Skip to content
Launchpad
Enrol

T2· Engineering: tech

AI-native Software Development

You will build and ship real software with AI coding agents while staying the engineer who can test, review and explain every line.

Choose a planRead the syllabus
Who it is for
Students from any CS-adjacent branch who already write code and want to work the way modern teams do with Claude Code, Copilot and Cursor. Laptop required.
AI core
9 units · 20 h
This course
6 modules · 12 lessons · 2.3 h
Live projects
2, on Professional and Career
01Roles it prepares you for
  • Software Engineer Trainee / SDE-1
  • Full-stack Developer
  • AI-native Software Engineering Intern

The skills these roles ask for. Preparation, not a promise of a job.

02Tools you will use
  • GitHub Copilot Student (verified students)Free tierVerified
  • GitHub Copilot FreeFree tierVerified
  • Claude Code (paid plans or API key; Saarthi sandbox credits)Saarthi sandboxVerified
  • Cursor free planFree tier
  • VS CodeFree tier
  • Git and GitHubFree tier
  • GitHub ActionsFree tier
  • pytestFree tier
  • Hypothesis (property-based testing)Free tier
  • Anonymised seller data pack v1 (Saarthi sandbox)Saarthi sandbox

You never pay for a tool subscription. “Verified” means we checked the free access on the vendor’s own site this month. Tool names describe what you learn; no vendor endorses Launchpad.

03Syllabus

What you will learn, in order.

Lesson films are narrated with an AI voice, over visuals made with AI tools and checked by our team. Saarthi, the coach, is an AI. Mentors and reviewers are people.

Part 1 · The AI core, shared by every stream

00Set up your coach1 hLearn how the core works, write the learning-context document that tells every AI tool who you are, and set Saarthi up as a coach that makes you think instead of thinking for you.
  1. How this core works6 min
  2. Write your learning-context document8 min
  3. Seven roles for AI, and study modes7 min
01How LLMs work and fail2.5 hBuild a working mental model of a large language model: tokens, prediction, context windows and memory. Then learn its predictable failures (hallucination, sycophancy, stale knowledge, bad arithmetic) and reproduce them yourself.
  1. Tokens and next-word prediction7 min
  2. Context windows and memory7 min
  3. Hallucination, sycophancy and other failures8 min
  4. Lab: one prompt, three models, five failures8 min
02Description and context engineering3.5 hWrite briefs that get the right output the first time: role, task, context, examples and format. Then make them reusable with Claude and ChatGPT Projects, Gemini Gems, custom GPTs and NotebookLM, and learn to work with PDFs, spreadsheets and images.
  1. The brief: role, task, context, format8 min
  2. Examples and output formats7 min
  3. Projects in Claude and ChatGPT8 min
  4. Gems, custom GPTs and NotebookLM8 min
  5. Working with files: PDFs, spreadsheets, images8 min
03Verify everything2.5 hCheck AI output the way fact-checkers do: lateral reading, tracing citations and numbers to the original, using deep-research modes without trusting them blindly, and testing a prompt properly with a 10-case golden set.
  1. Lateral reading7 min
  2. Checking citations and numbers8 min
  3. Deep-research modes: use and limits7 min
  4. Your first eval: a 10-case golden set8 min
04Connectors and MCP2 hConnect AI to the places your work lives (Drive, Gmail, Sheets, business data) without writing code. Learn what an MCP server is, why a reviewed directory differs from unreviewed community servers, how to grant the least access that works, and how to keep browser extensions on a short leash.
  1. What connectors and MCP are8 min
  2. Trust, least privilege and the reviewed directory8 min
  3. Browser extensions and AI browsers7 min
  4. Lab: ask the seller-data MCP server, check every answer8 min
05Agents and automations3.5 hHand multi-step work to AI safely. Tell an agent from an automation, decide what to delegate, use browser and coding agents with care, and build an n8n workflow that uses AI with a human-approval step before anything leaves the system.
  1. Agents vs automations: what to delegate8 min
  2. Browser agents, safely7 min
  3. Automation basics with n8n and Zapier8 min
  4. Lab: build an automation with a human-approval step8 min
  5. Failure modes and your failure-mode note7 min
06AI for learning and careers1.5 hUse AI to learn faster without outsourcing the learning, write applications that still sound like you, and practise interviews out loud with Saarthi.
  1. Learning with AI, not instead of learning7 min
  2. Applications in your own voice7 min
  3. Mock interview with Saarthi8 min
07Diligence: law, ethics, integrity2.5 hThe rules that apply when you use AI in India: the DPDP Act 2023 and its 2025 Rules, academic integrity and disclosure, copyright (including where Indian law is still unsettled), and bias. You finish by writing your own AI-use policy.
  1. DPDP Act 2023: personal data and AI8 min
  2. Academic integrity and disclosure7 min
  3. Copyright and AI in India8 min
  4. Bias and fairness7 min
  5. Write your personal AI-use policy7 min
08Core capstone1 hPut all four Ds together on one anonymised marketplace settlement file: ask good questions, automate one step, verify every number against Saarthi's P&L engine, and defend your work live in five minutes.
  1. The capstone brief6 min
  2. Lab: ask, automate, verify8 min
  3. Prepare your 5-minute defence7 min

Part 2 · AI-native Software Development

01How AI coding agents work2 lessonsThe agent loop for code, instruction files, where agents are strong and weak, and what students can access for free.
  1. Coding agents, honestly9 min
  2. Lab: set up your AI-native workspace12 min
02Specs, plans and small diffs2 lessonsDeciding what correct means before code exists, reviewing agent plans, and working in small tested commits.
  1. Spec first, then let the agent build9 min
  2. Lab: spec-first MTR parser14 min
03Testing AI-written code2 lessonsProperty-based tests, golden files and mutation thinking, so that tests and not hope tell you the code is right.
  1. Property-based testing for money and parsers9 min
  2. Lab: properties that catch real bugs14 min
04Reviewing and explaining AI code2 lessonsA review method and checklist for generated code, using AI reviewers as second readers, and explaining every line.
  1. Code review when the author is an AI9 min
  2. Lab: review a PR with planted defects15 min
05Debugging and refactoring with agents2 lessonsReproduce, isolate, then fix: bisecting history and data, hypothesis-driven debugging, and refactoring under tests.
  1. Debug like an engineer, with an agent9 min
  2. Lab: two bugs and a safe refactor15 min
06Full-stack delivery2 lessonsA boring, testable architecture, secrets and CI, and directing an agent to build a dashboard you can defend.
  1. Architecture and delivery for AI-built apps9 min
  2. Lab: dashboard skeleton with CI16 min
04Live projects

Two briefs. Real-shaped work.

  1. Project 1

    Parser library for messy marketplace exports

    Sellers live in CSV and spreadsheet exports from Amazon and Flipkart, and those files are messy: byte-order marks, summary rows, Indian number formats, mixed date formats, tax columns that differ by state, and refunds shown in several ways. Build a Python or TypeScript library that parses the anonymised MTR, Amazon settlement and Flipkart settlement files from the data pack into typed records, never drops a row silently, and proves it read every rupee. Use AI coding agents throughout, and keep a prompt and diff log that shows your engineering judgement.

    You hand in

    • A package with parsers for at least three export types, typed record models and a parse report (rows read, parsed, skipped, with reasons)
    • Example tests for every oddity found in the fixtures, plus at least four Hypothesis or fast-check properties (conservation, round trip, invariance, a domain rule)
    • Reviewed golden-file tests on anonymised fixtures and a green CI pipeline
    • PROMPTLOG.md covering every agent task: prompt, tool, commit, what you accepted, changed or rejected, and why
    • A README with usage, the known limitations and the business rules you chose
    • A 10-minute walkthrough in which you explain any function and test chosen by the reviewer

    Data: Anonymised seller data pack v1: mtr_b2c.csv, settlement_v2.csv, flipkart_settlement.csv, returns.csv, plus a synthetic 'ugly fixtures' set with planted format problems. Reviewed by Saarthi against a published rubric, signed off by a mentor.

  2. Project 2

    Full-stack mini seller dashboard you can explain line by line

    Build a small full-stack dashboard that shows a seller where their money went per SKU and month, from revenue through fees, refunds and reimbursements to net payout, using your Project 1 parsers on the anonymised data pack. Use AI agents to move fast, including for tests, but you must explain every AI-written test line by line in a live defence. Numbers must match the reference outputs for the data pack, and the app must be secure enough to hold seller data.

    You hand in

    • A deployed or locally runnable app (backend, database, frontend) with authentication, a month picker, a sortable SKU table and a revenue-to-net waterfall
    • P&L logic in one tested module, with unit tests, at least one property, API tests and one end-to-end test
    • A CI pipeline that lints, type-checks, tests and builds on every push
    • TESTS_EXPLAINED.md with a line-by-line explanation of every AI-written test and what bug it would catch
    • A prompt and diff log, plus a short security note (secrets, auth, data handling)
    • Peer review of another student's dashboard and a 15-minute live defence

    Data: Anonymised seller data pack v1: orders.csv, settlement_v2.csv, returns.csv, sku_master.csv, with engine_outputs_v1.json for checking totals. Reviewed by Saarthi against a published rubric, signed off by a mentor.

05Practise out loud

In voice mock interviews and client calls, Saarthi plays: Arjun, a senior engineer on a D2C brand's tech team, running a 60-minute pair-programming round. He hands you a failing test and a messy marketplace export, lets you use an AI assistant, and stops you every few minutes to ask you to explain the line you just accepted and what would break without it.

On plans that include mock interviews. You get written feedback after every call.

06Enrol

Pick a plan for AI-native Software Development.

One payment. The access deadline for each plan is shown before you pay.

  • Foundation

    01

    Learn the AI your field now runs on.

    ₹2,999

    One payment. GST included.

    • Access for 120 days (about 4 months) from the day you pay
    • No 1:1 mentor sessions
    • The common AI core and your domain course
    • Saarthi, your AI coach, any hour
    • Hands-on labs on free tools
    • Verifiable certificate
    Enrol on Foundation

  • Professional

    02

    Prove it on real work.

    ₹7,999

    One payment. GST included.

    • Access for 180 days (about 6 months) from the day you pay
    • One 1:1 session with a mentor
    • Everything in Foundation
    • Two live projects, reviewed by Saarthi and a mentor
    • Public portfolio page of verified work
    • Voice mock interviews
    • One 1:1 coaching session
    Enrol on Professional

  • Career

    03

    Work alongside our team.

    ₹14,999

    One payment. GST included.

    • Access for 240 days (about 8 months) from the day you pay
    • Four 1:1 sessions with a mentor
    • One 1:1 call with an industry expert
    • Everything in Professional
    • Four-week supervised practicum with the Saarthi team
    • Four 1:1 coaching sessions with your mentor
    • An exclusive 1:1 call with an industry expert in your field
    • CV and LinkedIn review
    • Priority mentor replies
    Enrol on Career

Your access period starts the day you pay and is shown before you pay. One exam pause per enrolment, for up to 15 days. When access ends the course locks, and your portfolio page and certificate stay live. Full refund within 7 days, pro-rata after that, and an automatic refund for any practicum, 1:1 mentor or expert session we do not deliver. Refund policy