Maria
Agentic Systems · Travel

Somewhere between "this shouldn't work" and "wait, why does nobody else do this" — this is where I build.

I design AI systems for e-commerce and SaaS brands who are very happy with the results and very nervous about you finding out.
28 brains.
40+ workflows (not these 280 free ones — mine have been yelled at, rewritten 6 times, and run 24/7 on real money. Reluctantly.)
Here are some cases with the names scratched off.

COMPOUND INTELLIGENCE ✦ AGENTIC SYSTEMS ✦ DIRECT RESPONSE ✦ ZERO HEADCOUNT ✦ AUTONOMOUS OPS ✦ SPEED OF MUTATION ✦ COMPOUND INTELLIGENCE ✦ AGENTIC SYSTEMS ✦ DIRECT RESPONSE ✦ ZERO HEADCOUNT ✦ AUTONOMOUS OPS ✦ SPEED OF MUTATION ✦
Two ways in

Pick the one that matches your current mood.

01
The Personal One

The awkward welcome speech

01 · Personal The awkward welcome speech
2 MIN

Who I am, why I built this, what you're looking at.

02
The Technical One

How it actually works

02 · Technical How it actually works
3 MIN

Architecture walkthrough — agents, scoring, reject loops.

What happens when nobody's watching.

Cases with the names scratched off. (because the systems run autonomously)
Vol. I · Chapter Zero · The Primer

Before we go further, a plumber.

Two encyclopedia entries for the same profession

§ 01 The Confusing One

Plumber, Theoretical

/ˈplʌmər ˌθɪəˈrɛtɪkl/ · noun
Definition

A tradesperson who, when asked to fix your sink, explains siphon physics, P-trap geometry, vent stack dynamics, and the fluid mechanics of negative pressure — while you nod politely, understanding nothing.

Result You leave with a headache and still don't know if the sink works.
§ 02 The Useful One

Plumber, Practical

/ˈplʌmər ˌpræktɪkl/ · noun
Definition

A tradesperson who, when asked to fix your sink, looks at it, fixes it, and says "nothing leaks, enjoy your bath 24/7."

Result You understand instantly. You go take a bath.
See also

§ AI Vendor, Contemporary — almost always of the theoretical variety. Talks RAG pipelines and multi-modal orchestration to hide the fact they built a ChatGPT wrapper. The following entries translate them back into human.

Vol. I · Chapter One · The Glossary

Everyone says agentic.
Here's what it actually means.

Five common terms, translated

The difference isn't AI. The difference is architecture.

Compound systems with scoring gates and reject loops don't just "use AI" — they build an intelligence layer that gets measurably sharper every week. That's not a feature. That's a moat.

Active
Ongoing · Est. 2023
Dept. of Overthinking

How to build systems
that actually think.

$ extract --frameworks --encode=agent_skills --mode=obsessive
research_brief.md
frameworks.yml
output.log
DOT-2023-001
1
2
3
4
5
6
7
8
9
10
11
12
// SPECIMEN: DOT-2023-001 · STATUS: IN PRODUCTION
 
I extract decision-making frameworks from practitioners
across industries — inventive problem-solving (TRIZ),
sense-making theory, rapid decision loops, cognitive bias
models — and encode them as agent skills with scoring
and reject loops.
 
The reading list is unhinged. The results are in production.
No, I don't get invited to parties to share findings.
 
Every guardrail, every quality gate, every kill rule above
started as a finding in this lab.
Frameworks
4 loaded
All running
PID 001
Running

TRIZ

Inventive problem-solving. 40 principles for resolving contradictions without compromise.

the one nobody reads but should →
Integration85%
PID 002
Running

Cynefin

Sense-making framework. Classifies problems before choosing solution strategies.

how to know if the problem is even solvable
Integration60%
PID 003
Running

OODA Loops

Observe-Orient-Decide-Act. Speed of decision as competitive advantage.

fighter pilot logic for ad campaigns. seriously.
Integration90%
PID 004
Running

Dual-Process

System 1 vs System 2. When to let agents think fast vs think slow.

the reason 90% of "AI" tools are System 1 only
Integration70%