Data & AI with Mukundan | Learn AI by Building

In this episode, Mukundan opens up about one of the most difficult phases of his job hunt and how he built a tiny 3-agent AI system that completely changed the way he applied, prepared, and stayed consistent. You will learn how the Researcher Agent, Writer Agent, and Reviewer Agent work together to turn any job description into clarity. You will also hear a raw, human story about self-doubt, burnout, and the psychology behind job search momentum. This is a deeply personal, practical episode for anyone who feels stuck, exhausted, confused, or overwhelmed in their job search.Optimized for: AI jobs, data jobs, job search tools, AI agents, career automation, productivity systems, job search burnout, how to find clarity in job search.

Join the Discussion (comments hub): https://mukundansankar.substack.com/notes

1. Tools I use for my Podcast and Affiliate Partners
   • Recording Partner: Riverside → Sign up here (affiliate)
   • Host Your Podcast: RSS.com (affiliate )
   • Research Tools: Sider.ai (affiliate)
   • Sourcetable AI: Join Here(affiliate)
2. 🔗 Connect with Me:
   • Free Email Newsletter
   • Website: Data & AI with Mukundan
   • GitHub: https://github.com/mukund14
   • Twitter/X: @sankarmukund475
   • LinkedIn: Mukundan Sankar
   • YouTube: Subscribe

I missed my parents, so I built an AI that talks like them. This isn’t about replacing people—it’s about remembering the voices that make us feel safe.

In this 90-minute episode of Data & AI with Mukundan, we explore what happens when technology stops chasing efficiency and starts chasing empathy. Mukundan shares the story behind “What Would Mom & Dad Say?”, a Streamlit + GPT-4 experiment that generates comforting messages in the voice of loved ones.

You’ll hear:

• The emotional spark that inspired the project
• The plain-English prompts anyone can use to teach AI empathy
• Boundaries & ethics of emotional AI
• How this project reframed loneliness, creativity, and connection

Takeaway: AI can’t love you—but it can remind you of the people who do.

🔗 Try the free reflection prompts below:

THE ONE-PROMPT VERSION: “What Would Mom & Dad Say?”

“You are speaking to me as one of my parents. Choose the tone I mention: either Mom (warm and reflective) or Dad (practical and encouraging). First, notice the emotion in what I tell you—fear, stress, guilt, joy, or confusion—and name it back to me so I feel heard. Then reply in 3 parts:

1. Start by validating what I’m feeling, in a caring way.
2. Share a short story, lesson, or perspective that fits the situation.

End with one hopeful or guiding question that helps me think forward. Keep your words gentle, honest, and simple. No technical language. Speak like someone who loves me and wants me to feel calm and capable again.”

Join the Discussion (comments hub): https://mukundansankar.substack.com/notes

1. Tools I use for my Podcast and Affiliate Partners
   • Recording Partner: Riverside → Sign up here (affiliate)
   • Host Your Podcast: RSS.com (affiliate )
   • Research Tools: Sider.ai (affiliate)
   • Sourcetable AI: Join Here(affiliate)
2. 🔗 Connect with Me:
   • Free Email Newsletter
   • Website: Data & AI with Mukundan
   • GitHub: https://github.com/mukund14
   • Twitter/X: @sankarmukund475
   • LinkedIn: Mukundan Sankar
   • YouTube: Subscribe

What if your job hunt could run like a data system?

In this episode, I share the story of how I used three AI agents — Researcher, Writer, and Reviewer — to rebuild my job search from the ground up. These agents read job descriptions, tailor resumes, and even critique tone and clarity — saving hours every week.

But this episode isn’t just about automation. It’s about agency. I’ll talk about rejection, burnout, and the mindset shift that changed everything: treating every rejection as a data point, not a defeat.

Whether you’re in tech, analytics, or just tired of the job search grind — this one’s for you.

🔹 Learn how I automated resume tailoring with GPT-4 🔹 Understand how to design AI systems that protect your mental energy 🔹 Discover why “efficiency” means doing less of what drains you 🔹 Hear the emotional story behind building these agents from scratch

• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• Tools I use for my Podcast and Affiliate Partners
  • Recording Partner: Riverside → Sign up here (affiliate)
  • Host Your Podcast: RSS.com (affiliate )
  • Research Tools: Sider.ai (affiliate)
  • Sourcetable AI: Join Here(affiliate)
• 🔗 Connect with Me:
  • Free Email Newsletter
  • Website: Data & AI with Mukundan
  • GitHub: https://github.com/mukund14
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe

What happens when an AI starts asking better questions than you?

In this 60-minute episode, I share the real story behind “The AI That Thinks Like an Analyst” — a Streamlit + GPT-4 project that changed the way I see data, curiosity, and creativity.

This isn’t a technical tutorial. It’s a journey into the mind of a data professional learning to think deeper — and how building this AI taught me the most human lesson of all: how to stay curious.

We’ll explore:

• Why the hardest part of analysis isn’t code — it’s curiosity.
• How I built a privacy-first Streamlit app that generates questions instead of answers.
• What AI can teach us about slowing down, observing, and thinking like explorers.
• The moment I realized data analysis and self-reflection are the same skill.

If you’ve ever felt stuck staring at your data, unsure what to ask next — this episode is for you.

📖 Read the full story: https://mukundansankar.substack.com/p/the-no-upload-ai-analyst-v4-secure

• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• Tools I use for my Podcast and Affiliate Partners
  • Recording Partner: Riverside → Sign up here (affiliate)
  • Host Your Podcast: RSS.com (affiliate )
  • Research Tools: Sider.ai (affiliate)
  • Sourcetable AI: Join Here(affiliate)
• 🔗 Connect with Me:
  • Free Email Newsletter
  • Website: Data & AI with Mukundan
  • GitHub: https://github.com/mukund14
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe

This week, I’m showing you exactly how I used AI agents to fix my job hunt — no hype, just results.

I was juggling dozens of job applications, interviews, and follow-ups until I built three small agents that acted like my personal job search team.

In this episode, I do a live demo of:

• A Researcher Agent that finds company insights automatically
• A Writer Agent that drafts personal outreach messages
• A Reviewer Agent that polishes tone and clarity

Together, they turned hours of chaos into minutes of clear progress.

You’ll see how these agents plan, collaborate, and improve your workflow — and how you can build your own version tonight using just ChatGPT or any LLM platform.

By the end, you’ll understand what makes agents powerful: planning, memory, and feedback.

🔗 Connect with Me:

• Free Email Newsletter
• Website: Data & AI with Mukundan
• GitHub: https://github.com/mukund14
• Twitter/X: @sankarmukund475
• LinkedIn: Mukundan Sankar
• YouTube: Subscribe

Data interviews do not have to feel messy. In this episode, I share a simple AI Interview Copilot that works for data analyst, data scientist, analytics engineer, product analyst, and marketing analyst roles.

What you will learn today:

• How to Turn a Job Post into a Skills Map: Know Exactly What to Study First.
• How to build role-specific SQL drills (joins, window functions, cohorts, retention, time series).
• How to practice product/case questions that end with a decision and a metric you can defend.
• How to prepare ML/experimentation basics (problem framing, features, success metrics, A/B test sanity checks).
• How to plan take-home assignments (scope, assumptions, readable notebook/report structure).
• How to create a 6-story STAR bank with real numbers and clear outcomes.
• How to follow a 7-day rhythm so you make steady progress without burnout.
• How to keep proof of progress so your confidence comes from evidence, not hope.

Copy-and-use prompts from the show:

• JD → Skills Map: “Parse this job post. Table: Skill/Theme | Where mentioned | My level (guess) | Study action | Likely interview questions. Then give 5 bullets: what they are really hiring for.”
• SQL Drill Factory (Analyst/Product/Marketing): “Create 20 SQL tasks + hint + how to check results using orders, users, events, campaigns. Emphasize joins, windows, conditional agg, cohorts, funnels, retention, time windows.”
• Case Coach (Data/Product): “Run a 15-minute case: key metric is down. Ask one question at a time. Score clarity, structure, metrics, trade-offs. End with gaps + practice list.”
• ML/Experimentation Basics (Data Science): “Create a 7-step outline for framing a modeling problem (goal, data, features, baseline, evaluation, risks, comms). Add an A/B test sanity checklist (power, SRM, population, metric guardrails).”
• Take-Home Planner: “Given this brief, propose scope, data assumptions, 3–5 analysis steps, visuals, and a short results section. Output a clear report outline.”
• Behavioral STAR Bank: “Draft 6 STAR stories (<120s) for conflict, ambiguity, failure, leadership without title, stakeholder influence, measurable impact. Put numbers in Results.”

If your “system” is 17 to‑do lists and three forgotten calendars, this episode is your reset. We build a Notion Life OS powered by three tiny AI agents that make daily planning stick:

• Capture Agent – Inbox anything in under 30 seconds, deduplicate, and route it to the right list.
• Prioritizer Agent – Convert chaos into a Today list using urgency × effort, hard time limits, and the rule of 3.
• Timebox Agent – Create a 3‑block schedule with buffers, calendar sync, and a 60‑second kickoff ritual. Plus: an Evening Reflection micro‑agent so you close the loop—wins, misses, one improvement. You’ll leave with prompts, templates, and guardrails you can copy tonight.

Primary keywords: AI agents, Notion planner, daily planning, timeboxing, productivity, routines, morning routine, evening reflection

Secondary keywords: capture to inbox, Eisenhower matrix, calendar sync, habit loops, task automation, micro‑automations

Links & Resources

• Recording Partner: Riverside → Sign up here (affiliate)
• Host Your Podcast: RSS.com (affiliate )
• Research Tools: Sider.ai (affiliate)
• Join the Newsletter: Free Email Newsletter to receive practical AI tools weekly.
• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• 🔗 Connect with Me:
  • Website: Data & AI with Mukundan
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe

If your job search feels like tab-hell—applications everywhere, prep scattered, follow-ups forgotten—this episode is your reset. I walk you through three small but mighty AI agents you can build in an afternoon:

• Application Tracker Agent — paste a job link → extract company, title, pay, location → auto-log to Notion/Sheets → set a 7-day follow-up. • Interview Prep Agent — feed the JD + your resume → get tailored behavioral questions, SQL/case drills, and a tight “Tell me about yourself.” • Follow-Up Agent — generate a thank-you in your voice, log the interview date, and nudge you if you haven’t heard back.

You’ll learn the agent essentials—planning, memory, feedback loops—plus a copy-and-paste framework, example prompts, and quality checks so your agents save time instead of making noise.

Chapters below. Show notes include my working templates, prompts, and affiliate tools I actually use (Riverside for recording, RSS.com for hosting, Sider for research). Rate the show if this helped—it means a lot.

Primary keywords: ai agents, job search, interview prep, application tracking, follow-up emails Secondary keywords: Notion, Google Sheets, SQL interview, behavioral questions, automation, productivity, podseo, career tools

Links & Resources

• Recording Partner: Riverside → Sign up here (affiliate)
• Host Your Podcast: RSS.com (affiliate )
• Research Tools: Sider.ai (affiliate)
• Join the Newsletter: Free Email Newsletter to receive practical AI tools weekly.
• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• 🔗 Connect with Me:
  • Website: Data & AI with Mukundan
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe

AI agents are everywhere in the headlines — but what do they really do? In this episode of Data & AI with Mukundan, we cut through the hype and explain, in plain language, how AI agents actually think.

You’ll learn the three key ingredients that separate real agents from chatbots:

• Planning: breaking big goals into concrete steps
• Memory: remembering context so actions feel consistent
• Feedback: adjusting when things go wrong instead of collapsing

I also walk through a live demo where an AI agent triages my Google Calendar and Gmail inbox. You’ll hear exactly how it proposes deep-work sessions, admin blocks, and even a workout — all while avoiding conflicts and asking for my approval before making changes.

To make this practical, I include a true/false quiz to test your instincts and a set of discussion prompts to help you imagine how agents could save you hours in real life.

By the end of this episode, you’ll know:

• How to tell the difference between a chatbot, automation, and a real AI agent
• Why most flashy demos online fail in practice
• How to build your first mini-agent with just one tool and a simple feedback loop
• Why agents only matter if they give you back time and focus

If you’ve ever wished for an assistant to handle your messy inbox, your cluttered schedule, or your repetitive tasks, this episode will show you how AI agents can actually do it. No buzzwords, no sci-fi — just practical, useful AI that you can build today.

Links & Resources

• Today's Demo: Here
• Quiz: Here
• Recording Partner: Riverside → Sign up here (affiliate)
• Host Your Podcast: RSS.com (affiliate )
• Research Tools: Sider.ai (affiliate)
• Join the Newsletter: Free Email Newsletter to receive practical AI tools weekly.
• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• 🔗 Connect with Me:
  • Website: Data & AI with Mukundan
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe

Plain-English agents, not hype: plan, use tools, add guardrails—then dry-run a calendar + inbox agent that saves hours.

You’ve heard “AI agent” everywhere, but definitions vary. In this episode, Mukundan explains—in plain, practical language—what a real agent is and when to use one. We’ll contrast agents with chatbots and simple automations, walk through the five pillars (goal, plan, tools, memory, feedback), and strip the tooling of buzzwords. Then we run a live dry-run: two 90-minute deep-work blocks, one 45-minute admin sweep, and a 30-minute workout that avoids your existing commitments. We finish by triaging sample emails into reply/delegate/archive/read-later and drafting five concise replies with one clear next step each. Safety first: drafts-only, tentative calendar holds, approval gates, and fallbacks if tools fail. Copy the templates from the show notes and ship your v0.5 tonight.

Lightning Round: True/False (answers in the episode)

1. An AI agent is just a chatbot.
2. Remove a tool and it still makes progress → probably a real agent.
3. Clear success criteria matter less than good prompts.
4. Chatbots reply; agents execute across steps.
5. Fixed automations are best when inputs rarely change.
6. If a tool disconnect breaks everything, it’s a brittle macro.

Links & Resources

• AI Agent Copy-Paste Templates (run these in ChatGPT): Get your free copy
• Recording Partner: Riverside → Sign up here (affiliate)
• Host Your Podcast: RSS.com (affiliate )
• Research Tools: Sider.ai (affiliate)
• Join the Newsletter: Free Email Newsletter to receive practical AI tools weekly.
• Join the Discussion (comments hub): https://mukundansankar.substack.com/notes
• 🔗 Connect with Me:
  • Website: Data & AI with Mukundan
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe