Ship two AI services in 10 hours.

Companies don't hire AI users any more. They hire engineers who build, evaluate and deploy production AI systems. Week 1 is where you start — ReleaseBot built line by line alongside an engineer, MinuteMaker shipped by you and graded by one. Both land on your GitHub.

Start the 10-hour sprint — ₹599 See all 17 weeks

₹599 for Week 1, credited in full against the fee. LMS login via email in 24 hours. The full programme is 17 weeks and 33 builds; Cohort 2 enrolment closes 16 October.

WEEK 1 · GRADED

MinuteMaker

78/100
Correctness
22/25
Completeness
21/25
Design
16/25
Clarity
19/25
This is what comes back at the end of Week 1. Reviewed by an engineer, not a bot.
17Weeks
33Real builds
170+Hours

// Recorded weekdays · Live weekend builds · For developers with 2+ years shipping production code

WHAT YOU SHIP FIRST

The ten hours, and what comes out of them.

One you write alongside the instructor, line by line. One you ship on a new input and an engineer scores it. Both deployed, both on your GitHub.

ReleaseBot

guided · live day FastAPI · Pydantic · SSE

RAW RELEASE NOTES IN

- api is way faster now (~40%)
- killed the old v1 api
- fixed that annoying login bug
- added dark mode i guess
- db migration, run it before deploy

STRUCTURED CHANGELOG OUT, STREAMING

PERF  Request latency reduced ~40%
      p95 340ms → 204ms
BREAK v1 API removed
      migration required before deploy
FIX   Authentication session bug
FEAT  Dark mode
OPS   Database migration
Notice what it did. "api is way faster now" became a PERF entry with p95 numbers attached. "killed the old v1 api" was classified BREAK and linked to the migration. That is semantic classification, not string formatting — Week 7 is where you prove it holds on inputs it has never seen.

MinuteMaker

you ship it · graded scorecard returned

MEETING TRANSCRIPT IN

SARAH: ok so the vendor thing. we can't
sign until legal clears it.
RAJ: i can chase them, probably end of
next week?
SARAH: fine. and someone needs to tell
the client we're slipping.
RAJ: that's you, you own that relationship.
SARAH: ...yeah ok.

STRUCTURED MINUTES OUT

DECISION
Vendor contract blocked pending legal review

ACTIONS
[Raj]   Chase legal on vendor clearance
        due 2026-09-18
[Sarah] Notify client of timeline slip
        owner inferred from context
The hard part is not extraction. Nobody said "Sarah owns this action" — she said "…yeah ok." Inferring ownership from a conversational concession, and knowing when you are wrong to infer it, is the difference between a demo and something a team would use.
PROOF

Built by students. Week 1, then Week 2.

Two services from Cohort 1, a week apart. Both deployed, both running, repos available on request. Thirty-three builds is this, thirty-three times.

WEEK 1

MinuteMaker

Built by Pranav in Week 1. MinuteMaker turns meeting transcripts into structured meeting minutes and action items, then delivers the summary directly to Gmail.

WEEK 2

FeedbackSorter

Built by Ankush Saha in Week 2. FeedbackSorter classifies incoming feedback by intent and urgency, then benchmarks model performance to identify the best fit for the task.

Week 1 puts two of these on your GitHub. Ten hours, one built alongside an engineer and one graded by one, ₹599 credited against the full fee.

Start the 10-hour sprint — ₹599
WHY THE OTHER 16 WEEKS EXIST

Anyone can make it work. The job is proving it does.

Below is a real evaluation run against a golden set. Four rows pass. The fifth is the one that decides whether a system ships, and most people never write it. Weeks 9 to 16 are where you do.

eval run — support-assistant v4 golden set: 120 cases
pass retrieval@5 returns the source doc118/120
pass refuses when no source matches114/120
pass p95 latency under 2000ms1840ms
pass no PII in logged completions120/120
?? the answer is actually correctno test
Most candidates get to line four. The job is line five.
5%

of custom enterprise AI tools ever reach production. The reasons are almost never the model.

MIT Project NANDA, State of AI in Business 2025. RAND puts the AI project failure rate at twice that of non-AI IT projects.
01

Evaluation

Golden sets, adversarial inputs, and a harness that runs on every change — so you can say whether the citations are real, and prove it.

02

Cost

Token accounting, prompt caching and small-model routing, with a savings report — so the number at ten times the traffic is not a guess.

03

Reliability

Tracing, fault injection and a resilience report — so you know what happens when the vendor rate-limits you at 2am.

WHO TEACHES IT

Meet the course designers and instructors.

Two practitioners, not professors. The curriculum is built by Agama Solutions, a US IT staffing firm that has placed Indian developers in American tech companies since 2005 — so it teaches what their clients interview for now. Every credential below is public and linked.

Vinay Bamil

Vinay Bamil

COURSE DESIGNER · PHD IN AI
EX GEN AI COACH, GOOGLE

Designed the course and teaches most of it. Reviews every Cohort 2 capstone personally — your architecture decisions, your tradeoffs, your deployed system.

LinkedIn ↗
Randeep S. Bhatia

Randeep S. Bhatia

CTO AT SPLASH
EX TWITCH, AUDIBLE & EA · AAAI PUBLISHED

Built systems powering 750 million streams. Patent inventor, AAAI published, 100+ conference talks, 15+ years across Twitch, Audible, EA and Splash.

LinkedIn ↗
INDUSTRY VALIDATED

Two leaders put their names to it.

Senior technology leaders who read the curriculum and went on the record.

Most AI courses produce people who can talk about AI. CoreSmart produces people who can actually ship. Every week delivers a usable artifact rather than just a certificate.

Ashish MagoCo-founder & CTO, Compliance Kart · Ex CTO, LMCE · Ex Director Technology, Publicis Sapient LinkedIn ↗

Teams already have AI tools, but delivery velocity remains unchanged. CoreSmart's model addresses the real gap by helping developers govern AI systems at scale.

Jignesh ModiCXO, Global Hospitals & Healthcare Technology · Digital Transformation & AI Leader LinkedIn ↗
17 WEEKS IN FULL

Sixteen teaching weeks. One capstone week.

Open any week to see what you learn, the stack you use, and the two projects that leave your machine at the end of it.

  • Prep week: environment setup, Python and API refresher
  • Onboarding + fast-track foundations (no prior AI assumed)
  • How modern AI products are built, layer by layer
  • LLM internals and how RLHF shapes behaviour
  • The model / retrieval / tool / memory stack
  • Streaming responses and structured output
  • Latency, cost and quality tradeoffs
PythonFastAPIPydanticOpenAI / AnthropicSSE
PROJECT 1 · BUILT LIVE
ReleaseBot — A service that streams messy notes into a clean, structured changelog.
PROJECT 2 · GRADED
MinuteMaker — A service that turns a meeting transcript into structured minutes and action items.
  • How LLMs actually work under the hood
  • Choosing the right model and provider
  • An evaluation primer: measuring quality
  • Provider tradeoffs across the market
  • Cost and latency-aware model selection
OpenAIAnthropicOpen-source modelsPython
PROJECT 1 · BUILT LIVE
IntentIQ — An intent classifier that picks the right model for the job.
PROJECT 2 · GRADED
FeedbackSorter — A tool that sorts inbound feedback by intent and urgency.
  • System prompt design and few-shot patterns
  • Strict output schemas with Pydantic
  • Function and tool calling, end to end
  • Streaming (SSE) patterns
  • Classification and routing logic
Pydantic v2Tool callingFastAPISSE
PROJECT 1 · BUILT LIVE
TicketStream — A bot that classifies and routes incoming requests automatically.
PROJECT 2 · GRADED
ReviewRouter — A bot that tags product reviews by sentiment and topic, then routes them.
  • Embeddings and cosine similarity
  • Chunking strategies and their tradeoffs
  • Vector databases and indexing
  • Multimodal ingestion — PDFs, images, tables
  • Semantic retrieval by meaning
EmbeddingsVector DBPython
PROJECT 1 · BUILT LIVE
KnowledgeVault — A search engine over your documents, by meaning not keywords.
PROJECT 2 · GRADED
PaperFinder — A semantic search tool over a set of research papers.
  • The full RAG pipeline, end to end
  • Grounding answers in retrieved sources
  • Generating trustworthy inline citations
  • Measuring whether an answer is grounded
  • Fallback behaviour when no source fits
RAG pipelineVector DBOpenAI / Anthropic
PROJECT 1 · BUILT LIVE
CitationRAG — An assistant that answers from documents and cites every claim.
PROJECT 2 · GRADED
DocuRAG — A cited RAG assistant over a document set of your choice.
  • Query transformation — HyDE, step-back
  • Reranking and context compression
  • Context engineering principles
  • Conversation state management
  • Improving retrieval measurably
HyDERerankingVector DBPython
PROJECT 1 · BUILT LIVE
RAGOptimizer — An upgraded assistant that improves retrieval and proves the lift.
PROJECT 2 · GRADED
RerankLab — A lab that applies reranking and compression to a new corpus.
  • Building golden test datasets
  • Pass/fail thresholds and metrics
  • Adversarial testing and red-teaming
  • Experiment design for AI systems
  • Turning results into a real report
Golden datasetsEval harnessPython / Pandas
PROJECT 1 · BUILT LIVE
BreakRAG — A harness that stress-tests a RAG system to find where it breaks.
PROJECT 2 · GRADED
RAGBench — A benchmark that scores a RAG system before and after on a golden set.
  • When to fine-tune versus prompt
  • LoRA and parameter-efficient fine-tuning
  • Running open-source LLMs
  • Small language models (SLM)
  • Benchmarking a tuned model
LoRA / PEFTOpen-source LLMsPython
PROJECT 1 · BUILT LIVE
SpecialistTuner — A fine-tuned small model specialised for one task.
PROJECT 2 · GRADED
DomainTuner — A small model fine-tuned on a domain dataset, benchmarked against the base.
  • Workflows versus agents, and when to use each
  • The agent loop from first principles
  • ReAct, reflection and planning patterns
  • Agent state management
  • When NOT to use an agent
Agent loopTool usePython
PROJECT 1 · BUILT LIVE
OpsAssist — An agent that completes a multi-step task on its own using tools.
PROJECT 2 · GRADED
ResearchAgent — An agent that researches a document set and writes a cited brief.
  • Multi-agent orchestration patterns
  • Router and specialist agent designs
  • Long-term and shared memory
  • Inter-agent communication
  • Coordinating a multi-step workflow
Multi-agentMemory storePython
PROJECT 1 · BUILT LIVE
TriageFlow — A system that coordinates multiple agents to resolve work.
PROJECT 2 · GRADED
DeskOrchestrator — A router-plus-specialist agent pipeline over a workflow.
  • The Model Context Protocol (MCP)
  • Agent-to-agent (A2A) communication
  • AGENTS.md and tool discovery
  • Exposing tools to agents safely
  • Building interoperable agent systems
MCPA2APython
PROJECT 1 · BUILT LIVE
AgentMesh — A mesh that connects agents and tools across an interoperable layer.
PROJECT 2 · GRADED
ToolBridge — An MCP server that exposes a set of tools to an agent.
  • Prompt injection attacks and defence
  • PII detection and redaction
  • A practical responsible-AI checklist
  • Human-in-the-loop checkpoints
  • Bias, fairness and safety basics
PII detectionGuardrailsPython
PROJECT 1 · BUILT LIVE
GuardianAI — An assistant hardened with guardrails and PII protection.
PROJECT 2 · GRADED
SafeAssist — A guarded assistant for a sensitive domain with a human in the loop.
  • Building developer-tooling agents
  • Streaming UI patterns
  • UX feedback and progressive disclosure
  • Agents that read and act on code
  • Designing agents for trust
Streaming UIAgentsPython
PROJECT 1 · BUILT LIVE
WorkbenchAI — A developer-tooling agent with a live, streaming interface.
PROJECT 2 · GRADED
PRCopilot — An agent that reviews a pull request or summarises a diff, live.
  • Containerising AI services with Docker
  • Deploying to a public URL
  • Observability: tracing and metrics
  • Versioning and rollbacks
  • Async request handling
DockerTracing / metricsCloud deploy
PROJECT 1 · BUILT LIVE
DeployCore — An AI service deployed the production way, live to a public URL.
PROJECT 2 · GRADED
ObserveOps — Tracing, metrics and versioning added to a deployed service.
  • Retries, fallbacks and timeouts
  • Circuit breakers for AI calls
  • Fault injection and chaos testing
  • Graceful degradation
  • Producing a resilience report
Reliability patternsFault injectionPython
PROJECT 1 · BUILT LIVE
ReliabilityKit — A toolkit that makes an AI service resilient under failure.
PROJECT 2 · GRADED
ChaosProbe — A probe that fault-injects a service and reports its resilience.
  • AI FinOps: measuring and cutting cost
  • Prompt caching strategies
  • Small-model routing
  • Self-healing patterns
  • Producing a cost-savings report
Prompt cachingSLM routingPython
PROJECT 1 · BUILT LIVE
CostGuard — A layer that cuts an app's AI spend without losing quality.
PROJECT 2 · GRADED
CachePilot — Caching plus small-model routing added to an app, with a savings report.

The whole course comes together in one real production system — not a demo build. Choose one of six ready-made capstone projects, each shipping with a cleaned, licensed dataset, or bring your own data and we help you source and scope it.

WHAT YOU DELIVER
A deployed capstone system, a live demo and architecture walkthrough, and 33 builds on your GitHub.
HOW IT IS GRADED
A panel reviews your build and your presentation, scored on the same four criteria, with detailed written feedback.

Week 1 is the ₹599 sprint. LMS login via email in 24 hours — build on your own schedule, submit when you are ready. Whatever you pay is credited against the full fee.

Start the 10-hour sprint — ₹599
THE CAPSTONE

Week 17: a system you present and defend.

Every track ships with a cleaned, licensed dataset. Or bring your own idea and we help you scope it.

CaseCompass

Ask 40,000 real court opinions anything: grounded, cited answers over public US case law.

LEGAL

MediGuard

A patient-info assistant with medical-grade guardrails, grounded in official health sources.

HEALTHCARE

FilingScout

An analyst agent that reads SEC filings and writes cited earnings briefs on any company.

FINANCE

StackSage

A developer support copilot trained on real Stack Exchange Q&A and open-source docs.

DEV TOOLS

TravelGenie

An agent that plans complete day-by-day itineraries, cited from real travel guides.

CONSUMER

PulseBrief

A scheduled agent that turns the week's world events into one clean, cited briefing.

MEDIA & OPS
AFTER YOU FINISH

What you walk out with, and what it is for.

Seventeen weeks produce 33 deployed builds and a capstone you have defended. The last stretch of the programme is spent making that legible to the people hiring.

Portfolio review

A working session on your repos: README structure, architecture write-ups, evaluation results and cost reports presented so a reviewer can see the judgment behind the code in under five minutes.

Interview preparation

System-design and technical interviews run against your own capstone — the tradeoffs you made, the failure modes you tested, the numbers you can defend. Same questions the curriculum was built around.

ROLES THIS PREPARES YOU TO INTERVIEW FOR
AI Engineer GenAI Engineer Applied AI Engineer LLM Engineer AI Platform Engineer ML / AI Solutions Engineer AI Product Engineer
This is not a job guarantee. We do not place you and we do not promise an outcome that depends on a hiring market we do not control. What we guarantee is that you finish with deployed systems, public repos and the ability to demonstrate rather than describe your work.
PRICING

Start with the 10-hour sprint.

It costs ₹599 because it is a real week of the course, not a sales page.

WEEK 1
₹599
Comes off the full fee if you continue. Not refundable on its own.
  • Prep week and recorded foundations, LMS login via email in 24 hours
  • Week 1 in full — ReleaseBot and MinuteMaker
  • Your graded scorecard, returned by an engineer within 72 hours of submission
  • Both builds deployed and on your GitHub, yours to keep either way
Start the sprint — ₹599
FULL PROGRAMME · COHORT 2
₹85,000₹72,250
Early bird for this cohort. List price applies from Cohort 3.
  • 17 weeks · 33 deployed builds · capstone
  • Every graded project reviewed by an engineer
  • Live weekend build sessions, recorded weekdays
  • EMI option available
  • Your ₹599 deducted from this figure
Enrol now — ₹72,250

// Enrolment closes 16 October

Post payment, LMS login via email in 24 hours. Work through it on your own schedule, submit MinuteMaker whenever you are ready, and an engineer returns your scorecard within 72 hours. Cohort 2 starts 23 October with the first live session, and enrolment closes 16 October — you need to be enrolled by then to be in the cohort.

QUESTIONS

Before you ask us.

It can, and you should let it. What it cannot do is tell you whether the retrieval is correct, what the system costs at ten times the traffic, where it fails under load, or defend the architecture to a panel deciding whether to fund it. Indian developers report the highest trust in AI tools of any major market — a combined 56% in Stack Overflow's 2025 survey. The companies hiring you do not share it: only 5% of custom enterprise AI tools ever reach production. Closing that gap is judgment, and judgment is the thing that gets graded here.

Around 10 hours a week, roughly 170 across the 17 weeks. Weekday content is recorded. Build sessions are live on weekends and recorded, so missing one does not put you behind.

No. The ₹599 sprint starts once your LMS login arrives by email (within 24 hours), you build at your own pace, and grading is rolling with a 72-hour turnaround. Cohort 2 itself starts 23 October, which is when the live weekend sessions begin. That date matters if you continue into the full programme; it does not gate Week 1.

Prep week and Week 1 in full, with LMS login via email in 24 hours — both builds, plus your graded project returned with a scorecard and written feedback from an engineer inside 72 hours of submitting. Both builds stay on your GitHub either way. Nothing waits on a cohort date. It is not refundable on its own; it is credited in full against the fee if you enrol. It costs ₹599 rather than nothing because people who pay finish.

Developers with 2+ years shipping production code. No AI background needed — Week 1 opens with fast-track foundations including a Python and API refresher, and you do not need ML going in. What you do need is fluency writing code and working with APIs, because the course spends its time on evaluation, reliability and cost rather than on teaching you to program. Under two years, the material will land as theory rather than as judgment, and judgment is the thing being graded.

Do not take our word for it — check the people. Vinay's Google and PhD credentials, and Randeep's Twitch, Audible and EA record: both public, both verifiable in a few minutes from the links above. Ashish Mago and Jignesh Modi have publicly attached their names to the curriculum. And the two Cohort 1 services on this page are running right now, and the repos are available on request.

Full refund within 14 days of enrolment, no questions asked. After 14 days the fee is non-refundable, since by then you have had the live sessions, the graded reviews and the material. The ₹599 sprint is separate and is credited in full against the fee when you enrol.

No. We guarantee you graduate with a deployed system, 33 builds on your GitHub, and the capability to demonstrate — not describe — what you built. Any programme claiming a placement guarantee in this market is either lying or burying the cost somewhere you cannot see it.

Look at it from the buyer's side rather than the developer's. 95% of custom enterprise AI tools never reach production (MIT Project NANDA), and trust in AI accuracy among developers globally has fallen from 40% to 29% in a year — 46% now actively distrust it against 33% who trust it. The skill being priced in 2026 is not generation, it is validation: evaluation pipelines, hallucination debugging, model upgrade control, adversarial testing. Using AI makes you a user. Building and governing AI systems makes you the person who signs off on shipping them.

Yes. EMI options are available at checkout on the full programme fee. The ₹599 for Week 1 is a single payment.

An engineer, every week, against correctness, completeness, design and clarity. Written feedback, never a bot and never self-assessed.

Ten hours, two deployed services, one graded scorecard. ₹599, credited against the full fee. Enrolment for Cohort 2 closes 16 October.

Start the 10-hour sprint — ₹599
10-hour sprint · ₹599Cohort registration closes 16th Oct
Start →