Niralworks Academy·An academy for agentic engineering
A rigorous weekend bootcamp that teaches you to design, build, and ship autonomous AI systems the way working engineers do — fundamentals first, then frameworks, then production. Mentored, code-reviewed, and finished with a defended capstone.
01·Why this exists
Across fintech, commerce, logistics, and SaaS, companies are deploying agents that plan, call tools, and complete real work. Engineers who can build and operate these systems are scarce enough that hiring managers wait months.
Your university syllabus won't cover any of this before you graduate. We will — in twelve focused weekends, taught the way serious engineering is always taught: fundamentals first, then frameworks, then production.
No hype. No prompt-of-the-week. A discipline, learned properly.
The agentic engineer's toolkit — what you'll be hired to do
02·Curriculum
Every phase ends with something that works. Every week ends with a code review from a working engineer.
AG-101
Phase 01 · Weeks 1–3
You'll buildA document-intelligence assistant that answers with receipts.
AG-201
Phase 02 · Weeks 4–6
You'll buildAn autonomous research agent that browses, extracts, and reports.
AG-301
Phase 03 · Weeks 7–9
You'll buildA supervised multi-agent pipeline that completes real work end-to-end.
AG-401
Phase 04 · Weeks 10–12
You'll buildYour capstone — a production agent system, deployed and defended.
Live labs + recorded material · Code review every week · Cohort capped at 40
03·Outcomes
01
Three or more working agent systems on your GitHub — not tutorial clones, but tools with real users, real failure modes, and real fixes.
02
A production agent system with evaluations, tracing dashboards, and a cost model. You'll defend it like an engineering review, not present it like a slideshow.
03
You'll think in architecture decisions, failure modes, and cost tradeoffs — the difference between someone who follows agent tutorials and someone who can own an agent system.
04
A cohort of forty, an alumni community, and mentors who stay reachable after the program ends. The peers you'll build with for years.
Built for the roles the industry is hiring for: AI engineer, agent engineer, LLM platform engineer.
04·Who it's for
Built for
Not for
Saturday
3-hour live lab with the week's concept, then a build brief on the spot.
Sunday
Build review with mentors — your code, critiqued line by line — plus office hours.
Through the week
Self-work and assignments. Budget 10–12 hours total, at the pace of a real job.
05·Plans
Start with fundamentals, or go straight to production-grade agent engineering. Both are live, mentor-led, and capped.
P·01
8–10 weeks · live online
2nd-year students building real fundamentals
You build and explain a working AI application — and start a GitHub portfolio that grows every year.
Inquire about FoundationP·02
Flagship
12 weekends · live online · Sat–Sun
3rd/4th-year students going production-grade
You design, build, evaluate, and deploy production-oriented agentic systems — with a defended capstone.
Inquire about ProgramFor colleges
A one-day, hands-on AI agent workshop for your students — 100 to 300 participants, live builds, no slideware. The first step of a campus partnership: hackathons, certification programs, and faculty enablement follow.
Book a campus workshopFormat
1-day hands-on workshop, on campus or online
Batch size
100–300 students
Fee
₹25,000 – ₹50,000 per engagement
Follow-ons
Hackathons · campus certification · faculty enablement
06·Mentors
Every mentor works on agentic systems in production. They teach what they did last month, not what they read about last year.
Lead Mentor · Agent Platforms
Built payment-reconciliation agents handling millions of transactions a day at a global fintech. Teaches architecture and the unglamorous parts of production.
Mentor · Applied LLMs
Former ML engineer; ships retrieval and evaluation infrastructure for enterprise systems. Leads Phase 01 and makes fundamentals feel like power tools.
Mentor · Systems & Deployment
Platform engineer who has operated agent fleets on AWS and GCP. Runs the Ship phase: deployment, cost, latency, and things that break at 2 a.m.
Mentor · Evaluations & Safety
Research background in LLM evaluation. Obsessed with measurable reliability — teaches you why 'it seems to work' is not an eval.
Guest sessions from engineers and founders run through every cohort
07·Questions
Anything else? Write to hello@niralworks.com
No. You need comfortable Python, basic data structures, and the willingness to grind for twelve weekends. We start from LLM fundamentals and build up to production-grade agent systems. Students who have never trained a model do fine; students who have never written code do not.
Plan for 10–12 hours: live sessions on Saturday and Sunday, plus self-work and assignments through the week. The workload is deliberately close to a real job so you learn what the pace of shipping actually feels like.
Every session is recorded, and we run office hours on weekdays. But code review happens live, and mentors grade your week's build — consistent attendance is what separates people who finish from people who don't. Miss more than two weekends and we'll ask you to defer to the next cohort.
No — and we're upfront about it. We're an academy, not a placement agency. What we do is make you genuinely good at an in-demand craft: you leave with a deployed portfolio that speaks for itself. Treat anyone who promises you placements as a red flag, not a feature.
It's published, not hidden: the Agentic AI Foundation is ₹4,999 for early cohorts (standard ₹7,999), and the Agentic Engineer Program is ₹19,999 for Cohort 01, with installment options. Partial scholarships exist for exceptional students who need them.
You get a certificate. But the real credential is your GitHub: three or more deployed agent systems, a capstone with evaluations and tracing dashboards, and a public build log. Hiring managers read repos, not PDFs.
2nd to 4th-year undergraduates and PG students from any accredited college, any branch — CSE, IT, ECE, or otherwise. Send an inquiry, and if it's a fit we'll set up a short call before offering a seat. Your college tag doesn't matter.
Yes. We run one-day hands-on AI agent workshops for 100–300 students (₹25,000–₹50,000 per engagement), with hackathons, campus certification, and faculty enablement as follow-ons. Email hello@niralworks.com to book one.
Yes, all live sessions, reviews, and materials are in English. You need working fluency, not perfection.
08·Inquiries
Inquiries open · Cohort 01 · closes Sep 30
No essays, no recommendations, no fee. Tell us which plan you're considering and what you want to know — we reply personally.