AI for Deep Research: Intelligent Tools and Workflows
Overview
This hands-on session explores how AI agents and copilots transform research – from discovery and synthesis to data-driven insight generation. Through guided demonstrations, participants will learn how to conduct advanced searches, organize knowledge, and analyze supporting datasets using Perplexity AI, ChatGPT (Agent Mode), Google NotebookLM, Microsoft Copilot for Excel, and Python in Google Colab. The class emphasizes how to turn questions into structured, verifiable, and data-supported answers.
This course is included in the AI Annual Learning Pass.
Schedule
Register 21 days before class start date and save 10%! Enter discount code EARLY10 during registration.
Duration: 2 hours
Dates
Times
Location
Price
Who Should Take This Course
Audience
- Researchers, analysts, and data professionals needing faster information and data synthesis
- Educators and students conducting research projects or literature reviews
- Knowledge workers and consultants who regularly prepare reports or policy briefs
- Anyone looking to combine AI reasoning with data analysis for evidence-based insight
Why You Should Take This Course
Learning Objectives
After completing this session, participants will be able to:
- Describe how AI tools support deep research and data-driven reasoning.
- Use Perplexity AI for multi-source discovery and citation-based synthesis.
- Demonstrate ChatGPT Agent Mode for iterative questioning and structured insight generation.
- Apply Google NotebookLM for organizing and cross-referencing research materials.
- Analyze research data using Microsoft Copilot for Excel (Advanced Mode) and Python in Google Colab.
- Evaluate which AI tools best fit specific research and data validation needs.
Course Outline
AI for Deep Research: Intelligent Tools and Workflows
1. Concept Review
- Defining “deep research” in the AI era
- From retrieval to reasoning to evidence – how modern agents construct knowledge
- Roles of memory, multi-document synthesis, and data augmentation
2. Demos: AI Research in Practice
Goal: Showcase how agentic AI tools handle complex research and data tasks.
- Demo 1 – Perplexity AI:
-
- Perform multi-source literature search with citations and linked references
- Use Pro features (Copilot mode, Collections, Comet browser integration)
- Demo 2 – ChatGPT (Agent Mode):
-
- Build a “Research Assistant” agent for iterative Q&A and source analysis
- Show file uploads, memory, and reasoning chains
- Example: Summarize and compare policy or scientific topics
- Demo 3 – Google NotebookLM:
-
- Import PDFs or notes to summarize and link insights
- Demonstrate cross-referencing and traceability of findings
- Demo 4 – Microsoft Copilot for Excel (Advanced Mode):
-
- Analyze research datasets or survey data directly in Excel
- Use Copilot to create summaries, charts, and insights from raw data
- Show how Copilot bridges natural language and quantitative analysis
- Demo 5 – Python in Google Colab:
-
- Use Colab to clean, analyze, and visualize a dataset from Perplexity/NotebookLM findings
- Demonstrate lightweight Python for validation (e.g., text analysis or data correlation)
3. Discussion & Takeaways
- Comparing transparency, data depth, and ease of use across tools
- Balancing automation with critical thinking and source verification
- Designing a personalized AI “Research Stack” and data pipeline
- Future direction: integrating agents (n8n, Opal) for automated research loops
4. Wrap-Up + Q&A