How the engine works: The swarm architecture

04/21/2026

To write better prompts, it helps to understand what happens when you hit “Generate.” Most consumer AI tools work linearly: You ask a question, and the LLM predicts the next most likely token based on its training data. In finance, this creates a hallucination risk. That’s why we built our architecture to separate intent from evaluation.

Intent parsing: When you type a prompt, a primary agent analyzes your text to extract specific financial constraints, sector themes, and exclusion criteria.
The evaluation swarm: The system then dispatches a concurrent swarm of evaluation agents. Imagine 5,000 analysts working in parallel. Each agent is assigned specific assets to evaluate against your criteria using real-time and historical market data.
Construction and weighting: The results are aggregated, scored for relevance, and constructed into a weighted index.

Because of this architecture, the AI flourishes when you give it specific, multi-factor instructions. It doesn’t just “guess” good stocks; it screens for them based on the logic you provide.

A complete walkthrough: From prompt to evaluation to index

Here is an example of a full prompt, the system’s interpretation, and the resulting index. This mirrors how the swarm architecture works behind the scenes.

User prompt:

“Take the S&P 500 and remove low cash flow companies. Include companies with exposure to AI infrastructure, semiconductor supply chains, and data-center operations.”

Intent extracted:

Base universe: S&P 500

Exclude: Companies with weak or negative free cash flow

Signals: AI infrastructure, semiconductor supply chains, data centers

Evaluation phase:

- 500 companies evaluated across cash-flow health, fundamentals, revenue

  drivers, product exposure, supply-chain positioning, and historical

  sector linkages.

- 143 companies match the “AI infrastructure” definition.

- 58 companies removed due to low or negative free cash flow.

- Remaining candidates screened for thematic and financial criteria.

Final index:

28 holdings

- Top weights: MSFT, KLAC, SMCI, ANET, CDW

- Evidence provided for each holding (excerpt below)

Example holding rationale:

“Microsoft is a leading provider of AI infrastructure through its Azure cloud platform, operates extensive global data centers, and is deeply involved in the AI ecosystem, making it an obvious match for significant exposure to AI infrastructure and data-center operations.”

Please note that LLMs are stochastic, meaning the system may produce slightly different results each time, especially when a company sits on the edge of your criteria. Behind the scenes, we mitigate this by evaluating multiple passes and averaging the outcomes.