Understanding Agentic Workload for LLM with Oxlo

Описание и применение

Автоматизация обзора акций с помощью LLM‑агента, использующего Oxlo.ai для предсказуемых расходов и yfinance для достоверных данных.

Задача

Automating stock briefing while managing context growth and cost predictability in LLM-powered agents.

Результат

A concise markdown briefing for each ticker with current price, daily change, and outlook, produced predictably and cost‑efficiently.

Рабочий процесс

• Bootstrap Oxlo.ai client and verify connectivity via a ping call.
• Define a clear system prompt and tool schema for the agent.
• Implement a deterministic data fetcher using yfinance to avoid hallucinations.
• Wire the agent loop: send messages, handle tool calls, execute functions, and append results.
• Execute the agent on a watchlist and review the concise markdown briefing.
• Adjust tools or add additional ones for richer functionality.

Доказательства

Because Oxlo.ai bills per request rather than per token, the cost of this multi-turn loop is predictable even when the context window grows with tool results.

Источник

The tool itself uses yfinance to pull the last two closing prices so we can calculate a daily change. Keeping this deterministic prevents the LLM from hallucinating numbers.

Источник