Jeannie: An Agentic Field Worker Assistant
summary
Jeannie is an agentic field assistant that combines task preparation PDF generation via Playwright with SQLAlchemy database calls, external weather APIs, document retrievers and LLMs (OpenAI + Llama family experiments) under a hybrid workflow+agent architecture. A live demo generates a one‑page briefing and turns a voice description into a structured incident report that the system inserts into the DB (demo showed ID 41), dropping a ∼30‑minute manual report to a short conversation; frontend uses Chainlit and deployment runs on Azure.
AI-written summary · about
chapters (8)
- 0:00Jeannie introduction
- 1:12Genie’s evolution
- 8:39Field worker challenges
- 11:47Task prep with Genie
- 13:13Agents vs workflows
- 15:28Live demo task prep
- 19:38Agentic AI impact
- 20:42Q&A
related talks
40mAI Agents in Practice
49mAI Agents: Collaboration in Real-Life Applications
36mBuilding Agentic AI Assistants: Lessons from productionising agents in Preclinical R&D
24mAgentic Al in SW Development: Evolving Patterns & Protocols
41mBuilding LLM Agents – Challenges and Learnings
40mAgents in Action: Advancing Open Source AI Missions
22mThe AI-augmented leader: Architecting your own virtual chief of staff
32mBuilding an Advanced Knowledge Assistant