Low-Code Data Scientist: Building AI Agents and Systems Without Writing Code



Overview

UPDATE: following its recent release, this course will cover OpenAI's GPT-5 and its applications for full-stack AI development from a low-code (AI-assisted) perspective.

Empower Your Future with AI: No Coding Required 

"AI won't take your job, but someone using AI might." This statement has never been more relevant. With the rapid rise of Generative AI tools like ChatGPT, the way we build software is evolving and natural language is becoming the new programming interface. 

This transformation opens up exciting possibilities for domain experts. By combining their existing knowledge with AI tools, professionals can now build intelligent systems without writing traditional code. This course is designed to help you do exactly that. 

Who Is This Course For? 

This course is ideal for professionals who are not developers but want to better understand artificial intelligence and make use of AI in their roles. No coding or prior AI experience is required; anyone who is IT literate can take this course. Typical participants include: 

  • Business analysts 
  • Account managers 
  • Technical architects 
  • Data analysts 
  • Project managers 
  • IT sales and pre-sales professionals 
  • Media and PR specialists 
  • Network and systems administrators 

Learning Outcomes 

Grounded in the principles of prompt engineering and AI collaboration, this course focuses on building real-world AI solutions using low-code tools and large language models (LLMs) such as ChatGPT. 

You will explore three core themes: 

  1. Building AI-driven applications using generative models 
  2. Designing and deploying AI agents with low-code workflows
  3. Developing full-stack AI systems without traditional coding 

You are not expected to write code, although some demonstrations may include coding for illustrative purposes. The emphasis is on using natural language and low-code platforms to harness the power of AI. The main tools/platforms used are Langflow, Lovable and OpenAI.

This course will cover OpenAI's recently released GPT-5 and its applications for full-stack AI development from a low-code (AI-assisted) perspective.

By the end of this course, you will be able to: 

  • Build AI applications using machine learning and deep learning models 
  • Design and deploy AI agents using low-code tools
  • Create end-to-end AI solutions without needing to become a developer 

Dates, Times and Delivery

This online taught course will run from 24 November - 10 December 2025. Tutorials will be delivered via Microsoft Teams on Mondays, Wednesdays and Fridays from 14:00 - 18:00 (UK time).

Session Dates:

  • Monday 24 November
  • Wednesday 26 November
  • Friday 28 November
  • Monday 1 December
  • Wednesday 3 December
  • Friday 5 December
  • Monday 8 December
  • Wednesday 10 December

A world clock, and time zone converter can be found here: https://bit.ly/3bSPu6D

No attendance at Oxford is required and you do not need to purchase any software.

Accessing Your Online Course 

Details about accessing the private MS Teams course site will be emailed to you during the week prior to the course commencing.  

Please get in touch if you have not received this information within three working days of the course start date. 

Programme details

The following topics will be covered over the course of eight online sessions: 

Foundations of Artificial Intelligence 

  • Core concepts and historical evolution of AI 
  • Introduction to machine learning (ML) and deep learning 
  • Understanding the AI development pipeline 
  • Understanding reasoning, planning and autonomy in AI systems 

Introduction to Low-Code AI Ecosystems 

  • What is low-code/no-code AI? 
  • Overview of platforms: OpenAI, LangFlow, Azure AI Studio, Supabase, Lovable.dev 
  • Other low code tools and platforms: ex Zapier, Make  
  • The role of the Low-Code Agentic Product Manager 
  • Forward deployed engineer and the low-code AI ecosystem 

Understanding and Using Large Language Models (LLMs) 

  • LLM fundamentals: transformers, tokens, embeddings 
  • LLM capabilities and limitations 
  • LLMs as reasoning engines 
  • Retrieval-Augmented Generation (RAG) and hybrid architectures 

Prompt Engineering and Context Design 

  • Prompting as a new programming language 
  • Prompt patterns: Zero-shot, Few-shot, Chain of Thought (CoT), ReAct, Reflexion 
  • Context engineering and Memory-Context-Planning (MCP) 
  • Evolution of prompting 

Low-Code Model Development and Deployment 

  • Rapid training and deployment of ML models without code 
  • Building visual ML workflows and data pipelines 
  • CRUD (create, read, update and delete) operations via natural language 
  • Structured data access through conversational interfaces 

Conversational Interfaces  

  • Designing natural language interfaces for engaging with users (chat) 
  • Workflow design for AI agents 
  • LLM-first design: conversational UX (user experience), intent capture, accessibility 
  • Personalising user experience with AI  

Designing and Deploying AI Agents 

  • An end-to-end methodology for designing an AI agent 
  • Agent design patterns: reactive, deliberative, autonomous, RAG 
  • Agent skills: tool use, memory, personalisation, decomposition 
  • Looping architectures: Reason → Act → Reflect 
  • Multi-agent orchestration and coordination 
  • UX patterns for agent interfaces 

Building Reasoning Workflows 

  • Chaining tools and prompts for complex tasks 
  • Using function calling and APIs dynamically (e.g. OpenAI tools) 
  • Automating workflows  
  • Reasoning pipelines and modular design thinking 

Full-Stack AI Platform Development 

  • Building end-to-end LLM applications with integrated frontend and backend 
  • Connecting agents to structured databases and document stores 
  • Creating dashboards, summaries and reports from structured or unstructured inputs 
  • Storing, reusing and scaling agent modules dynamically 

Evaluating, Reflecting and Iterating AI Systems 

  • Task-based and user feedback-based evaluation 
  • Prompt logging, observability 
  • Building metrics dashboards to track agent/LLM performance 

Scaling Low-Code AI Solutions 

  • From prototype to production: managing growth 
  • Governance: security, compliance, output constraints 
  • Monitoring and iterating based on real-world feedback 

Capstone Project 

You will have four weeks after the end of the taught sessions to complete a project, which will be based on the above themes.  This serves as an opportunity to use the knowledge gained in the course. You will do so as part of a group, with each group expected to commit approximately 10 hours of work to the project outside of the live sessions. Credits for AI tools/platforms will be provided as needed for the project. 

Note: Considering the rapidly evolving nature of this topic, the programme details are subject to change.  

Digital Certification

Participants who satisfy the course requirements will receive a University of Oxford digital certificate of completion. To receive a certificate at the end of the course you will need to:

  1. Achieve a minimum attendance at online sessions of 75%.
  2. Submit completed work as part of the capstone project after the end of the taught sessions

Participants who meet this criteria will be emailed after the end of the course with a link, and instructions on how to access their University of Oxford digital certificate. 

The certificate will show your name, the course title and the dates of the course you attended. You will also be able to download your certificate or share it on social media if you choose to do so.

Fees

Description Costs
Course Fee £1720.00

Payment

Fees include electronic copies of course materials. 

All courses are VAT exempt. 

Register immediately online  

Click the 'Book now' button on this webpage. Payment by credit or debit card is required. 

Request an invoice 

If you require an invoice for your company or organisation, please email us to request an online enrolment form. Payment is then accepted online, by credit/debit card, or by bank transfer. 

Tutors

A full list of speakers and their biographies can be found here.

Ajit Jaokar

Course Director

Ajit is a dedicated leader and teacher in Artificial Intelligence (AI), with a strong background in AI for Cyber-Physical Systems, research, entrepreneurship, and academia. 

Currently, he serves as the Course Director for several AI programs at the University of Oxford and is a Visiting Fellow in Engineering Sciences at the University of Oxford. His work is rooted in the interdisciplinary aspects of AI, such as AI integration with Digital Twins and Cybersecurity.

His courses have also been delivered at prestigious institutions, including the London School of Economics (LSE), Universidad Politécnica de Madrid (UPM), and as part of The Future Society at the Harvard Kennedy School of Government.

As an Advisory AI Engineer, Ajit specialises in developing innovative, early-stage AI prototypes for complex applications. His work focuses on leveraging interdisciplinary approaches to solve real-world challenges using AI technologies.

Ajit has shared his expertise on technology and AI with several high-profile platforms, including the World Economic Forum, Capitol Hill/White House, and the European Parliament.

Ajit is currently writing a book aimed at teaching AI through mathematical foundations at the high school level.

Ajit resides in London, UK, and holds British citizenship. He is actively engaged in advancing AI education and innovation both locally and globally. He is neurodiverse - being on the high functioning autism spectrum.

Ajit's work in teaching, consulting, and entrepreneurship is grounded in methodologies and frameworks he developed through his AI teaching experience. These methodologies help to rapidly develop complex, interdisciplinary AI solutions in a relatively short time. These include:
1. The Jigsaw Methodology for low-code data science to non-developers.
2. The AI Product Manager framework and AI product market fit framework 
3. Software engineering with the LLM stack 
4. Agentic RAG for cyber-physical systems.
5. AI for Engineering sciences: 
6. The ability of AI to reason using large language models

He also consults at senior advisory levels to companies.

His newsletter on AI in Linkedin has a wide following 
https://www.linkedin.com/newsletters/artificial-intelligence-6793973274368856064/

Anjali Jain

Tutor

Co-founder, Erdos | Author | Senior Tutor in AI & ML, University of Oxford | AI Ambassador, Oxford AI & ML Competency Center | Data Architect, Metro Bank

Anjali Jain is a London-based data architect, author, and AI expert with over two decades of experience in software development, architecture, data strategy, and applied machine learning. 

At the University of Oxford, she serves as Senior Tutor in AI and Machine Learning and as AI Ambassador at the AI & ML Competency Center, where she leads strategic initiatives in AI education and research.

She is the co-founder of Erdos Research, a collaborative research and innovation lab focused on building and implementing AI systems, advancing prompting methods, and developing tools for AI-assisted software engineering.

Anjali also serves as Data Architect at Metro Bank, where she supports the integration of AI into financial systems with a focus on data governance, data architecture and compliance.
She is the co-author of “10X AI Developer Guide with BRIDGE AI Framework” and “AI-Assisted Programming for Web and Machine Learning”, offering practical methodologies for building intelligent, human-centric technologies.

Ayşe Mutlu

Tutor

Data Scientist

Ayşe Mutlu is a data scientist working on Azure AI and devops technologies. Based in London, Ayşe’s work involves building and deploying Machine Learning and Deep Learning models using the Microsoft Azure framework (Azure DevOps and Azure Pipelines).

She enjoys coding in Python and contributing to Open Source Initiatives in Python.

Application

How to apply for this course

  1. Complete this short online application form
  2. The administration team will forward your application to the academic review panel, and then be in touch with an update on your application
  3. If successful, you will be asked to make payment via our secure online payment portal. 

IT requirements

This course is delivered online using Microsoft Teams. You will be required to follow and implement the instructions we send you to fully access Microsoft Teams on the University of Oxford's secure IT network.

This course is delivered online; to participate you will need regular access to the Internet and a computer meeting our recommended Minimum computer specification.

It is advised to use headphones with working speakers and microphone.

Terms & conditions for applicants and students

Information on financial support