Page de couverture de Data & AI with Mukundan | Learn AI by Building

Data & AI with Mukundan | Learn AI by Building

Data & AI with Mukundan | Learn AI by Building

Auteur(s): Mukundan Sankar – Practical AI & Analytics
Écouter gratuitement

À propos de cet audio

Practical, human-first AI. Each week we build small, useful AI tools and workflows—so you can apply them the same day you listen.

Data & AI with Mukundan is where real-world problems meet practical AI. You don’t learn AI by collecting tabs—you learn it by shipping small, useful things. I’m Mukundan, an analytics pro, GPT builder, and lifelong learner. Every week we take one problem and build a solution you can actually use: smarter job-search helpers, portfolio reviewers, AI that speeds up analysis, slide/summary assistants, and more.

You’ll hear the decisions behind each build—what to automate, how to evaluate quality, how to keep outputs reliable, and how to make it useful today. We keep the language plain, the examples concrete, and the steps realistic whether you’re hands-on or just AI-curious.

Recurring themes: LLM applications, prompt design, evaluation, retrieval patterns, analytics workflows, career use-cases, and product thinking for AI. New episodes weekly. Subscribe for the how-to; stay for the shipped thing.

🔗 Connect with Me:

  • Free Email Newsletter
  • Website: Data & AI with Mukundan
  • GitHub: https://github.com/mukund14
  • Twitter/X: @sankarmukund475
  • LinkedIn: Mukundan Sankar
  • YouTube: Subscribe
Mukundan Sankar
Économie
Épisodes
  • Tiny AI Prompts for Big Productivity: Mastering the 80‑20 Rule with Practical AI
    Sep 9 2025

    Discover how small AI prompts can transform your productivity. In this episode, Mukundan explains the 80‑20 rule. Mukundan demonstrates AI workflows for scheduling and focus, and introduces a Prompt Wallet to help you beat decision fatigue. Perfect for anyone seeking practical AI and better time management.

    Episode Highlights

    1. 80‑20 Rule Explained: Most of your progress comes from a few critical actions. Learn how to identify them with prompts.
    2. Prompt Structure 101: Context, constraints, desired outcome, and a tiny first step.
    3. Classic Prompts: 10‑minute workouts, zero‑based budgeting, Pomodoro study plans, teach‑back outlines, and Power Clean 15.
    4. New Productivity Hacks: Time blocking, task prioritization, interrupt handling, focus sprints, and daily review.
    5. Live Demo: Mukund feeds tasks into the AI and shows how it schedules a day, orders tasks by impact, manages interruptions, and sets up a focus sprint.
    6. Seven‑Day Challenge: Try one prompt per day and track whether you start within 60 seconds. Join the conversation with #PromptWalletChallenge.

    Takeaways & Actions

    • Start with your context and constraints. Ask for a plan and a micro‑action.
    • Most results come from a handful of well‑chosen tasks. Use prompts to find them.
    • Commit to the seven‑day challenge. Sign up for the free newsletter and email Mukundan your progress.
    • Download the free Prompt Wallet PDF to keep all the scripts handy.
    • Support the show by subscribing and leaving a review; tell your friends if you found value.

    Links & Resources

    • Prompt Wallet PDF: 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
    Voir plus Voir moins
    27 min
  • The No-Upload AI Analyst: Hash, Mask, Redact—AI Analytics Without CSV File Uploads
    Sep 2 2025

    AI, data, numbers—without uploads. Hash, mask, and redact PII, then run data analytics locally for time-saving and privacy.

    In this episode, we build a No-Upload AI Analyst that keeps your PII safe: HMAC SHA-256 hashing, masking, and redaction using policy presets and client-side transforms. We’ll: • Reframe the problem (insights > risk) • Set four hard constraints (no uploads, local preferred, policy presets, human-readable audit) • Use rules-first privacy + schema semantics • Walk the 5-step workflow (paste headers → pick preset → set secret → transform → analyze) • Show real-world cases (HIPAA/HITECH-aware analytics, FERPA contexts, product analytics) • Share a checklist + quiz + local Streamlit approach Perfect for data teams in healthcare, finance, education, and privacy-sensitive orgs.

    Key takeaways

    • Stop uploading customer data. Transform it client-side first.
    • Use HMAC hashing to keep joins without exposing raw emails/IDs.
    • Mask for human-readable UI; redact when you don’t need the field.
    • Ship a data-handling report with every analysis.
    • Run the app locally for maximum privacy.

    Affiliate note: I record with Riverside (affiliate) and host on RSS.com (affiliate). Links in show notes.

    Links

    • Blog version: (Free): 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

    Voir plus Voir moins
    27 min
  • AI Meal Planner — What to Cook Tonight with What You Have
    Aug 26 2025

    AI, data, and analytics pick three cookable dinners from the ingredients and appliances you already have—no grocery run.

    We use AI, data, and a rules-first analytics score to rank real meals you can make tonight with what’s in your pantry. A lightweight rules engine avoids AI hallucinations; Chef-AI adds safe swaps and one-line directions. You’ll learn a copy-paste AI prompt, how to reduce waste, and how analytics rank time, fit, and vibe.

    3 bullets (skimmable):

    • Rules > raw AI for reliable, cookable results
    • Analytics score to rank fastest/best-fit meals
    • Copy-paste prompt for 3 ideas in under a minute

    You’ll learn

    • Why a rules engine beats raw AI for reliable, cookable recipes
    • How an analytics score prioritizes the best matches fast
    • A copy-paste AI prompt that returns 3 make-tonight ideas in under a minute
    • How to reduce waste and keep weeknight meals simple & tasty

    Try this prompt: I have [3–5 ingredients] and these appliances: [list]. Suggest 3 meals I can make in under 30 minutes. If something’s missing, suggest simple pantry substitutions. Keep it realistic and give one-line directions for each.

    Quick quiz True or False — If you only rely on AI, it may assume tools you don’t have and suggest impossible recipes. Answer: True. Start with rules; use AI for riffs and swaps.

    Discussion question When you’re deciding on dinner, do you want structure (reliable classics) or creativity (something new)? Reply on Substack or X—I'll share the poll next week.

    Resources & links

    • Blog Link: https://mukundansankar.substack.com/p/pantry-plate-the-aifirst-way-to-decide

    Key takeaways

    • Put rules before AI for cookable results.
    • One clear AI prompt can end dinner indecision in minutes.
    • AI is a partner, not the chef.

    Affiliate partners (links below):

    • RSS: your podcast, get free transcripts, and earn ad revenue with as few as 10 monthly downloads. Sign up here.
    • Sider AI. AI-powered research and productivity assistant for breaking down job descriptions into keywords. Try Sider here.
    • Riverside FM: Record your podcast in studio-quality audio and 4K video from anywhere. Get started with Riverside here.

    Affiliate disclosure: Some links may be affiliates. If you use them, I may earn at no extra cost to you.

    Answer: True.

    Keywords: ai, ai meal planner, data, data analytics, analytics, time-saving tools, pantry, dinner ideas, recipe generator, meal planning

    Voir plus Voir moins
    23 min
Pas encore de commentaire