Subscribe
Sign in
Home
ᯓ➤ START HERE
💎 PREMIUM ROBOTS
Archive
Leaderboard
About
⚡Build smarter
Latest
Top
Discussions
Robots ate my MCP
How to connect RobotsOS to the AI you already use, then call in the right robot when you need one.
Sep 4
Â
•
Â
Mia Kiraki ðŸŽ
36
18
5
Before you build an AI agent, give it a way of seeing
How to turn the methods and references already inside your world into different AI behavior.
Aug 7
Â
•
Â
Mia Kiraki ðŸŽ
20
2
4
How I turn things that follow me around into useful analogies
A process for turning films, books, observations, and old memories into questions, methods, and things your field would not have produced on its own.
Jul 24
Â
•
Â
Mia Kiraki ðŸŽ
36
12
9
How to appraise your content archive like a museum curator
Four frameworks from museum science to kintsugi that turn your back catalog into a 30-day action plan.
Jul 10
Â
•
Â
Mia Kiraki ðŸŽ
56
6
11
A failed universal language explains why you keep picking the wrong AI output
The case for working with the differences between AI models instead of hunting for the single best output, told through two old stories about language.
Jun 24
Â
•
Â
Mia Kiraki ðŸŽ
43
16
12
How four Greek winds became an AI agent that attacks arguments from every direction
A pressure-testing AI agent built on four adversarial perspectives and one rule: they can't talk to each other.
Jun 12
Â
•
Â
Mia Kiraki ðŸŽ
37
4
9
How to deliberately push a good idea past "interesting" with AI
A four-question framework for turning a good idea into an extraordinary one, testing for tension, enemy, activation, and transferability before you…
May 15
Â
•
Â
Mia Kiraki ðŸŽ
41
11
10
AI research is shadows on a wall: how to find the disagreements that sharpen your thinking
Why AI summaries erase the disagreements that would sharpen your thinking, and a step-by-step contradiction mapping method for building positions that…
May 1
Â
•
Â
Mia Kiraki ðŸŽ
27
6
10
One day with Claude Opus 4.7 and it had me build my own AI model evaluation tool
I ran the same prompt across three models and got three different kinds of wrong. Here's the tool I built so you can stop guessing which model fits your…
Apr 24
Â
•
Â
Mia Kiraki ðŸŽ
41
14
13
I built an AI greenhouse where scattered thoughts go find each other
How a greenhouse-inspired AI system tracks your half-formed ideas, cross-references them over weeks, and flags the exact moment they're worth turning…
Apr 8
Â
•
Â
Mia Kiraki ðŸŽ
63
21
16
AI content research is making you less interesting. Here's what I built to fix it
Meet WATSON, the AI editorial researcher I built to kill generic content research. The full architecture, the methodology, and the first agent inside…
Mar 11
Â
•
Â
Mia Kiraki ðŸŽ
110
43
31
I created a crossword to redesign how AI workflows work
The "Crossword Method" for building AI workflows where every step constrains the next, so you stop copy-pasting guidelines into fourteen different…
Feb 25
Â
•
Â
Mia Kiraki ðŸŽ
52
36
11
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts