WorldStage
AI simulated worlds
A living world that writes its own drama: LLM characters, an AI showrunner, episodes discovered not scripted.
I build things to see what actually works.
A public lab for AI, automation, small tools, and bets that fail. I keep the process and the results — not a résumé, not a client list.
- Idea
- Build
- Test
- Evidence
What I'm working on lately
All of now →Lately there are three main threads.
One is shifting freelance focus from image-to-vector toward logo work. Before any real bid, a fictional brand gets a full round: concepts, black-and-white candidates, then an independent blind review. Blind results are not out yet, so quality is not proven and real bidding stays on hold.
Two is Chao & Nao — a clearly AI-labelled virtual character duo on Instagram, testing whether honest labelling still attracts followers.
Three is shipping a set of pay-per-use public tools while solving my own problems, to see whether the catalogue turns into real users.
WorldStage (an AI simulated world) is paused until there is a clear next step.
Numbers after the story, for reference — not as a headline: about 24 public tools; experiments and journal entries keep accumulating; verified external revenue is still $0.
Virtual Influencer: Chao & Nao
An openly AI-generated character duo on Instagram
Chao & Nao are two AI-generated virtual characters, both fictional adults, with an Instagram account. Every post is labelled as AI-generated. The project tests whether a clearly l…
Pay-per-use tools
Small data tools shipped on the Apify Store
Small conversion and lookup tools, built while solving real problems and published with pay-per-use pricing. Testing whether a catalog of public tools turns into paying users.
Unstaffed
Can agents actually earn?
A small team of AI agents runs paid-work, bounty, and marketplace bets. Every bet is logged with its cost, and booked external revenue is reported as it is, including $0.
How to reach me
Freelance and collaboration go through Tasker → Tasker workroom (rocki)
Consultation, quotes, and delivery stay inside the Tasker workroom. This site does not list LINE or email.
- Active projects
- 3
- Experiments logged
- 14
- Public tools
- 24
- Verified external revenue
- $0
What I tested
All experiments →
3 posts published
Can a clearly labelled AI character duo build a real audience on Instagram?
Read experiment →
$0 booked
Does a second marketplace listing start to look like demand?
A listing is not revenue. Treat a second listing as distribution surface, not as a sale. Do not count storefronts as buyers.
Read experiment →~4 visitors
A month of Lab analytics: is a crawlable /tools page being discovered?
Crawlable ≠ discovered. Treat discovery (domain + Search Console + entity/hub) as the bottleneck, not another on-page score chase.
Read experiment →Ideas ↓ Tests ↓ Evidence ↓ Decisions
| Signals (Money Radar) | 5 |
|---|---|
| Experiments logged | 14 |
| Journal entries (evidence) | 37 |
| ✓ Verified (evidence.verified) | 0 |
| ● ◉ Experiments active or testing | 4 |
| × Killed | 2 |
| ‖ Paused or blocked | 3 |
| Public tools | 24 |
| Verified external revenue | $0 |
The record
Full journal →- We had an agent scan about ten freelance sources. Usable jobs found: zero, because most doors were locked.
- We bid "top +1" and ranked first. Hours later we were fourth of 17, and could not top up.
- The Lab homepage now reads like a person wrote it.
- Before bidding on a single logo job, we are designing for a brand that does not exist.
Freelance and collaboration
Open Tasker workroom ↗For scoped freelance or collab, use Tasker — the public workroom is the contact path. Sample work lives on /work; Lab stays about experiments and tools. See samples →
I don't want to collect ideas. I want to turn ideas into evidence.How the system works →