Skip to main content

Investing Team

Can a team of specialized AI agents outperform a solo human investor?

DeFi maths not as hard as you think.

Agent Roles

Each agent has a defined job, specific data sources, and clear output format.

RoleJobData SourcesOutput
Valuation AgentCalculate intrinsic value, flag mispricingOn-chain metrics, DeFi Llama, token terminalFair value estimate + confidence band
Sentiment AgentGauge market mood, detect narrative shiftsSocial media, funding rates, fear/greed indexSentiment score (-1 to +1) + trend direction
Fundamentals AgentAnalyze protocol health and growthRevenue, TVL, active users, developer commitsHealth scorecard + growth trajectory
Technicals AgentIdentify entry/exit timing signalsPrice action, volume, on-chain flow dataSignal (buy/sell/hold) + strength rating
Risk ManagerSet position limits, monitor exposurePortfolio composition, correlation matrix, VaRMax position size + portfolio risk score
Portfolio ManagerMake final decisions, generate ordersAll agent outputs + human-set constraintsTrade orders with reasoning

Interaction Model

Signal aggregation, not majority vote:

  • Each agent publishes a signal with confidence level
  • Portfolio Manager weighs signals by historical accuracy, not equally
  • Conflicting signals trigger deeper analysis, not paralysis
  • Risk Manager has veto power — can block any trade that violates portfolio constraints

Conflict resolution:

  • When Valuation says "cheap" but Sentiment says "fear" — that's opportunity. Size appropriately
  • When Technicals says "buy" but Fundamentals says "deteriorating" — that's a trap. Pass
  • When all agents agree — that's either genuine conviction or a crowded trade. Check contrarian indicators

Failure Modes

AgentFailure ModeSymptomFix
ValuationStale model assumptionsFair value hasn't updated despite market regime changeForce model refresh on macro trigger events
SentimentEcho chamber dataAll sources agree because they read each otherAdd contrarian sources, weight primary data higher
FundamentalsLagging indicatorsMetrics report past, not futureWeight leading indicators (dev activity, governance proposals)
TechnicalsOverfittingPerfect backtests, poor live performanceOut-of-sample validation, reduce indicator count
Risk ManagerOver-conservativeBlocks every trade, portfolio goes staleDynamic risk limits based on volatility regime
Portfolio ManagerDecision paralysisConflicting signals cause inactionTime-box decisions, default to smallest safe action

Human Override

The human investor remains the outer loop. Override the agent when:

  • Macro regime change — Agents trained on historical data can't anticipate unprecedented events (new regulation, protocol exploit, geopolitical shock)
  • Ethical boundary — Agent recommends a position in a project you don't trust or that conflicts with your values
  • Information asymmetry — You have private context (upcoming partnership, insider insight) that agents don't
  • System failure — Agent outputs are contradictory, stale, or obviously wrong. Shut down and diagnose before trading

Rule: If you override more than 30% of agent recommendations in a month, either the agents need retraining or you need to trust the system more. Track which is right.

Trading Stack

  • Execution: Jupiter APIs for token swapping, Meteora/Orca for LP positions
  • Data: Helius for transaction management, Switchboard oracles for market analysis
  • Speed: Jito Bundles for reliable execution, Helius RPC for priority fees
  • Inference: Kuzco for on-chain inference payments

Context

Questions

If a team of specialized agents can process more data and act faster than a solo investor, what unique value does the human bring to the loop?

  • When agents disagree, is the Portfolio Manager actually resolving the conflict or just picking the signal it agrees with?
  • What happens when all agents are trained on the same historical data and a genuinely novel event occurs?
  • At what portfolio size does the cost of running an agent team justify itself over manual management?