Prompting isn't a system
Copy-pasting into a chat window doesn't scale past you. There's no trigger, no memory, no record, and nothing happens when you're on leave. You learn to turn a prompt into a process that runs itself.
Trusted by
PwC
EY
IDFC First Bank
Deloitte
Oracle
Ford
Ujjivan Small Finance Bank
Air India
Punjab National Bank
RateGain
LatentView
Redington
Saurashtra Cement
Nexturn
TPAC
Reliable Group
Gates Foundation
Google
Pepsi Co
Wipro
Capgemini
Visa
Cohort 03 · Live · Weekends only
29 August – 20 September 2026 · Weekend mornings, 10:00 IST
Build no-code AI agents that do the work.
Four weekends, weekends only. Ten hours of instructor-guided building, six hours of live coaching on the agent you build yourself. You leave with something running a real task from your own work — not a certificate for watching videos.
- 10 hrs
- live teaching
- 6 hrs
- live coaching
- 8
- sessions, weekends only
- 0
- lines of code
Flowise + n8n · Free LLM API keys · No prior AI experience
A starter kit you can build as your own
Ticket and vendor triage agent
Same skeleton every build follows — arrives → agent reads → grounded → gate → output.
The gap
Everyone is using AI. Almost nobody has put it to work.
Chatting with a model saves you ten minutes. An agent that runs unattended every morning saves you the task. The difference is not intelligence — it is plumbing, and plumbing is now drag-and-drop.
The tutorials assume a developer
Most agent content is written for people who read Python. This course is built the other way round: you'll understand embeddings, tool calls and context windows properly, and you'll never open a terminal to do it.
Demos don't survive contact with work
An agent that works in the room and breaks on Monday is worse than nothing. Error branches, approval gates, evaluation sheets and cost ceilings are taught as part of building — not as an afterthought.
Who joins
Anyone who owns a process. No technical background needed.
Pick the one closest to you.
You run a function, and the busywork runs you
“Four hours of my week is moving information between an inbox, a sheet and a chat window.”
Finance, HR, operations, marketing, sales, procurement, customer support. You know exactly which task should be automated — you have never had a way to build it without raising a ticket with IT and waiting a quarter.
You walk out with
- One real task from your job, fully automated and running on a schedule
- The vocabulary to brief an AI vendor or your IT team without being sold to
- A repeatable method for spotting the next five processes worth automating
- A cost model, so you can say what the agent costs per run
How it runs
Build it with the instructor. Then build yours, independently.
Closer to a group class than a lecture. Everyone follows the same build on screen, then repeats it on their own use case. In the coaching sessions a handful of those attempts get worked through live — and the rest of the room learns from the fix.
Instructor-guided build
Five sessions, all following one agent as it gets built end to end. You are not watching slides — your canvas is open and you build the same thing at the same time. Each session adds a layer to the same agent, so by the last one it is a real, deployed system.
Every session ends with a handout: the exact steps to repeat on your own use case.
Independent build, mentored
You apply those same steps to a use case of your choosing, or one of five starter kits. Where you get stuck, you send a short note ahead of the session. The instructor triages them and works the common failures live, on real screens.
One flow gets fixed on screen. Thirty people learn the fix.
- 01
Learning session
Build the reference agent alongside the instructor, layer by layer.
- 02
Your build
Repeat the same steps on your own use case, in your own time.
- 03
Coaching session
Send what broke. Watch it get fixed live, along with everyone else's.
- ↻
Repeat
Four weekends, until your agent runs on its own.
- 8 sessions, two hours each
- Weekends only — nothing is ever scheduled midweek
- Free setup call before the cohort opens
The curriculum
One agent, built in five layers.
Rather than five shallow demos, the class builds a single agent — the Desk — and each session adds one layer to it. Documents and requests arrive, it reads them, answers from your own reference material, files what it can and escalates what it can't. Every layer transfers directly to whatever you build on your own.
5 instructor-guided sessions · 2 hours each · weekend mornings, IST
Session 01 — Think like an agent
What an agent actually is, how a language model behaves, and why most people's prompts fall apart the moment something depends on them. The longest hands-on stretch of the course, because everything after this assumes it.
Covered in session
- Agent vs chatbot vs macro. Goals, tools, memory and autonomy — the four things that make something an agent
- How an LLM really behaves. Tokens, context windows, temperature, system vs user instructions, and the honest reason it invents things
- The reason–act–observe loop, explained without a single equation
- Anatomy of a Flowise chatflow. Nodes, ports, chains, connections and the credential store
- Prompts that hold up. Role, constraints, output schema, few-shot examples and explicit refusal rules
- Structured output. Forcing clean fields so the next step in your workflow can rely on them
- Choosing a model. Speed, cost and accuracy trade-offs, in plain rupees
The Desk gains · live
Layer one. A request arrives as messy text; the Desk returns owner, category, deadline and urgency as clean structured fields — the same way every time.
Your handout
Pick your use case and your starter kit. Build the same extraction layer on your own inputs. Note every case where the output came back wrong.
Your own build
You learn on one build. You apply it to yours.
The class builds the Desk together. Between sessions you build your own version of it — same five layers, your domain. Start from one of these five kits, each shipped with sample data and a template so nothing stalls for want of a spreadsheet. Or bring a process from your own job; we'll scope it together early on so it's finishable inside the cohort.
Same skeleton every time — something arrives → agent reads → grounded → gate → output
Kit A · Finance
GST invoice reconciliation agent
Invoices arrive as PDFs in a mailbox and a Drive folder. Your agent reads them, pulls GSTIN, HSN, taxable value and tax heads, matches each against the purchase register, and posts a daily exception report of everything that doesn't tie out. Nobody opens a PDF manually again.
- Trigger01
Invoice lands in mail or Drive
- Agent02
Extract GSTIN, HSN, taxable value, tax
- Tool03
Match against purchase register
- Gate04
Flag mismatches over tolerance
- Output05
Daily exception report to finance
A three-minute recording
Screen-record your agent doing its job and talk over it. No live presentation, no scheduling, no stage fright — and you keep the video.
Four things, published upfront
Does it run unattended? Is it grounded in a real source? Does it fail safely? Do you know what it costs per run?
Written feedback, everyone
A rubric score and notes on every submission, not just the strongest. Certificate on a pass. Best builds published to the cohort gallery.
The tools
Two open-source standards. Both free to start. Neither needs code.
We teach the pair together because they solve different halves of the problem — and because connecting them is what turns a clever demo into an operating system for your work.
Flowise
A visual builder for LLM applications. You drag nodes onto a canvas to compose chains, retrieval pipelines and multi-agent flows, then publish them as a chat widget or an API endpoint.
- Chatflows and Agentflows
- Vector stores and document loaders
- Memory, tools and custom tools
- Embedded widget, shareable link, API
n8n
A workflow automation platform with several hundred integrations. It gives your agent triggers, credentials, access to the tools your business already runs on, and a full log of every execution.
- Schedule, webhook and form triggers
- Gmail, Sheets, Drive, Slack, WhatsApp, CRMs
- Branching, batching, error handling
- Execution history and alerting
Sayantan Dawn
Data Science & Generative AI Educator · Risk Modelling Specialist
Who's teaching
Taught live, by someone who hires for this.
Ten years across analytics, credit risk modelling and generative AI at Citi, JP Morgan, Tiger Analytics and BRIDGEi2i. Founder of Last Bench, where he has mentored more than 500 students and professionals into roles at Citi, HSBC, Barclays, JP Morgan, Genpact and EXL.
Every session is delivered live, with a cohort small enough that you can interrupt. Nothing is pre-recorded, nothing is read off a slide, and every build happens on screen in real time — including the parts that break.
10+
Years in analytics & GenAI
500+
Mentored into roles
6
Institutes taught at
Workshops at IIT Kanpur · IIT Bombay · ISI Delhi · IIFT · BHU · Calcutta University
Before you start
What you need on day one
Shorter than most lists, deliberately. There is no Python prerequisite, because there is no Python.
- A laptop
- Stable internet
- An email address
- One process you know well
- Curiosity
Not needed: coding, a CS degree, a paid API account, or prior AI experience.
On the other side
What the certificate actually proves
Anyone can attend. The certificate is issued only once the capstone clears the rubric — so it means something specific.
- Designed, built and deployed a working AI agent end to end
- Hands-on with Flowise, n8n, RAG and vector stores
- Submitted a recorded build scored against a published four-point rubric
- Can walk an interviewer or a board through the build and its cost
Enrolment
One price. Everything included.
No upsells, no premium tier, no separate charge for the recordings.
Cohort 03 · Live seat
₹3,999
+ 18% GST · per person
Cohort 03 runs 29 August – 20 September 2026 · begins Sat 29 August, 10:00 IST
--
Days
--
Hours
--
Mins
--
Secs
Thirty seats, because six hours of coaching split thirty ways is the honest limit.
Seats
1
- Course fee
- ₹3,999.00
- GST at 18%
- ₹719.82
- API keys and software
- Free
- Total payable
- ₹4,718.82
Sixteen hours live, which puts an hour of it at about the price of a pizza. GST invoice issued against your company GSTIN, so input credit can be claimed.
What the fee covers
- 10 hours of instructor-guided building across 5 sessions
- 6 hours of live coaching across 3 sessions
- A 30-minute setup call before the cohort opens
- Free LLM API keys — no card, no credits, no surprise bill
- Five starter kits with sample data, plus a weekly handout
- Every session recorded and shared within 24 hours
- All Flowise and n8n templates built in class, yours to reuse
- Written rubric feedback on your recorded demo
- Private cohort community, and office hours for two weeks after
- Certificate on a passing submission · GST invoice for input credit
Nothing else to buy
Flowise and n8n are open source, and their free tiers cover everything we do. Free LLM API keys are issued to you in week one. Your spend beyond the course fee is zero.
FAQ
Questions people ask before enrolling.
Do I need to know how to code?
No. Every agent in this course is built by dragging nodes onto a canvas and connecting them. You'll learn to read a data structure and write instructions in plain English — but you will not write a single line of code, and no session assumes you've ever opened a terminal.
How much time will this take, and is anything midweek?
Nothing is ever scheduled midweek. Eight live two-hour sessions across four weekends — five instructor-guided learning sessions (10 hours) and three coaching sessions (6 hours), all on weekend mornings IST. Beyond that, budget roughly two hours a week on your own build, whenever suits you. The full session calendar goes out with your joining pack.
Do I need to attend the coaching sessions if I'm not stuck?
Come anyway — that's where a lot of the learning happens. Each one opens with the same pattern rebuilt in a different domain, then Sayantan works through the failures the cohort actually hit. Watching someone else's broken retrieval get fixed is often more useful than fixing your own, because you see the diagnosis rather than just the answer.
Can I bring a use case from my own job instead of a starter kit?
Yes, and professionals usually should. We'll scope it together early on so it's realistically finishable inside the cohort. The only difference is materials: the five kits ship with sample data and a template, and your own use case won't. Coaching access is identical either way.
What will the software and API keys cost me?
Nothing. Flowise and n8n are open source and their free tiers cover everything we do, and free LLM API keys are issued to you in week one — no credit card, no prepaid credits, no bill arriving later. Beyond the course fee, your spend is zero.
I'm a commerce student with no technical background. Is this for me?
Yes, and you have an advantage you may not expect. Agents are only useful when someone genuinely understands the process being automated — a CA student understands reconciliation better than most engineers do. Domain knowledge is the hard part. The canvas is the easy part.
Will I get a certificate?
You submit a three-minute screen recording of your own agent within a week of the final session — no live presentation, no scheduling. It's scored against four published criteria and the certificate is issued on a pass, with written feedback either way. The recording itself is the better credential: you can send it to a recruiter or a manager.
Can my employer pay? Will I get a GST invoice?
Yes. Add your company name and GSTIN on the enrolment form and the invoice is raised in your organisation's name before the cohort starts, so input credit can be claimed. For teams of five or more, mention it in the form and we'll set up a single consolidated invoice.
What if I miss a live session?
Everything is recorded and shared within 24 hours, and the coaching sessions exist precisely to catch you up — so a missed learning session is recoverable. That said, this is built around live building. If you expect to miss more than two of the eight, the next cohort is a better fit.
What are the system requirements?
Any Windows, Mac or Linux laptop with 8 GB of RAM and a stable connection. If you'd rather not install anything, both Flowise and n8n can be run entirely in the cloud and we'll walk through that setup in the setup call before the cohort opens.
What's the refund policy?
Attend the first learning session in full. If it isn't what you expected, write in before the second session begins and the fee is refunded, no questions asked.