01Start here
RAG Document Pipeline
A complete retrieval-augmented generation flow over your own documents — ingestion, chunking, vector storage, and a retrieval chain with tuned parameters that returns accurate, grounded answers.
No code required. In one session you'll visually build a document Q&A chatbot, an AI agent that connects to live tools, and a multi-step workflow — drag, drop, run, done.
See the curriculumYour take-home work
Build these with your instructor. Keep them, adapt them, and put them to work after the workshop.
Next cohort coming soon
03Make it yours
A production-grade supervisor-worker architecture: one orchestrator routes tasks to specialised sub-agents, aggregates their outputs, and returns a unified response — exported as a deployable REST API.
Founder of AISOLO Technologies; AI entrepreneur & educator
350K+
Students
12+
Yrs exp
3
Startups
Yash Thakker is the founder of AISOLO Technologies and one of the most sought-after AI educators in the country. He's known for one thing above all: by the end of any session, students have already built something — no saving it for 'later.' His classes are built around real-life, happening-right-now examples, zero dry theory, and a teaching energy that makes complex things feel obvious. With over a decade shipping AI products across media, fintech, and edtech, Yash has delivered every learning format imaginable — in-person workshops, live bootcamps, online courses, and hybrid sessions — always exploring new ways to make learning land faster. He's obsessed with what learning looks like for this generation, now that AI changes what's even worth teaching. He has reached 350,000+ learners and is the creator behind BGBlur.com and explainx.ai.
Teaches on
Has trained teams at
What you’ll take away
Beginner-level workshop
Langflow is a visual canvas where you build AI workflows and agents by connecting blocks — no code, no boilerplate, no waiting on a developer. You drag in a document loader, connect it to an LLM, add a memory block, and your AI assistant is running. This workshop covers the full picture: how to read and answer questions from your own documents, how to give your agent real tools like web search and APIs, and how to chain multiple agents together so they collaborate on a task. Whether you're a founder, marketer, operations manager, or PM — if you can use a whiteboard, you can build in Langflow. By the end you'll have three working AI workflows built during the session, ready to share or deploy the same day.
The curriculum
4 hours live · Recordings included
Understand how Langflow works: nodes, edges, components, and the underlying LangChain execution graph. Set up your Langflow environment, tour the component library, and build your first end-to-end flow — a basic LLM chat with memory. Learn how Langflow maps to LangChain concepts so you can debug and extend anything you build.
Build a retrieval-augmented generation pipeline from the ground up — document loading, chunking strategy, embedding model selection, vector store ingestion, and retrieval chain assembly. Learn why naive RAG fails and how to tune chunk size, overlap, and retrieval parameters to get the right context into every response. Finish with a working Q&A pipeline over your own documents.
Extend your flows beyond static documents. Connect live APIs as tool nodes, wire in web search, build conditional routing so agents decide which tool to call, and handle errors gracefully when external calls fail. Add memory so your agent tracks conversation state across turns. Leave with a flow that reads from the real world and responds intelligently.
Design supervisor-worker multi-agent architectures in Langflow — one orchestrator delegates to specialised agents, aggregates results, and returns a final output. Learn Langflow's deployment options: API export, Docker, and cloud hosting. Add logging, trace your flow's execution, and review the patterns that separate a reliable production workflow from a fragile demo.
Skills you’ll practice: Langflow graph runtime · RAG pipeline design · Chunking and embedding strategy · Vector store integration · Tool node wiring · Conditional routing · Conversation memory · Multi-agent orchestration · Langflow deployment · Flow observability
skills
Everything you practise hands-on across the live sessions.
faq
Everything you need to know before enrolling.
No. Langflow is a visual canvas — you build by connecting blocks, not writing code. If you can use a tool like Notion or Figma, you can build in Langflow. No programming background required.
Learn with your teammates
Save 20% when 2 or more teammates enrol in the same cohort.
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team. Live remote, in person, or hybrid.
Book a private cohortReviews
4.5averagefrom 119,479 reviews of Yash’s courses on Udemy, by 304,941 learners
Reviews from this workshop come first. Messages marked “From …” are from students of Yash’s other live workshops and bootcamps.
“I'd tried building a RAG app in pure LangChain and spent a week on plumbing. In Langflow I had the same pipeline working in under an hour. The chunking and retrieval session alone was worth attending.”
“As a PM I couldn't write the LangChain boilerplate myself, but I could design and test the full agent flow in Langflow. I showed the working prototype to engineering and we shipped it in two weeks.”
“The multi-agent session was the highlight — Yash builds a supervisor-worker system live on screen. Watching it come together step by step made the architecture click in a way blog posts never did.”
“We were prototyping an internal knowledge-base chatbot. After this workshop I had a working RAG flow connected to our Notion docs by end of day. Deployed to our Slack bot the next morning.”
Oct 2026 cohort“The instructor, Mr. Yash Thakker, kept things as simple as feasible and demonstrated easy to understand examples. The diction, clarity of speech, pace etc. was just fine, and he paused for us to try something and patiently answered our doubts.”
Oct 2026 cohort“Overall it was very well presented and the information shared with us was useful.”
