Building Systems with the ChatGPT API vs Machine Learning Specialization

Across 11 short lessons (roughly 90 minutes total), the course covers a complete pipeline for multi-step LLM systems: how language models and tokenisation work, the chat format and system-user message separation, input classification for query routing, the OpenAI Moderation API, chain-of-thought prompting to handle multi-step questions, chaining several focused prompts where each consumes the previous output, output checking, and a two-part section on evaluating LLM responses at the system level. Reviewers consistently praise the logical progression and the theory-to-practice balance. The principal mark-down is age and depth: the course was built on GPT-3.5 Turbo in 2023 and has not been meaningfully updated, so it predates tool calling, structured JSON outputs, and reasoning models, and it stops short of real-world deployment concerns such as latency management, cost at scale, and production observability.

Isa Fulford, Member of Technical Staff at OpenAI, leads the code demonstrations while Andrew Ng frames the broader concepts and asks the questions a beginner would actually ask. Reviewers across blogs and Coursera call the pairing "highly knowledgeable and effective communicators." The teacher-demonstrator dynamic mirrors how a learner thinks through a new problem step by step, keeping each lesson of five to twenty minutes focused and coherent. Because Fulford comes directly from the team that built the ChatGPT API, the design decisions behind the Moderation API, the chat format, and tokenisation carry genuine authority rather than third-hand explanation.

The course is free on the DeepLearning.AI platform with every Jupyter notebook runnable directly in-browser — no OpenAI API key, no local Python environment, and no subscription required. The Coursera guided-project version is also free to audit. For roughly 90 minutes of hands-on instruction from two of the most credible names in the field, delivering reusable architecture patterns for multi-step LLM systems, the value proposition is essentially unmatched among paid or free alternatives. The only caveats are that a graded assignment and certificate on the Coursera version sit behind a paid enrolment, and the free tier leaves no portfolio artefact by default.

The patterns taught — classify the input, moderate for safety, reason in steps, chain focused prompts rather than one monolithic prompt, then evaluate the output — are exactly how production LLM features are structured in practice. Multiple reviewers note that the progression from basic API calls to a multi-stage orchestrated system reflects real engineering work. The gap is that the 2023 course predates the patterns now central to production LLM development (tool calling, structured outputs, retrieval-augmented generation), and at least one practitioner reviewer noted that the finished chatbot example would require substantial hardening before it approached something ready for deployment beyond a prototype.

Every lesson pairs a video with a runnable Jupyter notebook, and the course builds one coherent end-to-end example: a customer-service chatbot that classifies incoming queries, runs them through the Moderation API, applies chain-of-thought prompting to multi-step reasoning, chains successive focused prompts, retrieves product information, and evaluates whether its own output actually addresses the user's question. The Coursera version holds a 4.7/5 rating across 346 learners. The caveat is that there is no graded project or kept portfolio artefact on the free tier, and the supplied notebooks now require fixes (deprecated API syntax, missing helper files) to run locally outside the course sandbox.

Reviewers consistently praise the breadth of the curriculum — supervised learning, neural networks via TensorFlow, decision trees, unsupervised learning and a first look at reinforcement learning — all within 95 hours. The main critique is insufficient depth in certain areas: one reviewer noted the course "doesn't go into a lot of detail on some things" and another flagged that it "skipped over essential libraries like Scikit-Learn preprocessing and Pandas." The reinforcement learning module is widely described as an overview rather than a deep treatment.

Andrew Ng receives near-universal praise across every source. Hacker News commenter rg111 called him "among the best teachers I have ever seen" and farzatv declared it "one of the best courses on ML." The Forecastegy review echoes this: "Andrew Ng's teaching style is both intuitive and engaging." Critical comments about Andrew Ng's delivery are essentially absent in the data collected.

At $49/month Coursera subscription, learners who complete the specialization in two to three months pay roughly $98–$147 for content that carries strong brand recognition. Free audit is available for lectures only. The Interview Guys review calculated this as "one of the best returns in professional development" given ML engineer salary data. The subscription model is criticised by learners who take longer than expected.

Browser-hosted Jupyter notebooks with no local install are praised by multiple reviewers, including Valentyn Druzhynin who highlighted "no installation required" as a key comfort factor. The getbridged.co review noted that mentors on forums provide "thoughtful replies." However, several reviewers flagged that auto-grader unit tests "can be frustrating" and one commenter (BeetleB on HN) found assignments trivially scaffolded.

The course deliberately teaches industry tools — NumPy, scikit-learn, TensorFlow — and multiple reviewers credit it with building a genuine foundation. However, the Neural GPT reviewer on Medium pointed out missing Pandas and sklearn preprocessing coverage, and The Interview Guys stress that "this certification will not make you a machine learning engineer" without supplementary portfolio projects. Datasets in the course are clean and structured, far from real-world messiness.