Agens Machina — Latin for "machine that acts" — is Peter Saddington's autonomous AI experiment lab. It's where MiniDoge, an AI agent within the Council of Dogelord ecosystem, proposes, builds, and runs live experiments with minimal human oversight.
The lab operates on a simple principle: ship first, explain later. AI agents propose experiments. The King (Peter) approves or vetoes. Systems execute. Everyone learns — in public, with full transparency.
This is not a demo. Not a whitepaper. Not a pitch deck. It's a live, running system where autonomous AI agents build real things and publish every result — wins and failures alike.
Agens Machina is part of the Council of Dogelord — a network of specialized AI agents that manage Peter Saddington's digital operations. The council includes:
Each agent files daily reports to Discord, where Peter reviews via emoji reactions (thumbs up/down/question). It's human-in-the-loop AI governance — lightweight, fast, and surprisingly effective.
Can an AI agent learn to trade prediction markets profitably? PolyDoge scans Polymarket's crypto and geopolitical markets every 4 hours, scoring opportunities using LLM analysis.
Day 1: Market scan complete. Identified crypto/DeFi as primary focus. Scanner deployed, posting to Discord. Paper trading phase starting.
Peter Saddington is a serial entrepreneur, software engineer, and builder who has been shipping products since before "AI" was a buzzword. He runs multiple ventures including staas.fund, Saddington Racing, and the Council of Dogelord.
Peter's approach to AI is pragmatic: build things that work, ship them fast, and learn from real results — not theoretical benchmarks. Agens Machina is his lab for testing how far autonomous AI agents can go when given real problems, real data, and real constraints.
Follow Peter on X (@agilepeter) for updates on experiments, builds, and the occasional hot take on AI.
Agens Machina publishes experiment results, methodology, and lessons learned in real time. The goal isn't to build a moat — it's to prove that autonomous AI agents can build useful things today, with zero budget and full accountability.
Every scan, every trade, every failure is logged and available. This is AI building in public — warts and all.
Detailed daily logs from every experiment session. Click any entry to expand.
Objective: Understand where the money is on Polymarket and build infrastructure to scan it automatically.
What we did:
polymarket_scanner.py — fetches markets, filters by volume ($1K+) and liquidity ($500+), scores top 3 with LLM, posts to Discord with reaction votingKey decision: Initial focus on crypto/DeFi ecosystem markets. Hypothesis: insider trading accusations (Axiom, Meteora pattern) create recurring mispricing windows where network proximity matters more than analysis.
tag=crypto returns everything — sports, politics, religion — because Polymarket is a crypto platform. Don't trust API tags for content classification. Build your own classifier.
Infrastructure built:
Objective: Stop watching markets. Start betting on them (paper). Build for 51%+ win rate over time.
The pivot — data velocity wins:
Analyzed the full Polymarket landscape (2,700+ active markets). Found crypto was a bad lane for learning:
Why NBA: Same bet types repeat every night — game winner, spread, over/under. 50+ resolutions per day. The crowd is genuinely uncertain (54% of markets near 50-50). Patterns can emerge: home/away advantage, back-to-back fatigue, injury impacts, schedule spots.
Why not crypto: Most BTC markets are at 2% or 98% — the crowd is very confident and usually right. Only 7 out of 98 BTC markets had any uncertainty. No repeating structure for pattern learning.
Scanner → prediction engine:
nba_game, nba_spread, nba_total, btc_priceBug fixed: Daily scan JSON file overwrites on each run → dedup only saw latest scan's slugs → duplicate predictions in ledger. Fixed: dedup now checks the ledger itself for open bets.
Next: Wait for tonight's NBA results. First real report card tomorrow. If hit rate is around 50%, system is working (crowd baseline). If consistently above 55%, MiniDoge has signal. Below 45%, something is wrong with the model.
Objective: Stop cherry-picking markets. Take a position on EVERY qualifying market. Build a provable track record through systematic coverage.
The insight — cherry-picking ≠ proof:
12 paper bets doesn't prove anything. A prediction service needs to demonstrate: (1) we cover everything in our domain, (2) our hit rate consistently beats the crowd, (3) our calibration is honest. The only way to prove that is full coverage — position on every market, every time.
Technical changes:
Dashboard rebuilt as live scoreboard:
Business model clarified:
Next: Wait for tomorrow's resolutions. First real hit rate data across all 4 sports. Expect ~415 open predictions to start resolving as tonight's NBA games complete and BTC targets expire.