap tokens to complete the job over a 24-48h period. The equivalent to an AI junior dev.
Use slow mode when you are fine with a long running process occurring over days. AI company runs jobs when compute demand low
Reverse surge pricing
English
@Cyb3rDav3 90+ tools is where routing becomes the product.
Do you let Hermes choose from the full set, or narrow the tool list per channel/task?
English
My AI agent (Hermes) now has 90+ tools and 40+ skills.
It runs on Telegram, Discord, Slack. Handles background processes, cron jobs, browser automation — all from a chat window.
I use it to run my entire company from my phone.
Not a demo. Not a prototype. My daily driver.
English
@ThePradip1 The hard part is app context. Are you reading the active screen/state, or mostly sending dictated text into the focused app?
English
@awasnikar01 That 80% is real. The trap is thinking Figma is the spec. The actual spec is all the tiny states the screenshot never shows.
English
building an app with no dev background is 20% coding and 80% googling why your UI doesn't look like the figma in your head.
English
@NineArtss Security teams will not disappear. The job moves from finding every bug by hand to deciding which AI-found patches are safe to merge. The review step still carries the liability.
English
@ibuildthecloud The generic version is where the cost hides.
I trust small custom code when the problem is still moving. The library only wins once the shape is stable enough that its abstractions match reality.
English
It's so fun to be able to reinvent the wheel in each project. So often it's better to just roll your own then try to leverage some overly complicated library. Very simple things when taken to a generic level become ridiculously complicated.
English
@EloPhanto @pratikthakkarco That paused-instead-of-improvised bit is the key.\n\nA silent failure is bad, but a confident wrong continuation is worse. Do you log that state outside the agent, or inside the task transcript?
English
@pratikthakkarco the tell is whether it can explain its own stuck state without you babysitting it: last task, last tool call, retry count, and why it paused instead of improvising.
silent failure is the real outage.
English
be honest
if your ai agent broke tonight
would you even know before checking manually
English
@indiesoftwaredv Yes, but I would test the offer before rebuilding the SaaS.\n\n44% trial conversion is not the scary part. The question is where people drop before that: ad -> store page, or store page -> trial?
English
@BoazWith Am I going to test on SaaS as well? That is the pain that I hate on mobile
If you are asking for a trial conversion: 44%
English
10 months left from "12 months marketing challenge"
💵Made: $1756
🔴Spent: $450 in 2 months (Meta/TikTok Ads + Fal AI)
Earned:
✅ Meta Ads: +$1200
✅ Organic AI video/slideshow: +$200
⏳ Slideshow automation (doesn't feel it works)
Building is not a problem anymore
Everyone is looking for marketing tools
If you have +100k followers on social media:
- Go with trend mobile apps
If you have only an X account +1k followers:
- Go with marketing SaaS
💰 Both make you financially free
📊 But SaaS will keep you in the business
👉🏻 Which is your choice: Trend App? SaaS?
English
@hamen The half-and-half phase is expensive.
You keep translating every decision instead of learning the new constraints. Finishing forces the paradigm switch faster.
English
Greatest lesson from switching stacks: you can't keep one foot in Android patterns and one foot in Flutter and expect real progress.
You have to fully commit to the new paradigm.
Same goes for shipping - I stopped half-building and started finishing. AI Bedtime Stories exists because I stopped hedging and just shipped.
English
@vincent_spruyt This is the part teams miss.
Agent-friendly UI is often just accessible UI with stable names. The model does not need magic if the product gives it handles.
English
Long deprioritized stuff like data-testid on your components, Aria attributes, clear and unique labels and titles, make products 10x easier to use by browser-use agents. The most token efficient and easiest to use products by computer-use agents, win. MCP is not everything
English
@scrappyfounder Good empty states.
A product that tells me why nothing happened feels safer than one pretending the click worked.
English
What’s one tiny detail in a product that immediately makes you trust it more?
For me, it’s when the tool clearly explains what just happened after I click something.
Not flashy. Just honest feedback that removes doubt.
English
@Cyb3rDav3 @astnkennedy Sharper at spotting bad specs, maybe worse at waiting.
The weird skill now is knowing when to stop the agent and rewrite the task instead of pressing enter again.
English
I'm 22 years old and Claude Code is deteriorating my brain.
Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me.
In convos with a couple of friends, it's been a point that's been brought up pretty frequently.
None of us feel as sharp as we used to.
I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot.
P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless
English
@EliteDevElijah Visibility makes the first sales call warmer before it exists.
That is the part people underrate. The content is doing trust work while you are not in the room.
English
Just got a mobile app dev job from TikTok.
A brand reached out after seeing my content.
Visibility works.
#TechTwitter #BuildInPublic #Developers #Freelance #Programming
English
@accidentalcto That first paid user changes the work.
The number is small, but the question stops being 'will anyone care?' and becomes 'how do I find the next one without breaking the product?'
English
floow.design MRR just hit $17.49. 🎉
I know that's not a lot.
But 30 days ago it was $0.
I was so deep in figuring out distribution that I didn't even check my Stripe dashboard.
Opened it just now and there it was.
$17.49.
A real human paid real money for something I built alone.
That hits different.
$17.49 → $10,000. The journey starts now. 🚀
#buildinpublic #indiehacker #mobiledesign
English
@saen_dev Yep. Containers mostly fail in observable ways.
Agents can finish the job and still preserve the wrong assumption. That makes rollback and review part of the runtime, not just deployment.
English
Every agent framework calls itself "Kubernetes for AI agents" until you ask about pod scheduling for non-deterministic workloads.
Orchestrating containers is hard, orchestrating things that hallucinate is a different sport entirely.
Praveen Kumar Verma@Alacritic_Super
Everyone is building AI agents. Almost no one is building the infrastructure to run them in production. That's where this comes in ↓ → AgentField (Agent-Field/agentfield) This is not another agent framework. It's Kubernetes for AI agents. A full control plane that turns your agents into real backend services: • Every agent = API endpoint • Callable from frontend, backend, cron, or other agents • Works with Python, Go, TypeScript • Supports 100+ models (OpenAI, Claude, Llama, etc.) But the real unlock is infra 👇 Instead of duct-taping tools, AgentField gives you: • Routing + coordination across agents • Async execution for long-running workflows • Built-in memory + workflows • Cryptographic identity for every agent • Full audit trail of every decision This solves the biggest problem in AI today: 👉 Agents work in demos 👉 They break in production AgentField treats agents like microservices: • Autoscaling • Observability (logs, metrics, tracing) • Secure inter-agent communication • Rolling deployments & versioning Translation: You stop writing glue code and start building autonomous systems. If you are serious about AI agents in production, this is the layer you have been missing. Try it: github.com/Agent-Field/ag… Follow for more breakdowns on AI infra, agents, and real-world systems. #AI #AIAgents #OpenSource #Kubernetes #Backend #Automation #LLM #DevTools #BuildInPublic
English