frAInk runs bounded, logged experiments with autonomous agents — researching, building, and acting in the real world. The pipeline plans, decides, and executes with real guardrails, real logging, and real money on the line. Nothing is faked. Everything is documented.

Planner

Read-only research layer. Fetches, analyzes, synthesizes. Never decides. Never acts.

Policy

The gatekeeper. Evaluates reports, enforces guardrails, approves or blocks. Never executes.

Executor

The action layer. Touches APIs, sends emails, logs experiments. Only acts on Policy-approved instructions.

Guardrails are non-negotiable. $100 max per cycle. $10 max single action. Kill switch. Policy approval required. Everything logged. Anomalies surfaced. Nothing buried.

Experiment Log
F007

CPI Bracket Predictions

Two CPI bracket bets placed. frAInk's first macro-economic prediction market play.

2026-04-10 TYPE 2 — Live Prediction Market Cost: $28.74 In Progress
F006

Chicago Weather — NO Rain

Second weather prediction. Settled WIN. +$5.40. Guard #6 reset to CLEAR.

2026-04-09 TYPE 2 — Live Prediction Market Cost: $4.60 Complete — WIN +$5.40
F005

Multi-City Weather Predictions

25 contracts across 5 cities. Testing broader market coverage and cushion sizing.

2026-04-05 TYPE 2 — Live Prediction Market Cost: $18.50 Complete — Mixed results
F003

First Live Kalshi Predictions

frAInk's first real money. $7.26 on Phoenix weather. The pipeline caught a bad thesis before it cost us.

2026-04-02 TYPE 2 — Live Prediction Market Cost: $7.26 Complete — WIN +$2.74
F002

First Full Paper Trading Day

5 stock trades, 2 Kalshi predictions, 1 stop-out. frAInk's first full day.

2026-03-30 TYPE 2 — Paper Trading (Full Day) Cost: $0.00 Complete
008

frAInk Joins the AI Chatroom

Claude and GPT-4o argue theory. frAInk argues from data.

2026-03-28 TYPE 3 — Social / Identity Cost: $0.00 Complete
007

Universe Scanner — frAInk Finds His Own Leads

A screener that only looks where you point it is half a screener.

2026-03-28 TYPE 2 — Capability Build Cost: $0.00 Complete
006

Kalshi Market Scanner — Revival

Exp 002 said economics markets were gone. They were closed on a weekend.

2026-03-29 TYPE 2 — Integration Rebuild Cost: $0.00 Complete
F001

Screener-Assisted Paper Trades — SOL + ETH

SOL closed at -$8.40. That's not failure — that's the system working.

2026-03-23 TYPE 2 Action — Paper Trading Cost: $0.00 Complete
005

Arbitrage Evaluation

47,000 people liked this arbitrage thread. frAInk checked the math.

2026-03-20 TYPE 4 — Article Evaluation Cost: $0.00 Complete
004

First Paper Trades — ABT / MU / DG

My AI agent placed its first paper trades autonomously.

2026-03-20 TYPE 2 Action — Paper Trading Cost: $0.00 Complete
003

First Live Market Data — SPY / QQQ / AAPL / NVDA

frAInk's first look at real market data.

2026-03-19 TYPE 1 Research Cost: $0.00 Complete
002

Kalshi Market Scanner

I built a market scanner. The market it was scanning no longer exists. (Corrected by Exp 006.)

2026-03-19 TYPE 2 Action — App Build Cost: $0.00 Complete
001

Kalshi Prediction Market Research

frAInk's first experiment. We had to start somewhere.

2026-03-18 TYPE 1 Research Cost: $0.00 Complete

Full experiment files live in github.com/letmebefraink/frAInk-lab/experiments — each one includes the full hypothesis, guardrails in effect, and the raw result.