← back
Build an AI Research Agent: Apoorva Joshi
Takeaway
Use agents only when the task truly needs multi-step reasoning, tools and memory — and pick ReAct or Reflection patterns to keep the planning loop tractable.
Summary
- Workshop defines agents as LLMs that reason, plan and execute via tools, contrasting them with prompting, RAG and simple chat.
- Decision rubric: agents are warranted for complex multi-step tasks needing aggregation, visualization, and personalization — not for trivia or single-doc Q&A.
- Walks through planning patterns: Chain-of-Thought, Tree-of-Thoughts, ReAct, and Reflection, with ReAct used in the hands-on lab.
- Components covered: planning/reasoning, memory (short and long-term in MongoDB), and tools; the lab builds an AI research agent end-to-end.
- Lead instructor is a MongoDB DevRel with prior cybersecurity ML experience.
agentsreactmongodb
Original description
In this 2 hour workshop, we will build an AI research agent that can search for research papers, summarize them, and answer questions on topics based on past research. We will use MongoDB as the agent's memory provider and knowledge store, open-source LLMs as the agent’s “brain”, and LangChain to orchestrate the end-to-end agentic workflow. Attendees will be provided with all the resources required to successfully execute the hands-on portions of the workshop, including a GitHub repository consisting of notebook templates with pseudocode. Attendees will replace the pseudocode with their own code during the workshop. For this workshop, attendees will need basic to intermediate knowledge of Python, and a laptop with the latest version of Python installed. The preferred environment for running the labs is Google Colab, but for those who would prefer a local setup, instructions can be found here: https://mongodb-developer.github.io/ai-agents-lab/docs/dev-env/dev-setup#local-setup Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Apoorva Apoorva is a Data Scientist turned Developer Advocate, with 6 years of experience applying Machine Learning to problems in Cybersecurity, including phishing detection, malware protection, and entity behavior analytics. As an AI Developer Advocate at MongoDB, she now helps developers be successful at building AI applications via written content and workshops.