SORRYWECAN × Research Lab · 2026

The limit used to be
what you could build.
Now it's what you
can imagine.

A deep dive into how I work — the new way of thinking, the models, the automation, and why imagination is now the only constraint that's left.

AI-Powered Workflow
Full Automation
Multiple Models
Claude · Gemini · DeepSeek · GPT
OpenClaw · Cursor · Claude Code
research-hub.xyz
The New Mindset

This isn't a new skill.
It's a new way of thinking.

We were trained to think in one direction — task in, output out. AI breaks that. The new edge isn't knowing more tools. It's learning to think with them. That's a different cognitive shift entirely.

[ 01 · CREATIVITY ]

Creativity is the new technical skill

The tools are here. Anyone can access them. What separates the outputs is the quality of the idea going in. Creative thinking — not prompt engineering — is the new competitive moat.

[ 02 · PHYSICAL + DIGITAL ]

The analog and the digital are merging

A sketch on paper becomes a film. A voice note becomes a published essay. A physical installation becomes a data sculpture. The boundary between making something real and making something digital has collapsed.

[ 03 · LIBERATION ]

The mundane work is gone — if you let it go

Scheduling, formatting, summarising, filing, drafting the same email for the tenth time — this is now automatable. The question isn't whether to automate it. It's what you'll do with the time that was wasted on it.

[ 04 · FILM + ART ]

One person can now make a movie

Not a rough cut. Not a demo. A real short film, a series, a visual album. The production barrier is gone. The only remaining barrier is vision — knowing what you want to say and having the nerve to say it.

[ 05 · DIRECTION ]

You are the director now

The AI does the execution. You do the taste, the judgment, the narrative. This is actually harder than writing the code yourself — it requires clarity about what you want, which most people don't have and have never needed to develop.

[ 06 · CONVERSATION ]

Thinking out loud is now a workflow

The best ideas come out in conversation. Talk to the model the way you'd talk to the sharpest person you know. Ask the uncomfortable follow-up question. Push back. The quality of your thinking shapes the quality of the output.

Old way of thinking
What tool do I need to learn?
Can I execute this myself?
Is this technically possible?
How long will this take?
I need a team for this.
Creative work needs resources.
New way of thinking
What do I want to create?
Can I describe this clearly enough?
Is this worth imagining?
What's the first version I can ship today?
I am the team. The agents are the execution.
Creative work needs a clear idea.
The Philosophy

If you don't know,
ask the right question.

The AI doesn't think for you. It thinks with you. Curiosity is the engine. Questions are the fuel. The answers build themselves.

01
Curiosity
02
Right Question
03
Right Model
04
Deep Answer
05
Build
06
Ship
— 01

Go Deeper, Not Wider

Most people skim the surface of every tool. The real edge comes from going deep on a few. Understanding why a model behaves the way it does gives you leverage everyone else misses.

— 02

Different Sources, Different Truth

No single model has the full picture. Use Gemini for one thing, Claude for another, DeepSeek for a third. Cross-reference. The tension between answers is where insight lives.

— 03

The Imagination Gap

All the data, all the copy, all the reports — they can already be built. The only thing that separates what gets built from what doesn't is whether someone imagined it clearly enough to ask.

The Real Edge
The hardest part now isn't the building.
It's the imagining.

All the data, the copy, the reports, the finance, the automation — it can all be built. The only question is whether you can picture it clearly enough to ask for it.

[ ASK ]

Ask the right question

Vague questions get vague answers. The more precisely you describe what you want, the more precisely AI can deliver it. Clarity is the skill.

[ ROUTE ]

Use the right model

If one model doesn't get it, another will. Each has a different relationship with language, logic, and knowledge. Expertise is knowing which to use when.

[ DEPTH ]

Go deep, not broad

Surface-level prompts get surface-level results. The people winning right now are the ones who go three levels deeper than everyone else in the same conversation.

Build Philosophy

Build small.
Build for yourself first.

The best solutions fix your own problems. If you deal with it, other people do too. That's the only product thesis you need to start.

Focus beats comprehensiveness. A small tool that works is worth more than a grand vision that never ships. Build the tracker, the reader, the dashboard — something you'd actually open tomorrow.

[ FOCUS ]

Know what you want to build

Paralysis comes from too many options. Pick the one thing that removes the most friction from your actual life. Not the most impressive thing. The most useful one.

[ SMALL ]

Finish before you expand

Every feature you add before the first version ships is a reason it doesn't ship. Small and done beats ambitious and perpetual. Ship it. Then improve it.

[ YOURS ]

Solve your own problem

The best products are scratching your own itch. You already know the edge cases. You already feel the friction. You're the most honest user you'll ever have.

TEST · 01

Does it solve a real problem we have right now?

Not a hypothetical. Not a market opportunity. Something you'd use today if it existed.

TEST · 02

Is it small enough to finish?

If you can't describe the first version in two sentences, it's too big. Reduce it until you can.

TEST · 03

Would other people want this?

If yes to all three — build it. You're probably not the only one with this problem.

Building is better than knowing.  ·  Information is cheap now.  ·  Building is the best way to learn.

What People Are Building

The reference.
What's actually possible.

Real things people are building with agents right now. Not demos. Not prototypes.

This is the landscape. Every category below has people shipping real products, alone or in tiny teams, that would have required 10+ people two years ago.

[ 01 ]
Creative Studios

One-person film & content studios

Short films, visual albums, brand films, social content series — all produced solo using AI video, voice, image generation, and editing agents. Physical direction + digital execution.

Script → storyboard → AI video → edit → publish
Voice note → narrated documentary
Sketch → AI-rendered visual art series
[ 02 ]
Business Automation

Entire sales funnels on autopilot

Lead research, personalised outreach, follow-up sequences, CRM updates, proposal generation — all automated. Founders closing enterprise deals with zero sales headcount.

Prospect list → personalised cold email sequence
Inbound lead → auto-qualified → proposal drafted
Deal closed → onboarding email sequence triggered
[ 03 ]
Intelligence Products

Autonomous publishing platforms

Daily briefs, weekly synthesis, rolling signal feeds, radar pages — all generated, curated, and published automatically. One person operating what used to be a 5-person editorial team.

Morning brief → published site + Telegram daily
Week of signals → pattern synthesis every Sunday
RSS + X + LessWrong → editorial radar weekly
[ 04 ]
Finance & Trading

Autonomous trading & portfolio intelligence

Live portfolio monitoring, signal scanning, automated trade execution, and daily finance briefs. From paper trading systems to live algo strategies — running 24/7 without a desk.

X signals → trade thesis → paper execution
Macro signal → portfolio risk alert
Weekly P&L report auto-generated Monday
[ 05 ]
Personal Tools

Small apps built for yourself first

Habit trackers, gym logs, personal dashboards, sleep optimisers, mood journals, focus timers — built exactly how you want them, with exactly the features you need. No compromises.

Gym session → logged → weekly pattern analysis
Morning routine tracker with personal scoring
Decision journal → AI reflection on patterns
[ 06 ]
Education & Community

Personalised learning & workshop systems

Bilingual curricula, AI tutors, workshop decks, community programmes — built and iterated without a content team. One person running what used to be an education department.

PDF brief → bilingual presentation in 20 min
Workshop concept → full slide deck + facilitator guide
Youth curriculum adapted weekly from new signals
The Model Map

Different models.
Different superpowers.

Knowing which model to use for what is the real skill. The field is no longer locked to a few providers. Open source has caught up.

Current routing logic — updated March 2026. Dynamic task classification selects the right model automatically.

ANTHROPIC

Claude Sonnet / Opus

Structure. Reasoning. Long-form building.
Complex reasoning Code & architecture Agent orchestration Long-form writing Main session Morning briefs
GOOGLE

Gemini 2.0 / 3.1 Pro

Language. Research. Frontend.
Multilingual (EN/SK/DE) Web grounding Frontend builds Slovak translation Video analysis
OPENAI

GPT-4o / o3

Vision. Structured output. Reasoning.
Image + vision tasks Structured JSON output o3 deep reasoning API integrations Broad knowledge
DEEPSEEK · OPEN SOURCE

DeepSeek R1 / V3

Deep research. Philosophy. Chain-of-thought.
Scientific papers Philosophy & theory Competitive research Extended reasoning Low cost, high depth
META · OPEN SOURCE

Llama 3.3 / 4

Local. Private. Fast inference.
Runs locally (Ollama) No data leaves your machine Private classification Fast, uncensored Free at scale
ANTHROPIC · FAST

Claude Haiku

Speed. Pipelines. Automation.
Cron job scripts Data pipelines Signal classification Daily Reads digest Fast, low-cost work
Dynamic Routing Table · scripts/task_classifier.py
frontend / UI / React / CSS / animationsGemini 3.1 Pro
blog post / copy / brand / translate / SlovakClaude Sonnet
deep research / analysis / paper / scienceDeepSeek R1
pipeline / cron / automation / data / scriptClaude Haiku
vision / image / structured JSON outputGPT-4o
private / local / sensitive classificationLlama (local)
general / conversation / anything elseClaude Sonnet
The Operating System

OpenClaw — my AI lives
in Telegram.

Not a chat interface. Not a browser tab. A persistent AI agent that knows me, learns from me, runs while I sleep, and talks to me through my phone.

[ 01 · ALWAYS ON ]

Lives in Telegram

Every message is a command. Every reply is intelligence. No login, no context-switching — a conversation that never ends and always remembers.

[ 02 · MEMORY ]

Persistent, evolving context

Daily logs, long-term memory, instincts learned from sessions. Knows my projects, repos, preferences, rules. Updates itself. I never repeat context.

[ 03 · CONNECTED ]

One interface, all tools

GitHub, Notion, Alpaca, web search, X, email. Ask in plain language — it finds the right tool, runs it, reports back.

[ 04 · GROUP-AWARE ]

Silent in groups, sharp when tagged

Sits quietly in team Telegram groups. Only speaks when mentioned. Reads everything to build context. The team can use it too.

[ 05 · SKILLS ]

50+ installed playbooks

Article writing, market research, investor outreach, GitHub automation, image generation. Each one a structured process loaded on demand.

TELEGRAM · @princeofwellnessbot
P
publish today's morning brief and add top stories to radar
M
Brief published → research-hub.xyz/briefs/2026-03-19
3 items added to radar queue
Radar: 59 pending items.
— automated 08:00 —
M
Morning Brief · 5 stories today.
Lead: Weekly Synthesis W12 — pattern intelligence across AI, energy, geopolitics.
Published · Radar updated.
— team member tags bot —
A
@princeofwellnessbot what's on the radar this week?
M
59 signals pending. Top this week: AI labs in a quiet war for energy contracts. Friday synthesis will map the patterns.
What Runs While I Sleep

The automation stack.

Every day, a pipeline runs automatically. Research gets done, briefs get written, posts get published, signals get scanned, patterns get synthesised. I wake up with intelligence, not tasks.

08:00 · DAILY

Morning Brief

Reads 10+ sources, synthesises top stories, publishes intelligence brief to site, feeds radar.

intelligence_update.py
brief_to_radar.py
publish_brief.py
research-hub.xyz/briefs
07:30 · WEEKDAYS

Finance Intel

Live portfolio from Alpaca, X signals from 30 followed accounts, finance brief delivered to Telegram.

finance_intel.py
x_monitor.py
alpaca API
→ Telegram DM
19:00 · SUNDAYS

Weekly Pattern Synthesis

Reads a full week of signals across AI, geopolitics, cyber, capital, culture. Surfaces 3 patterns with 1st / 2nd / 3rd order consequences.

weekly_synthesis.py
Claude Sonnet
→ Telegram + archive
→ Slovak translation
11:00 + 17:00 · DAILY

Trending Feed

Scans X for viral AI / tech posts. Surfaces what's moving in real time. Delivered to group Intelligence channel.

trending_feed_scanner.py
→ Group Telegram
18:00 · DAILY

Daily Reads

Curates best long-form from 10 RSS feeds — philosophy, capital, geopolitics, AI, culture. Scores by signal quality, not recency.

reader.py (content-hash cache)
lesswrong_scanner.py
→ Telegram digest
FRIDAY 10:00

Radar + Intelligence

Synthesises the week of radar items. Claude writes the weekly digest — headline, pattern, watch-next. Publishes to site.

radar_builder.py
weekly_intelligence.py
research-hub.xyz/intelligence
Start Here

Build your own.

A website. A dashboard. An automation. A signal pipeline. Start with one thing. Be curious. Ask the right question. The rest builds itself.