The Handler-Agent Model
Engram separates human and machine roles. The agent handles everything that scales: scanning hundreds of markets, computing technical indicators, pulling cached positioning and on-chain data, detecting behavioral patterns, logging snapshots, and generating diff summaries. None of this requires language model inference at scan time. All of it is deterministic computation against APIs and local data – LLM reasoning is invoked only for the filtered shortlist. The handler provides what does not scale: a thesis explaining why a trade makes sense right now, corrections when an agent’s setup misfires due to nuanced sentiment shifts, context for events not yet in the quantitative data, and a closing reflection on what the trade revealed.The Trade Flow
1. Agent Scans
The agent continuously monitors 200+ markets on Hyperliquid. A pre-filter pipeline computes technical indicators locally before invoking the language model. This reduces inference costs by roughly 99%, since only a filtered shortlist of 5-10 candidates requires LLM analysis.2. Agent Proposes
When the agent identifies a setup that meets its criteria, it presents a structured trade proposal to the handler:- Asset pair and direction (long/short)
- Entry price, stop loss, take profit
- Leverage and position size
- Risk as percentage of equity
- Reasoning – which data layers support the thesis
3. Handler Decides
The handler reviews the proposal and responds:- Approve – Execute as proposed
- Modify – Adjust parameters (move the stop, reduce size, change target)
- Reject – Pass on this setup
- Discuss – Ask the agent questions before deciding
4. Lesson Captured
At position open, the agent captures a snapshot of market state across 15 categories (140 fields). At position close, it captures an identical snapshot and computes the difference. What changed in volume, funding rates, open interest, whale cohort positioning, sentiment, and smart money flows between entry and exit? This diff, combined with the trade outcome and the handler’s reasoning, produces a structured lesson.5. Intelligence Compounds
Lessons sync to the central library. Pattern discovery tooling surfaces candidate patterns through statistical significance testing, embedding-based clustering, and feature importance analysis. A curation team validates these candidates through backtesting, confirms statistical robustness, and encodes proven patterns into shared skill files that all agents receive. When a skill file improves, every agent in the network improves simultaneously.Handler Feedback Channels
Handler feedback enters the system through five channels of increasing friction and value:| Channel | Friction | Value | Description |
|---|---|---|---|
| Trade decisions | Low | Medium | Approve or reject setups through the conversational interface |
| Corrections | Low | High | Override agent behavior (move stops, adjust size) - logged automatically |
| Context messages | Medium | High | Share information the agent cannot observe |
| Lesson ratings | Medium | Medium | Evaluate contributions from other handlers |
| Weekly reviews | High | Very High | Structured reflections surfacing calendar-aware risk factors and broader narratives |