00
AI-Native Weekend (free entry)
Two-day live masterclass that runs the month before the cohort. Optional but recommended. Leaves you with one shipped demo and a sense of whether the discipline fits.
SHIP · 1 public demo
INNORVE ACADEMY · COHORT 1 SYLLABUS
AI-Native Architecture.
Six weeks. Three tiers. One capstone.
A live, pod-based cohort taught by engineers who shipped production AI last quarter. You leave with six public ships, your own AI-native system in your own GitHub, a governance binder that passes a real model-risk review, and a capstone you can demo in five minutes without hedging.
| Application close | June 7, 2026 |
| Cohort start | June 14, 2026 |
| Demo Day | July 26, 2026 |
| Time commitment | ~8 hours / week (Week 4 needs more — plan for it) |
| Cohort size | 40 builders, pods of 8–12, mixed tier |
| Delivery | Zoom live + Discord async + shared GitHub org |
Three tiers
One curriculum, three intensity profiles. Pods mix tiers on purpose. Same bar to graduate.
| Tier | For | Price | Summary |
|---|---|---|---|
| Launch | Students · early-career | ₹9,999 ≈ $120 | Aspirants. You can read code and write a function. You haven't shipped AI to production yet. |
| Scale | Working professionals | ₹49,999 ≈ $599 | Operators. You ship AI to production today and want the discipline of architecture. |
| Assure | Senior architects · regulated shops | ₹1,49,999 ≈ $1,799 | Staff+ engineers, architects, CTOs at regulated shops. Capstone runs through Proofroom. |
Five scholarship seats reserved per tier. Mention financial need in your application; no documents required for the first-pass review. Full pricing & payment flow at innorve.academy/pricing.
Weekly arc
Each week ends with a public ship. No ship, no graduation.
01
AI Fluency & Context Engineering
System prompts with cached context, structured outputs, tool definitions. The shape of an LLM call that does not break in week six.
SHIP · Personal AI OS + prompt pack
02
RAG & Retrieval Systems
Ingestion, chunking, embeddings, hybrid search, reranking, citation-grounded answers. RAG that survives a real corpus.
SHIP · Working RAG app on your own data
03
Agent Engineering
Multi-step agents in LangGraph or the Claude / OpenAI Agents SDK, wired through MCP to real tools. Agents as state machines, not magic.
SHIP · Multi-step agent solving a real task
04
Evaluation, Observability & Trust · MOAT WEEK
The moat week. Eval-driven development, OpenTelemetry tracing, audit trails a compliance officer will accept, hallucination quarantine. Plan more than eight hours this week.
SHIP · Eval suite + audit trail + dashboard
05
Fine-Tuning, MLOps & Production
When fine-tuning beats prompting, LoRA / QLoRA on Modal or HF, deployment with canary rollout, cost tuning. Production discipline.
SHIP · Deployed, monitored, cost-tuned agent
06
Capstone & Demo Day
Scope, build, eval, govern, demo. Five-minute pitch, governance binder, live Q&A from a skeptical room. Graduate the way you would defend in production.
SHIP · Capstone + governance binder + pitch
Outcomes — what you can do by Week 6
These are not aspirations. They are the bar for graduation.
- 01Engineer a system prompt with cached context, structured outputs, and tool definitions a junior dev cannot produce by vibes alone.
- 02Stand up a production-grade RAG pipeline: ingestion, chunking, embeddings, hybrid search, reranking, citation-grounded answers.
- 03Design and ship a multi-step agent with LangGraph or the Claude/OpenAI Agents SDK, wired through MCP to real tools.
- 04Write an eval suite in Braintrust or Langfuse that catches regressions — golden datasets, LLM-as-judge, hallucination checks — and run it in CI.
- 05Instrument OpenTelemetry tracing, produce an audit trail a compliance officer will accept, and explain the difference between a trace and a log.
- 06Decide with numbers when fine-tuning beats prompting, run a LoRA/QLoRA job on Modal or HF, and deploy with canary rollout.
- 07Produce a governance binder: model card, risk assessment, eval report, prompt register, audit trail.
- 08Pitch your work in five minutes to a skeptical room and survive the Q&A.
The capstone
The capstone is the weeks-1-through-5 stack, cleaned up, wrapped in a governance binder, and pitched live to a room of alumni, instructors, and invited hiring partners. This is the week you stop being a student and become the person you list on your LinkedIn headline.
Required components
- A working AI-native system in your own GitHub repo, Apache 2.0.
- Governance binder: model card, prompt register, eval report, audit trail, risk assessment. Mapped to at least one framework (SOC 2, HIPAA, PCI, EU AI Act, NIST AI RMF, or DPDPA).
- Live 5-minute Demo Day pitch + Q&A.
- Peer review completed for every other pod member’s weekly ships (pass/fail, not letter-graded).
Assure-tier addendum
Capstones in the Assure tier run through Proofroom — a sealed manifest, an evidence binder, and a CCO-runnable verification transcript before Demo Day. See innorve.academy/sample-binder for the synthetic shape.
Refunds, withdrawals, deferrals
Within 7 days of payment confirmation: full refund, no questions. Days 8 to end of week 1: pro-rated by week. After end of week 1: no refund — pod dynamics depend on stable participation. Documented medical or family emergencies are exceptions and roll to the next cohort with priority. Full policy at innorve.academy/faq.
Apply
Cohort 1 applications close June 7, 2026. We review every application within 48 hours. Acceptance comes with a payment link and onboarding email.
Apply at innorve.academy/apply
Innorve Academy · Cohort 1 Syllabus · v2026-04-30 · innorve.academy