A part-time program for working professionals. Ship 20+ real builds with Claude Code, n8n and Supabase. Launch your own product. Pitch it to 25+ VCs at Demo Day.
Underneath all five: you learn to build by actually building.
Over the last year, a lot of working professionals have asked us the same thing: how do I learn to build with AI without quitting my job? And every existing answer was wrong for them. Full-time programs need you to quit. Online courses give you videos and a certificate, and most people finish neither. So we designed PGPx Ascend around one idea: you learn to build by actually building.
It starts with a 3-week online ramp, so if you've never written code you're not behind on day one. Then 5 days on campus in Bangalore for a kickoff. After that, for six months: two weekends a month online and one weekend a month on campus. Every weekend you are taught something and then you build something real. Months 7 and 8 are a sprint: your team, a mentor, one product, launched, with users, pitched to 25+ VCs at Demo Day.
A few things you should know. The program is rigorous. "I'm working" cannot be an excuse. It is not for job seekers; we don't offer career assistance. Getting in will be hard, because the quality of the cohort matters to us.
Five phases. You always know which weekends are online, which are on campus, and what you'll have shipped by the end of each.
How software works, AI literacy, builder stack set up. 2–3 hrs/week. Mandatory. It's also how you earn your seat.
Ship: live GitHub profile + verified stack
Meet the cohort, first automation, first deploy, first pod build, first demo. Full days.
Ship: 2 builds, portfolio live
Automations → Agents → Full-stack → Consumer app → B2B product → Pick your problem. 8 hrs live + 4–6 hrs build per week.
Ship: 15+ builds, 5 hackathon products
No lectures. Your team, one product, a mentor who has built with AI, weekly 30-min demos. 10–15 hrs/week.
Ship: the product itself, live, with users
Dress rehearsal, then a live pitch with real traction to a room of 25+ investors.
Ship: your pitch, delivered
Every month ends with something real, deployed, and public. Six of them, in order:
Triggers, webhooks, APIs, error handling. Then a cross-tool workflow between Gmail, Slack, Sheets and WhatsApp running on a schedule.
Tools, memory, orchestration, evals and guardrails. Deployed inside your email, Slack and calendar via MCP.
Schema design, auth, embeddings, transactional email, a payment page, analytics events, then a full redesign.
Signup-to-activation flow, trial and paywall design, instrumented funnel, then a public launch playbook.
Roles, permissions, billing, admin dashboards. Demos, pilots and onboarding, getting an organisation to adopt.
Pick a problem with evidence, recruit first users by hand, form a team, get a mentor, sprint for 8 weeks, pitch to 25+ VCs.
Go through it. If it feels right, apply. Each row is one weekend: what we cover, the tools, what you ship, and what you can do afterwards that you couldn't before.
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 1Self-paced | How software works, for non-engineers: code, APIs, databases, servers. | - | Foundations module + quiz | "The jargon doesn't scare me anymore." |
| Week 2Self-paced | AI literacy: what LLMs are, prompting with intent, why models fail. | ClaudeChatGPT | 10 real work tasks done with AI, documented | "I use AI daily, with intent." |
| Week 3Self-paced | Builder stack setup, guided: accounts, GitHub profile, first hello-world deploy. | GitHubSupabaseVerceln8nClaude Code | Live GitHub profile + verified working stack | "My stack is ready. I've earned my seat." |
| Day | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Day 1 | How AI works under the hood: model behaviour, context windows, cost, failure modes. | ClaudeClaude Code | Stack verified; first prompted builds | "I understand how AI actually works." |
| Day 2 | From prompting to building: n8n fundamentals, first workflow logic. | n8n | First working automation, live before dinner | "I built my first automation in a day." |
| Day 3 | Claude Code day one: repos, commits, deploys. Public portfolio begins. | Claude CodeGitHubVercel | Personal site deployed; first public commit | "I have a live website I built myself." |
| Day 4 | Full build day in pods: idea to working project, end to end. | Full stack | A personal project shipped in one day | "Idea to working product in a day." |
| Day 5 | Demo Day Zero: every student presents. Program mechanics, portfolio rules, cohort bonding. | - | First public demo; portfolio live with 2 builds | "I can demo what I build." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 1Online | n8n deep dive: triggers, webhooks, APIs, error handling. | n8nREST APIs | An automation solving a real task from your job | "I can automate any repetitive task in my job." |
| Week 2Online | Claude Code fundamentals: prompting for code, Git, debugging, deploying. How to evaluate AI-generated work. | Claude CodeGitHubVercel | A web app, deployed and live | "I can ship a web app without being a developer." |
| Week 3Online | Connecting your world: Gmail, Slack, Sheets, WhatsApp; scheduling and monitoring. | n8nGmail/Slack/Sheets APIs | A cross-tool workflow on a schedule | "My everyday tools talk to each other." |
| Hackathon 13 days · campus | "Automate your job": build an internal tool for your own company under time pressure. | Full automation stack | An internal tool your company can use on Monday | "I built something my company can use, in 3 days." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 4Online | Agent fundamentals: tools, memory, orchestration, system prompts. How models reason. | Claude APIAgent frameworks | A research agent that works autonomously | "I can build an AI that works on its own." |
| Week 5Online | Multi-step agents: reliability, evals, guardrails. Evaluation as a durable skill. | Eval tooling | An agent that uses 2+ tools reliably | "I can make agents reliable enough to trust." |
| Week 6Online | Agents in the wild: MCP, connecting to email, Slack and data; auth and permissions. | MCPSlack/Gmail | An agent working inside your daily tools | "I have an AI teammate inside my tools." |
| Hackathon 23 days · campus | Agent-a-thon: teams build an agent product end to end. | Full agent stack | A complete agent product, built and demoed by your team | "My team shipped a working agent in 3 days." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 7Online | Databases with Supabase: schema, auth, storage. Give AI your own data: embeddings. | Supabasepgvector | An app with login, a database, and AI answering over its data | "I can build apps that remember users." |
| Week 8Online | Product plumbing: transactional email, payments, analytics events. | ResendRazorpay / Stripe | An app that can charge money | "I can build something people pay for." |
| Week 9Online | UI/UX: design fundamentals, taste, component libraries, responsive design. | FigmaTailwind / shadcnv0 | A full redesign of your strongest earlier build | "My products look professional, not like prototypes." |
| Hackathon 33 days · campus | Ship a micro-SaaS in 3 days and get your first external users. | Full product stack | A micro-SaaS with first external users | "Strangers on the internet used something I built." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 10Online | Consumer foundations: signup/login, onboarding, trial design, hard vs soft paywall. | Supabase Auth | A consumer app with a real signup-to-activation flow | "I can design flows that turn visitors into users." |
| Week 11Online | Monetisation & analytics: payment page, trial-to-paid, usage analytics, retention. | Razorpay / StripePostHog / Mixpanel | A live paywall + fully instrumented funnel | "I can see exactly where users pay." |
| Hackathon 43 days · campus | Public launch: a Product Hunt launch as part of the curriculum. Launch prep, hunter outreach, live feedback. | Product Hunt | Your consumer app launched publicly, with real users | "I launched a product to the world." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 12Online | B2B foundations: business workflows, roles & permissions, invoicing, admin dashboards. | Supabase RLSDashboards | A B2B tool solving a real workflow (invoicing as the canonical build) | "I can build software businesses run on." |
| Week 13Online | B2B adoption: demos, pilots, onboarding, training, driving uptake inside an organisation. | Demo & onboarding tooling | A live pilot with a real business (your own company counts) | "I can sell software to a business and make it stick." |
| Hackathon 53 days · campus | B2B hackathon: build against a real company brief; negotiate and close a pilot. | Full B2B stack | A pilot with a real company | "A real company committed to using my product." |
| Week | What we cover | Tools | What you ship | "I can now…" |
|---|---|---|---|---|
| Week 14Online | How to pick a problem: founder-market fit, service-as-wedge, evidence over opinions. | Validation frameworksCustomer interviews | 3 problem statements backed by real evidence | "I know how to find problems worth solving." |
| Week 15Online | First users & consumer love: concierge MVPs, things that don't scale, distribution, pitch story. | Pitch craft | V1 pitch + a named list of committed first users | "I can get my first users and tell the story that wins them." |
| Hackathon 63 days · campus | The Hinge: idea lock, team formation, mentor attached to every product, sprint plan committed. | - | Locked idea, formed team, committed 8-week plan | "I know exactly what I'm building for the next 2 months, and with whom." |
| Phase | What happens | Support | What you ship | "I can now…" |
|---|---|---|---|---|
| Weeks 25–32Sprint | No lectures. Protected building time. Operate like a founding team: build, launch, get early users and feedback. | Weekly 30-min mentor demoAsync office hours | THE product: live, with users, traction and a story | "I'm not learning to build anymore. I'm a builder." |
| Demo Day2 days · campus | Dress rehearsal day, then Demo Day in front of 25+ VCs. | - | Your pitch, delivered to a room of investors | "I pitched my own product to 25+ VCs. Whatever happens next, I can build." |
Friday to Sunday at Mesa's Bangalore campus. Three days, one brief, a room full of people building next to you.
Build an internal tool for your own company, scoped and shipped under time pressure.
Teams design, build and demo a complete agent product end to end.
Compress the entire product loop into 72 hours and onboard strangers.
A Product Hunt launch as part of the curriculum. Launch prep, hunter outreach, live feedback.
Build to a customer's spec. Negotiate and close a pilot with a real business.
Idea lock, team formation, a mentor attached to every product, sprint plan committed.
Demo Days are hosted by the Mesa Startup Lab. After the 2-month sprint your team pitches its product, with a live demo, real users and real traction, to VCs from across the country.
Product, ops, marketing, finance, consulting. You use AI daily but can't yet turn an idea into a working product. In 8 months you will.
You want the next promotion sooner, and you've noticed that the people getting it are the ones who ship things. Automate your team's work, build the internal tools nobody else can, and become the person the company turns to for AI.
You run a business or a team. You want to automate it, build products around it, and stop waiting on a dev team for every idea.
| Online course | Full-time PGP | PGPx Ascend | |
|---|---|---|---|
| Format | Recorded videos, self-paced | 12 months, residential | 8 months, weekends: 2 online + 1 on campus per month |
| Your job | Keep it | Quit it | Keep it |
| Time | Whenever you want, which usually means never | Full-time | ~8 hrs live + 4–6 hrs build per week |
| What you leave with | A certificate | Placements and job outcomes | 20+ shipped builds on GitHub, one launched product with users |
| Peer group | None | Freshers / early-career | 50 working professionals, curated by interview |
| Campus & hackathons | No | Yes, daily | 6 × 3-day hackathons in Bangalore |
| Demo Day with VCs | No | Yes | Yes, 25+ VCs |
| Completion rate | Typically under 15% | High | Built for completion: cohort, campus, mentor, public portfolio |
Build weekends are led by people who ship with these tools every week. Every sprint team gets a mentor who has built with AI. Founders and VCs from Mesa's network join as guests through the year.
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
[Two lines on what they've built and what they'll teach you.]
Roughly 12–14 hours a week for six months, then 10–15 hours a week self-directed during the sprint. Weekday evenings are yours, except async office hours you can join if you're stuck. Outside Bangalore? Budget one trip a month, Friday to Sunday.
Online sessions are recorded. The build is still due. Hackathons cannot be made up, so plan your calendar around the six campus dates before you apply.
The quality of the cohort matters more to us than filling seats. 50 seats. Applications reviewed in rounds.
| Round | Deadline | Program fee |
|---|---|---|
| Early bird | 7 October 2026 | ₹ 11,75,000 + GST |
| Round 1 | 5 November 2026 | ₹ 12,00,000 + GST |
| Round 2 | 1 December 2026 | ₹ 12,25,000 + GST |
| Round 3 (final) | 22 December 2026 | ₹ 12,50,000 + GST |
GST at 18% applies. Fee includes all campus hackathons, kickoff week and Demo Day. Travel and stay in Bangalore not included. Seats are typically 80% full by the end of Round 2.
Yes, if you protect the weekends. Budget ~8 hrs live plus 4–6 hrs of building per week for six months, then 10–15 hrs/week during the sprint. Weekday evenings are free apart from optional office hours. It is rigorous by design; "I'm working" is not an excuse we accept once you're in.
Most of the cohort won't have. The 3-week on-ramp covers how software works, AI literacy and setting up your stack before day one. From there the tools (Claude Code, n8n, Supabase) are built for people who can describe what they want clearly, which is a skill we teach.
No. Two of every three weekends are online. You need to be on campus for the 5-day kickoff, six 3-day hackathons (Fri–Sun, once a month) and Demo Day. Plan for one trip a month.
Online sessions are recorded and the build is still due that week. Campus hackathons can't be made up. The six dates are published before you apply so you can block them.
No. Ascend is not for job seekers. It is for people who want to become AI-native operators and product builders. What you leave with is 20+ public builds, a launched product, a VC pitch and a 50-person builder network. That tends to change careers on its own.
It's yours: IP, users, everything. Teams that want to continue can apply to the Mesa Startup Lab for incubation and follow-on support.
50 working professionals with 2+ years of experience, selected by assignment and interview. Product, ops, marketing, finance, consulting and software engineers who want to move into product and business roles.
[Refund window and deferral terms to be confirmed.]
50 seats. Cohort 1 starts 7 January 2027. The full curriculum is above. If it feels right, apply.