Build.
Test.
Measure.
Learn.
Dhanvi Experiments is a growing record of the simulations, prototypes and system tests conducted while building Dhanvi. We publish favorable and unfavorable results alike.
This is a development research log — not a performance record.
System evolution in public.
Each experiment evaluates a distinct technical question within the platform architecture.
MULTI-AGENT PAPER TRADING
- 5 specialized agents
- 459 opportunities evaluated
- 33 selected trades
- +1.89% single-session simulated result
EMA MOMENTUM REVERSAL BACKTEST
- 1 defined strategy
- 72 daily bars
- 2 simulated trades
- -0.88% backtest result
EARLY STRATEGY GENERATION BACKTEST
- Historical strategy research
- Early research milestone
- Limited historical metadata
- ~24% historical backtest return
Different experiments. Different questions. One growing research record.
Multi-Agent Paper Trading
Testing whether specialized AI agents could coordinate across research, analysis and simulated trading during a complete market session.
EMA Momentum Reversal Backtest
A controlled historical backtest of the DHA-DEMO-EMA-MOM strategy on RELIANCE.NS, testing execution behavior, costs and strategy performance across 72 daily bars.
Early Strategy Generation Backtest
One of Dhanvi’s early strategy-generation experiments produced approximately 24% return in historical backtesting, motivating the development of a substantially more rigorous research and validation architecture.
Upcoming Research
Upcoming experimental simulation in development.
The research continues.
Experiment 001 tested multi-agent coordination in a paper-trading session.
Experiment 002 tested a defined strategy inside Dhanvi's historical backtesting engine.
Experiment 003 explored early algorithmic strategy generation.
More experiments will be published here as Dhanvi develops.