I built a company of bots

Описание и применение

Система Botropolis демонстрирует, как 20 специализированных агентов, распределённых по 10 департаментам и управляемых CEO‑агентом, могут эффективно обрабатывать запросы, используя YAML‑спецификации, аналитики и пайплайн обучения с LoRA.

Задача

Organizing multiple specialized agents into a coherent, company‑like structure to handle diverse tasks efficiently.

Результат

The system demonstrates that proper routing, agent specification, and analytics enable a scalable, company‑like agent ecosystem, though the demo‑scale research model is limited in factual reliability.

Рабочий процесс

• 1. User submits a request to the FastAPI server. 2. CEO agent parses the request and determines the relevant departments. 3. CEO routes the request to the appropriate specialist agents. 4. Each specialist agent processes its part and returns results. 5. CEO aggregates results into a single report. 6. Report is returned to the user via the browser UI.
• 7. Analytics track per‑agent calls, latency, and token usage for future optimization.

Доказательства

Botropolis: 20 specialist agents across 10 departments. Research has Scout. Code has Coder and Reviewer. Finance, legal, health, data, marketing, ops, security, support all have their people.

Источник

The CEO agent reads your request, routes it to the right departments, runs them, and compiles one report.

Источник

Each agent is a YAML spec: name, title, specialty, model, tools, system prompt, example tasks.

Источник

I trained botropolis-scout-tiny, a 5.5M-parameter transformer, from scratch on CPU on 300 synthetic Q&A pairs.

Источник

The part I am proudest of is the training pipeline. I trained botropolis-scout-tiny, a 5.5M-parameter transformer, from scratch on CPU on 300 synthetic Q&A pairs.

Источник

Usage analytics change how you build. Once you see per-agent latency and tokens, you start routing like a manager watching a budget.

Источник