Now open in offline mode (no live sessions) due to high demand — enroll anytime and earn the same certificate.
Mastering Prompting
A ground-up prompt engineering curriculum on Claude — from how LLMs actually work through the full prompt scaffold, core techniques, reliability engineering, extended thinking, multimodal and tool-use prompting, RAG, agentic systems, and production-grade evaluation.
Based on your location (India), you qualify for a Purchasing Power Parity discount.
Secure checkout via Razorpay
India checkout supports cards, UPI, net banking, and eligible EMI through Razorpay.
About this program
Prompting is the highest-leverage skill in working with Claude, and most people never learn it systematically. This course builds that skill from first principles. You'll start with what LLMs actually do and how Claude's context window, roles, and sampling parameters work, then learn the 10-element prompt scaffold that makes prompts predictable and tunable. From there we cover core techniques like few-shot prompting, chain-of-thought, XML tags, and prefilling, along with reliability engineering to reduce hallucinations and make outputs reproducible, and extended thinking and when to reach for it. You'll work with multimodal prompting across images, PDFs, and documents, tool use and function calling including computer use, and RAG and dynamic context injection. The course closes with agentic systems built on orchestrator and subagent patterns, memory, and safety, and finally treats prompts like code: versioning, eval suites, cost and latency optimization, and production monitoring. It ends with a capstone that ties every technique together. 10 modules, 63 lessons, fully self-paced. No live sessions required.
Who is this for?
Developers, product builders, and technical practitioners who want to systematically master prompting Claude — from first prompt to production-grade agentic systems
What you'll actively build & learn
Understanding Fundamentals
Grasp the core mechanics of AI systems, from transformers to retrieval algorithms, moving beyond superficial APIs.
Production-Ready Architecture
Learn how to architect scalable, resilient generative AI applications that handle edge cases and high throughput.
Hands-on Engineering
Write custom PyTorch models, build multi-agent swarms using LangGraph, and deploy to Kubernetes.
Verifiable Execution
Complete rigorous capstone projects that serve as a proof-of-work portfolio for your next AI engineering role.
Time Commitment & Schedule
Self-Paced Modules
Flexible
No live sessions — work through all 10 modules whenever suits you, in any order you need.
Hands-On Labs
~20 hrs total
Labs in every module: temp 0 vs. temp 1, insurance claim iteration, red-teaming a prompt, document extraction pipeline, a Q&A bot, a multi-agent research pipeline, and a final capstone.
Module-Based Syllabus
Each module is structured around three things: what you'll cover, what capability you'll walk away with, and the concrete deliverable that moves you toward a working system of your own. Work through them in any order, at any pace.
10 self-paced modules, 63 lessons — work through them in order or jump to the skill you need most right now
A working mental model of how Claude and LLMs behave, a personal prompt-engineering toolkit, and a capstone project that exercises the full pipeline
Practitioner-first lessons grounded in real Claude features, with hands-on labs that produce artefacts you can reuse immediately
How Claude Thinks — Mental Models Before Prompts
- What LLMs actually do, Claude's training and values, the context window, system/user/assistant turns, and temperature/top-p/max tokens.
An accurate mental model of what Claude is and isn't — the foundation for every prompting decision that follows.
A side-by-side comparison of temp-0 vs. temp-1 outputs on the same prompt, with written observations.
Anatomy of a Great Prompt
- The 10-element prompt scaffold, task context, tone context, detailed task rules, and output formatting.
The ability to structure any prompt using a repeatable, tunable scaffold instead of trial and error.
A fully scaffolded prompt for an AdAstra career coach persona, built element by element.
Core Techniques Every Prompter Must Know
- Few-shot prompting, chain-of-thought, XML tags for structured outputs, prefilling the assistant turn, and positive vs.
- negative instructions.
Fluency with the core toolkit of prompting techniques that underlie almost every advanced pattern.
Five iterations (v1→v5) of an insurance claim prompt, each applying one more technique.
Reliability Engineering — Hallucinations, Grounding, and Consistency
- Why hallucinations happen, four anti-hallucination techniques, document grounding, reproducibility, and evaluation basics.
The ability to make Claude say "I don't know" when it should, and to ground answers in real evidence.
A red-teamed prompt with documented failure modes and the fixes applied.
Extended Thinking and Reasoning Models
- What extended thinking does under the hood, when to use it, reading thinking traces, its downsides, and how it compares to prompt engineering.
Judgment for when extended thinking is worth its cost/latency tradeoff versus better prompting alone.
A with-vs-without extended thinking comparison on the same task, with a recommendation.
Multimodal Prompting — Vision, Documents, and Files
- Image prompting, PDF and document prompting, an accident-report case study, numbered element annotation, and combining modalities.
The ability to prompt Claude with images, PDFs, and structured documents for reliable extraction and analysis.
A working document extraction pipeline tested against a real multi-page document.
Tool Use and Function Calling
- How tool use works, designing tool schemas, parallel vs.
- sequential tool calls, error handling, and computer use/browser control.
The ability to give Claude well-designed tools and handle the failure modes that come with real tool use.
A research assistant that composes multiple tool calls to complete a multi-step task.
RAG and Dynamic Context Injection
- Why RAG, embedding and vector search, prompt patterns for RAG, hybrid retrieval, and context window management.
The ability to feed Claude the right knowledge at the right time instead of stuffing the context window.
A working Q&A bot backed by a retrieval pipeline over a real document set.
Agentic Systems — Multi-Step Autonomy and Multi-Agent Orchestration
- What makes a system "agentic", orchestrator vs.
- subagent patterns, memory architectures, safety in agentic loops, MCP, and prompt injection.
The ability to design multi-agent pipelines that plan, execute, and self-correct safely across many steps.
A multi-agent research pipeline with at least one orchestrator and two subagents.
Production Prompt Engineering — Evaluation, Iteration, and Scaling
- Prompt versioning, building an eval suite, the Anthropic Console Evaluate tab, cost and latency optimization, fine-tuning vs.
- prompting, and monitoring in production.
The ability to treat prompts like code — versioned, evaluated, and monitored — rather than one-off text.
A capstone: an eval suite and versioned prompt for a real use case, with a monitoring plan.
The syllabus builds toward a final proof of work.
The weekly syllabus is designed to stack toward a capstone that demonstrates what you can actually build. By the end of the cohort, you are not just finishing modules. You are presenting a concrete output that ties the learning arc together.
View Alumni CapstonesIndustry-Grade Certification
Earn a credential that actually matters. Every certificate is tied to your Capstone Project repo, valid for life, and optimized for your professional technical profile.
View Certification TiersYour instructor
Anubhav Srivastava
Anubhav has spent the past two decades building machine learning and AI systems across startups, large enterprises, and high-scale consumer platforms. He has worked on patented AI technologies, authored books, and founded multiple ventures, and is currently building a deeptech startup focused on physical AI. Known for combining technical depth with practical thinking, he enjoys breaking down complex ideas into clear, accessible insights and is driven by a curiosity for how technology can solve real-world problems.
From our students
Engineers at different levels share what they built and what changed.
500+
Engineers trained
25+
Engineering leaders
40+
SaaS startups
50+
Alumni network
Alumni at
“The most technically rigorous program I've attended. No fluff — just pure deep-dives into transformer blocks and swarm logic. It's about understanding how LLMs actually work.”
Siddharth S.
Staff Engineer · Build Your Own LLM
“LangGraph and multi-agent orchestration was the missing link for our production pipeline. Essential for developers who need to move beyond single-prompt engineering.”
Elena R.
Senior AI Engineer · Agentic AI
“Direct access to instructors who are actually shipping AI products. The focus on evals-driven development is unique — we implemented their RAG evaluation approach across our entire startup.”
Arjun R.
Tech Lead · Claude Code
FAQ
Common questions about courses, formats, and what to expect.