Leanpub Header

Skip to main content

AI Agents for Researchers

The instructor has published 100% of this course.Last updated on 2026-11-21

Learn to use AI agents at every stage of research, from literature and systematic reviews to data, analysis, and writing, without fabricated citations or unverified results. A quiz in every lesson and a certificate.

Minimum price

$39.00

$58.99

You pay

Author earns

$

Also available for 1 course credit with a Learner Membership

PDF
EPUB
WEB
About

About

About the Course

AI Agents for Researchers is a practical online course for graduate students, academics, and research professionals in any field who want to use AI agents across the whole research lifecycle.

In 12 lessons you follow a research project from question to publication:

  • Foundations: what agents change about research, models and tools, and how to direct an agent with clear, bounded tasks.
  • Evidence: grounded literature search, honest absence instead of invented citations, and agent-assisted systematic reviews.
  • Data and analysis: acquiring and cleaning data with provenance, verified analysis, and interpretation that claims no more than the evidence allows.
  • Writing and integrity: drafting from your real findings, reproducible pipelines, accountability, disclosure, and the future of research with agents.

The discipline throughout is verify, don't trust. Each lesson ends with a marked quiz (72 questions in total). Score 70% or more to earn your certificate of completion.

Share this course

Instructor

About the Instructor

Kompri

Kompri is an academic, author, investor, and educator based in Jambi, Indonesia. He holds a doctorate in Education Management and a bachelor’s degree in Physics, and has written and published dozens of books along with numerous other scholarly works. An avid reader, he is one of today’s most productive researchers. Alongside his academic career, he publishes both theoretical and practical books for readers around the world. His work rests on one conviction: knowledge is most valuable when it is clear, usable, and shared, so that anyone, in any country, can put it to work.

Material

Course Material

  • Welcome to the Course

  • How the Course Works

  • Earning the Certificate

  • Chapter 1: What AI Agents Mean for Research

  • 1.1 A New Kind of Research Collaborator

  • 1.2 What an Agent Is, and Is Not

  • 1.3 The Research Lifecycle, and Where Agents Fit

  • 1.4 The Promise: Speed, Scale, and Breadth

  • 1.5 The Peril: Fluent, Confident Error

  • 1.6 The Discipline of This Book: Verify, Don’t Trust

  • In Practice — The AI Scientist, and the limits of autonomy

  • Key Takeaways

  • References

  • Lesson 1 Quiz

    10 attempts allowed

  • Chapter 2: The Researcher’s Agent Toolbox

  • 2.1 The Model at the Core

  • 2.2 Tools: How an Agent Acts

  • 2.3 Retrieval and Grounding: The Most Important Tool

  • 2.4 Code Execution and the Analysis Environment

  • 2.5 Your Existing Tools as Agent Tools

  • 2.6 Choosing and Combining Tools

  • In Practice — The Model Context Protocol and the connected agent

  • Key Takeaways

  • References

  • Lesson 2 Quiz

    10 attempts allowed

  • Chapter 3: Asking the Right Question: Prompts, Context, and Scope

  • 3.1 Directing, Not Commanding

  • 3.2 Framing a Research Question an Agent Can Help With

  • 3.3 The Anatomy of a Good Prompt

  • 3.4 Context Engineering: Giving the Agent What It Needs

  • 3.5 Decomposing a Project into Agent-Sized Tasks

  • 3.6 Keeping the Human in the Loop

  • In Practice — “Lost in the Middle” and the shape of attention

  • Key Takeaways

  • References

  • Lesson 3 Quiz

    10 attempts allowed

  • Chapter 4: Searching and Reviewing the Literature

  • 4.1 Why Literature Search Is Hard

  • 4.2 Searching by Meaning

  • 4.3 Grounded Literature Review

  • 4.4 The Citation Trap

  • 4.5 Reading and Summarizing at Scale

  • 4.6 Building a Trustworthy Bibliography

  • In Practice — Mata v. Avianca: the warning every researcher should know

  • Key Takeaways

  • References

  • Lesson 4 Quiz

    10 attempts allowed

  • Chapter 5: Screening, Extraction, and the Systematic Review

  • 5.1 What a Systematic Review Demands

  • 5.2 The Systematic Review Workflow with Agents

  • 5.3 Screening at Scale

  • 5.4 Structured Data Extraction

  • 5.5 Cross-Study Synthesis

  • 5.6 Rigour, Documentation, and the Human Override

  • In Practice — Cochrane’s RCT Classifier: machines and the crowd

  • Key Takeaways

  • References

  • Lesson 5 Quiz

    10 attempts allowed

  • Chapter 6: Gathering and Managing Research Data

  • 6.1 What Gathering Data Involves

  • 6.2 Collecting Data with Agents

  • 6.3 Cleaning and Wrangling the Mess

  • 6.4 Managing Data: Provenance and the Audit Trail

  • 6.5 Data Ethics, Privacy, and Consent

  • 6.6 Reproducible Data Work

  • In Practice — The Reinhart-Rogoff spreadsheet and a missing five rows

  • Key Takeaways

  • References

  • Lesson 6 Quiz

    10 attempts allowed

  • Chapter 7: Agents for Data Analysis

  • 7.1 What Analysis Asks of Data

  • 7.2 Agents as Analysis Collaborators

  • 7.3 The Statistics Must Be Verified

  • 7.4 Exploratory Analysis and the Garden of Forking Paths

  • 7.5 Visualization and Honest Presentation

  • 7.6 Reproducible Analysis

  • In Practice — Many analysts, one dataset: how analytic choices move the result

  • Key Takeaways

  • References

  • Lesson 7 Quiz

    10 attempts allowed

  • Chapter 8: Interpreting Results and Avoiding the Traps

  • 8.1 From Result to Meaning

  • 8.2 Correlation, Causation, and the Agent’s Confident Story

  • 8.3 Statistical Significance Is Not Importance

  • 8.4 A Tour of the Traps

  • 8.5 What the Result Does Not Say

  • 8.6 Honest Interpretation with Agents

  • In Practice — Hormone therapy and the heart: when the correlation lied

  • Key Takeaways

  • References

  • Lesson 8 Quiz

    10 attempts allowed

  • Chapter 9: Writing the Paper with Agents

  • 9.1 What Scientific Writing Is For

  • 9.2 Agents as Writing Collaborators

  • 9.3 Drafting Without Losing Your Voice or Your Facts

  • 9.4 The Integrity Line: Authorship, Accountability, and Disclosure

  • 9.5 Citations, Plagiarism, and Fabrication

  • 9.6 Revision, Peer Review, and the Honest Paper

  • In Practice — “Certainly, here is a possible introduction”: AI in the literature

  • Key Takeaways

  • References

  • Lesson 9 Quiz

    10 attempts allowed

  • Chapter 10: Reproducibility and Open Science with Agents

  • 10.1 Why Reproducibility Is the Foundation

  • 10.2 What a Reproducible Result Requires

  • 10.3 Agents for Reproducible Pipelines

  • 10.4 Open Science: Data, Code, and Preregistration

  • 10.5 The Hazards Agents Introduce—and Can Fix

  • 10.6 Building Reproducibility In

  • In Practice — One hundred studies, thirty-six that held

  • Key Takeaways

  • References

  • Lesson 10 Quiz

    10 attempts allowed

  • Chapter 11: Research Integrity and Responsible Use

  • 11.1 What Research Integrity Requires

  • 11.2 The Line Between Use and Misconduct

  • 11.3 Accountability That Cannot Be Delegated

  • 11.4 Bias, Fairness, and Harm

  • 11.5 Transparency and Disclosure

  • 11.6 Building a Responsible Practice

  • In Practice — Diederik Stapel: fabrication, and the accountability no one escapes

  • Key Takeaways

  • References

  • Lesson 11 Quiz

    10 attempts allowed

  • Chapter 12: The Road Ahead

  • 12.1 What Is Changing, and Fast

  • 12.2 What Will Not Change

  • 12.3 The Researcher’s Evolving Role

  • 12.4 What to Cultivate

  • 12.5 The Research That Becomes Possible

  • In Practice — AlphaFold: what the partnership can achieve

  • Key Takeaways

  • References

  • Lesson 12 Quiz

    10 attempts allowed

  • Glossary

  • Bibliography

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub