Research 0
Research

Research

Independent AI researcher · ORCID 0009-0003-8679-1981

Research Areas
  • AI Systems

    How models, data and tools fit together into reliable systems.

  • Automation Thinking

    Where automation saves effort, and where it does not.

  • Intelligent Workflows

    AI designed around how people learn and work.

  • Scalable Architectures

    Designs that keep working as use grows.

Doctoral research

PhD · upcoming
Proposed thesis

Artificial Intelligence for the Computational Analysis of Cosmological Data and Ancient Astronomical Knowledge

This doctoral project asks how modern AI methods can help analyse cosmological observations and, separately, how they can help study and verify astronomical knowledge recorded in ancient texts and traditions. The work keeps a strict line between four kinds of content: scientific evidence, historical interpretation, hypothesis and tradition.

Objective 1Learn from sky data

Apply machine learning to public cosmological and astronomical datasets for pattern finding and classification.

Objective 2Read ancient sources

Use NLP to structure astronomical statements from ancient texts (including Sanskrit sources) into a searchable dataset.

Objective 3Test, don't assume

Compare recorded claims with computed sky positions and modern data, reporting agreement and disagreement openly.

Planned methods
  • Machine learning on open astronomy datasets
  • Multilingual NLP and knowledge extraction
  • Astronomical computation of historical sky positions
  • Transparent evaluation and labelled evidence levels
Status & next steps
  • Status: proposed. No results are claimed yet.
  • Literature review and dataset survey
  • Pilot study design
  • Seeking a doctoral supervisor and collaborators

Current project

Since Sep 2026

AI Doubt-Solving Assistant for Hindi and English Learners

RQ1 · Language gap

Does answer quality differ between Hindi and English questions?

RQ2 · Grounding

Does grounding answers in course notes (RAG) reduce errors?

RQ3 · Trust

Do learners find grounded answers more trustworthy?

Method: 50 bilingual doubts answered with and without retrieval, scored with a rubric. Data, code and a paper will be published openly.

RAGMultilingual NLPAI in EducationEvaluation
Dataset & code ↗

Publications

Books · papers · data
2026 · Book
Build Your First AI Models: A Hands-On Beginner's Guide to Machine Learning with Python

S. Tekriwal. AI Model Making: Basic to Advanced, Vol. 1.

2026 · Dataset
Bilingual (English–Hindi) learner doubts dataset, v1

50 questions for evaluating grounded AI answers.

In prep · Paper
Grounded AI answers for Hindi and English learners

First paper from the doubt-solving project; listed here once submitted.

Research log

Sep 2026
Project started

Registered ORCID iD · defined scope and three research questions · built a first 50-question bilingual dataset.

Nov 2026
Book 1 published

Build Your First AI Models, free to read online.

Next
Baseline & rubric

Baseline answers and an evaluation rubric.

Cite this book

APA

Tekriwal, S. (2026). Build Your First AI Models: A hands-on beginner's guide to machine learning with Python (AI Model Making: Basic to Advanced, Vol. 1). Sachin Tekriwal AI Research & Education Center.

BibTeX

@book{tekriwal2026buildfirstai,
  author    = {Tekriwal, Sachin},
  title     = {Build Your First AI Models: A Hands-On Beginner's Guide to Machine Learning with Python},
  series    = {AI Model Making: Basic to Advanced},
  volume    = {1},
  year      = {2026},
  publisher = {Sachin Tekriwal AI Research \& Education Center},
  url       = {https://memy.sachintekriwal.com/book/}
}
P
PihuYour guide