The archive
Essays
Meet the Builders: PathSetu — a Cloud Run AI mentor for first-generation students in India
Meet the Builders: 1000 Builders. 1000 Stories.
Program: Gen AI Academy APAC Edition
I am Abhishek Kumar. I am in Google Cloud Gen AI Academy APAC Cohort 3. This is my Meet the Builders story. Early-stage is allowed. A real local problem is not optional.
Watch the story
PathSetu Meet the Builders video — 1080p, about 4 minutes. Same story as this write-up. Google Drive link will be added here after upload (Anyone with the link).
The local problem
In India, career advice still concentrates in a few metro campuses and a few LinkedIn circles. First-generation students in tier-2 and tier-3 cities — Indore, Ranchi, Coimbatore, Guwahati, Nashik — often have the degree, not the map.
They get stuck on the same three questions:
- What role am I actually hiring for — PM, BA, operations, data — and what does “good” look like in year one?
- How do I turn college projects into a portfolio a hiring manager will trust?
- What should I practice this week, not “learn product management” as a slogan?
Generic chatbots hallucinate salary numbers, invent company processes, and give advice that does not match campus placements, family constraints, or Hindi/English mixed interviews.
That is a local access problem, not a content shortage.
What I am building
PathSetu is a student-facing AI mentor on Cloud Run. It answers in plain language, grounded in a curated career knowledge base (role definitions, portfolio rubrics, interview drills, weekly plans) — not the open internet.
If the question needs a human (a specific college placement cell, mental health, a scholarship office), it says so and stops.
Mapped to the Cohort 3 labs:
| Cohort 3 lab | PathSetu equivalent |
|---|---|
| Personalized customer experience (ADK + RAG) | Mentor agent that retrieves role maps, portfolio checklists, and interview drills from approved notes |
| Location intelligence (Gemini + BigQuery / MCP) | Where to run campus workshops first: city/college clusters with high demand and weak mentor supply |
| Operations productivity agent on Cloud Run | Placement-cell / campus-club assistant for session plans, follow-ups, and weekly practice queues |
Architecture (production path)
Path: Student → ADK + Gemini → RAG knowledge pack → Cloud Run → grounded answer, or human handoff.
| Step | What happens |
|---|---|
| 1. Ask | Student writes in plain language |
| 2. Reason | ADK + Gemini on Cloud Run |
| 3. Ground | Retrieve from the curated pack — not the open web |
| 4. Decide | Cite and answer, or stop and hand off to a counsellor / college office |
| 5. Locate (Track 2) | BigQuery + MCP: demand vs mentor supply by city/college |
| 6. Ops (Track 3) | Placement-cell agent: session plans and weekly queues |
Rules I will not break:
- No invented salaries, headcount, or “guaranteed placement” claims
- Cite the retrieved note when the answer is process-specific
- Escalate when the user needs a human counsellor or official college office
- Keep student PII out of prompts; treat chat logs as sensitive
Why this matters in APAC
Mentor access is uneven. A grounded agent on Cloud Run will not replace a good teacher. It can give a first-generation student a repeatable weekly plan at 11pm, in the language they actually use, without waiting for a metro mentor to reply.
#MeetTheBuilders #1000Builders1000Stories #GenAIAcademyAPAC #CloudRun #ADK
- Get link
- X
- Other Apps
Agentic AI: How It Will Redefine the Role of Product Managers in the Next 5 Years
The role of a Product Manager has always lived at the intersection of user needs, business goals, and technical capabilities. But today, we stand at the edge of a new transformation—one where Agentic AI is no longer science fiction, but a foundational shift in how we build and scale digital products.
Recently, I completed a course on Agentic Artificial Intelligence: Harnessing AI Agents to Reinvent Business, Work, and Life, and it reshaped my perspective—not just on AI, but on product management itself.
🧠 What Is Agentic AI, Really?
Unlike traditional AI models that wait for a prompt and respond, Agentic AI is autonomous and action-oriented. It doesn’t just suggest—it acts. These agents can plan, decide, and execute multi-step processes without needing step-by-step instruction from humans.
Imagine a digital product that not only collects user data, but decides how to act on it, personalizes the experience in real-time, and even adjusts its own features based on business performance. That’s not futuristic. That’s agentic.
🧩 What This Means for Product Managers
As a Product Manager, I’ve always seen my role as the glue between tech, business, and user value. But with Agentic AI, we’re entering a world where even the glue starts to evolve. Here’s how:
1. PMs Will Become Architects of Intelligence, Not Just Features
Agentic systems require deep workflow mapping. PMs will need to design intelligent flows, not just user journeys. We'll move from backlog grooming to agent behavior design—asking: “How should this AI act in different business scenarios?”
2. Metrics Will Get Smarter—And So Should We
With agents executing tasks autonomously, PMs will need to shift from output metrics (Did we ship it?) to outcome metrics (Did the agent improve customer retention?). We’ll spend less time tracking velocity and more time guiding ethical and strategic decision-making.
3. Cross-Functional Collaboration Will Level Up
Engineers will train agents. Designers will create interfaces not just for users—but for agents, too. As PMs, our job will be to orchestrate human-agent collaboration. That requires empathy, foresight, and an even stronger grip on business goals.
4. Ethics and Governance Will Be Our New North Star
With greater autonomy comes greater risk. What happens when an AI agent decides to offer a discount beyond the margin? Or prioritize one segment over another based on biased data? PMs will need to define clear ethical boundaries and governance protocols—not just feature specs.
👀 Real-World Signals
We’re already seeing early signs. Shopify is experimenting with AI agents for customer service. Zapier is evolving its automation platform into intelligent agents that “watch and act.” These aren’t isolated tools anymore—they’re becoming co-workers in the product pipeline.
And this isn’t limited to tech giants. Startups are launching agent-as-a-service models where products are less about interfaces and more about outcomes.
💡 So, What Skills Should PMs Build Today?
Here’s what I’m focusing on personally, and what I believe future-ready PMs should start building now:
-
Workflow thinking: Beyond screens—map full journeys and handoffs between humans and AI.
-
Prompt engineering: Not just how to instruct AI, but how to guide intelligent behavior.
-
Business + Tech fluency: Understand data pipelines, LLMs, and their impact on cost and speed.
-
Ethical judgment: Be the voice that questions not just “Can we?” but “Should we?”
🚀 Final Thought
The age of Agentic AI doesn’t replace Product Managers—it redefines us. Our success will depend not on how well we manage a backlog, but on how well we build intelligent systems that are useful, trusted, and aligned with human values.
If you're entering or growing in product management like me, don’t wait for this shift to happen. Start designing with agents in mind—because soon, we won’t just manage products. We'll co-create with machines.
📝 Have thoughts on how AI is changing your work too? I’d love to hear how you see this future evolving.
#ProductManagement #AgenticAI #ArtificialIntelligence #FutureOfWork #PMCareer #DigitalProduct #TechLeadership
- Get link
- X
- Other Apps