·
ai private equity experiments
The Principal and the Swarm
How AI agents turned one investor into a research firm, and what the experiments found. An overview of eight AI native intelligence experiments built from scratch in days.
Ankit Chandola
Experimenting at the intersection of AI, investing, and business / systems intelligence. Writing about its impact from 20 feet to 20,000 feet.
Principal at Queens Court Capital, a special situations PE firm. Previously H.I.G. Capital, Comvest Partners, and Fidus Capital. Michigan Ross BBA.
Interested in the systems or the thinking behind them?
Get in touch →PE & Credit
12+ years
Capital Deployed
$4B+
AI Experiments Built
10+ experiments
How it works
One principal. Many specialists.
One principal directs the work. Stable associates handle writing, analysis, engineering, and audit. A wider specialist bench comes in when needed. The tools matter; what matters more is judgment, agency, and the ability to drive execution.
Project Workspace
Claude Code
Separate harness
Orchestration · Principal
Frontier Reasoning Model
Routes tasks, manages context, coordinates the team
OpenAI Codex
Separate harness
Adjacent workstreams in the same project workspace.
Associates
Creative
Writing, design, strategy
Analysis
Research, analysis, fast iteration
Engineering
Code, debugging, architecture
Audit
QA, review, verification
Specialist Pool · On-Demand
Gemini Grok Kimi Minimax Claude GPT 5.4 + Others
Open-source and frontier models on US servers, called when specialized capabilities are needed.
The infrastructure is OpenClaw and Hermes agents, open-source orchestration layers. The system remembers context across sessions, can be reached from anywhere, and spawns specialized sub-agents whose work gets reviewed before it counts. The principal reviews every associate's work and respawns with corrections, like marking up a teammate's draft before it ships.
The entire system runs on a laptop. What remains expensive is judgment, agency, and the ability to drive execution: framing the problem, asking the right questions, and directing specialized intelligence where it matters most.
Selected Experiments
What the system produces
10+ experiments built from scratch with AI agents across investing, trading, and research infrastructure. No team. No subscriptions. No consultants.
🏗️
Business Intelligence Chicago Permit Velocity
Permit timing isn't one Chicago market. This tracks where approvals move fastest, where they stall, and which neighborhoods are improving.
Neighborhood intelligence
7.7×
spread between the fastest and slowest permit markets in the same city
Median
42d
Ranked
75
Fastest → slowest
Citywide median marker at 42 days threshold-adjusted
10,047 permits · 77 areas · momentum matters more than snapshot
🧬
Swarm Intelligence 100 AI Analysts Debate Peloton
Structured adversarial simulation. 100 agents with competing incentives. Five rounds of debate. Convergence reveals fragility.
Round 1 — the debate starts dispersed, with only a slight bearish edge.
55% bearish R1
Scroll-in animates once. Controls let you jump back.
91% bearish convergence · 5 rounds · 8.9/10 confidence
📊
Trading System Self-Teaching Options System
Three-layer architecture that taught itself to sell volatility. Nightly learner loops. Runs in production daily.
96.3% win rate · 41K lines · runs daily
📍
Local Intelligence Local Market Pricing Intelligence
A competitive intelligence system for fragmented service markets — pricing, review signals, and geographic tradeoffs synthesized into operator-grade local positioning.
Price Position P0
Review Signal 0/100
Geo Stickiness 0m
38 facilities · 165 reviews · 1,800 geo checks
⚡
Other Experiments
Roll-Up Readiness Index — metro ranking for PE consolidation targets
Brand Expansion Radar — competitive whitespace detection across markets
Autonomous Research Digests — daily AI-curated intelligence briefings
10+ experiments shipped so far, with more in flight.
Two Altitudes
The experiments are the 20-foot view — what I'm building. The essays are the 20,000-foot view — what it means when anyone can.
🔬 20 ft
The Builds
Specific systems. Real data. Working code. What happens when you point AI agents at a concrete problem and let them run.
The Principal and the Swarm →☁️ 20,000 ft
The Shifts
Economics, structure, and what changes when the cost of building intelligence drops to zero. The patterns behind the experiments.
The New Stable Orbits →The 20,000-foot view asks what's possible. The 20-foot view builds it.
Writing
View all →
Latest essays and field notes
🔬 20 ft
☁️ 20,000 ft
·
AI Economics Writing
The New Stable Orbits
How AI is rewriting which businesses can exist, and quietly opening the door to millions of new ones.