Aishwarya Ashok speaking on stage, mic in hand

▶ hands-on building · speaking · startup advisory

Build with AIsh

Bring AI into how you and your team build.

I build with you, 1:1 or with your team, on your stack and your backlog, and we leave with something that runs. Not coaching from the sidelines. Invite me to speak, bring me in to build with your team, or have me alongside while your startup makes its first AI bet.

Not sure which? Email me what you’re trying to ship and I’ll suggest the smallest useful first step.

Maven instructorStanford Seed Spark mentorStartup AI advisorTop 200 Creators · IndiaHost · The Founder’s FoyerLinkedIn Top Voice · AI & Tech

01 · speak

Invite me to speak

Keynotes, panels, and fireside chats on agentic AI, AI-native product building, and what changes for a product team when the agent writes the first draft. Practitioner talks, with live demos.

  • conferences & meetups
  • company all-hands & offsites
  • podcasts & livestreams
spoken at
on air
+ 8 more
Invite me

02 · train

Train you or your team

1:1 build sessions and team workshops on Claude Code, agents, evals, and the layers around them, for PMs, founders, and teams who need to ship with AI. We build on your stack and your backlog, and you leave with something that runs. Starting from zero? We begin with one workflow and write the contract before we touch a tool.

  • 1:1 build sessions
  • product & engineering teams
  • leadership cohorts
taught at
Plan a session

03 · advise

Startup AI advisory

0→1 product strategy, go-to-market, positioning, and early product marketing for AI-first startups: the same work I do with incubator founders, after 10+ years of shipping zero-to-one in SaaS.

  • pre-seed to Series A
  • deciding where AI fits first
  • GTM & positioning resets
advising with
Get in touch
5.0· 54 reviews

Maven · with Hamza Farooq

Claude Code in Practice

Build AI-native products with Claude Code: skills, subagents & agent teams.

Six applications, end to end: CLAUDE.md files that work, reusable skills, specialised subagents, coordinated agent teams, evals for AI output, and a deployable product by the last session.

for PMs · builders · founders

See the course
4.8· 141 reviewsFeatured on Lenny’s list

Maven · with Hamza Farooq

Agentic AI for Product Managers

Design, build, and deploy AI agents your business can run on.

Find the high-impact use cases, design and evaluate production-ready agents, and learn orchestration, memory, retrieval, and guardrail patterns well enough to lead the initiative yourself.

for PMs · business leaders · career switchers

See the course

Praxel Ventures × Masters’ Union

Building AI agents

Hands-on sessions on building AI agents.

I teach building AI agents with Praxel Ventures and Masters’ Union. Sessions and announcements go up on Praxel’s LinkedIn.

See Praxel’s updates

Prefer it private? The same curriculum on your own backlog: train your team.

Aishwarya speaking on stage at Zoholics
keynote · Zoholics
Aishwarya running an agentic-systems workshop for a team in a meeting room
agentic systems workshop · in the room
A Maven cohort on a video call with Aishwarya and Hamza Farooq
Maven cohort · with Hamza Farooq

▶ what I teach, and why it holds

The agent is the smallest part.

Whether it works a hundredth time is decided by the six layers around it, and building them is product work, not engineering work. Acceptance criteria become rubrics; edge cases become boundaries.

  1. 01Contractwhat the job is, and what ‘done’ must produce
  2. 02Harnessthe tools it can use, the notes it reads first, what it may touch
  3. 03Rubricshow ‘done’ gets separated from genuinely good
  4. 04Memorythe learning that carries forward to the next run
  5. 05Boundarieswhat must stay true while the agent works
  6. 06Statewhere the work stands, so it can continue instead of restarting

“Implementation gives us speed, but constraints give that speed the right direction. Coherence is what emerges when we keep doing both together.”

▶ more than vibe coding

Vibe coding is how most of us got our first working thing: prompt, look, prompt again. A builder’s job is what comes after: what ‘done’ must produce, what the agent may touch, what good means, what to keep for next time. That’s the difference between a demo and a system, and it’s what I teach.

  • prompt until it looks righta contract that says what ‘done’ must produce
  • the model can reach everythinga harness that decides what it may touch
  • ‘looks good’ is the reviewrubrics that separate done from genuinely good
  • re-explain it every sessionmemory and state, so the next run starts smarter

▶ learn from the conversations

The Founder’s Foyer

Hallway conversations with the people building the tools you use: 66+ episodes on AI, product, and growth, and a good chunk of what I teach was first worked out on this show.

with Shreyas Doshi · Casey Winters · Jonny Burger (Remotion) · Ryan Carson · Jaclyn Konzelmann (Google Labs) · Claire Vo (ChatPRD) and more

Follow along
Aishwarya AshokAI Product Builder · Teaching Agentic AIpublic post · 🌐Lately, as I’ve been building more workflows, agents, and configurations around models, I’ve been wondering about the difference between ‘abundant implementation’ and ‘abundant constraints.’ Because we can now turn an idea into a prototype or a functional app so quickly, the natural instinct is to keep building. Ship more ideas, automate more work, and give the model more things to do. There is nothing wrong with that. The more important trait is not simply being able to implement abundantly. It is being able to create abundant constraints around that implementation. When we ask a model to build something and leave the rest open, we give it far more control over the work than we realise. Constraints are how we bring our own judgment back into that process.…see more31 · 2 commentsLinkedIn News Indiafeaturing Aishwarya on AI burnoutpublic post · 🌐“AI hygiene in the way you actually work with AI… is going to get a lot more attention.” Most organisations sit at one of two extremes — mandating AI use, or employing it for optics’ sake — and few have found the intentional middle ground.…see more824 · 161 commentsAishwarya AshokAI Product Builder · Teaching Agentic AIpublic post · 🌐A few product + AI musings I’ve been sitting with lately and wanted to write down: 📌 Systems thinking is more than ever crucial, especially building and working with AI agents. Being able to think in steps, understand every order of operation, and knowing the overall architecture behind, and finally how all of these are interconnected, will get us in the right path with agents. 📌 A lot of product building is going to exist in the boundaries — whatever we call today as loops, graphs, harness, and the next pressing thing that’ll be highlight, all point back to a way boundary can be defined and applied.…see more63 · 18 comments

Why me, on one card

I’m a product builder who crossed over from telling product stories to shipping them, and then from shipping products to shipping them with agents. What I teach is what I do the other six days of the week.

  • 10+ years in SaaS, from zero-to-one products to hands-on building with models, agents, and workflows.
  • Co-teach two Maven courses with Hamza Farooq, including a course featured on Lenny’s list.
  • Trained 50+ global partners at Zoho across US, EU, India, ANZ, and UK markets.
  • Mentor for Stanford Seed Spark entrepreneurs; startup advisor with WeWork Labs and Aalamaram Incubator.

If you want the longer version, it’s on my about page; the interviews and bylines are under featured in.

Aishwarya

Let’s build

Drop me an email, and let’s build agentic AI systems together.

aishwaryaashok@gmail.comor chat with Aish’s AI first