Can AI drop a summer banger, or is it better off sticking to data pipelines?

In this episode of Data Party, we pivot from serious architecture talks to put Google Flow Music to the ultimate test. Watch as we attempt to create a SAAS tool into a summer banger!

While AI can produce impressive one-shot generations, fine-tuning and editing tell a completely different story. Join the breakdown of:

• One-Shot Magic vs. Editing Reality: Why AI models excel at generating initial concepts but struggle with iterative tweaks.

• The Regeneration Dilemma: Why tools like Google Flow Music insist on re-creating whole tracks instead of editing specific sequences.

• Broader AI Limitations: How these music editing friction points parallel common LLM pitfalls in slide creation, graphic rendering, and code generation.

• Product Opportunities: Where the massive white space lies for developers to build smarter, sequence-aware AI editing tools.

Whether you're building AI products or just curious if an algorithm can handle the mixing console, tune in for a fun, real-world reality check on the limits—and future—of generative creative tools!

Welcome back to Season 2 of Data Party! 🥳

As a small business owner, preparing taxes is one of those tedious, time-consuming tasks that nobody looks forward to. Too many forms, too much sorting, and way too much manual work.

In this season premiere, we’re fixing that by building an autonomous Tax Agent designed to handle the heavy lifting!

In this episode, we cover:

• The 2-Flow Architecture: Setting up quarterly checks and sweep confirmations.

• Connecting External Services: How we integrated Plaid to fetch financial transactions smoothly.

• File Tree & Claude MD: Structuring project files and instructions for clean execution.

• Real-World Demo: Watching the agent categorize expenses, update from human feedback in real-time, and calculate tax estimates.

• Iteration & Prompt Evals: Honest lessons learned from building and debugging AI agents.

🐙 Grab the Code:

Want to set this up for your own workflow? Grab our open-source GitHub repository here:

https://github.com/Happychick

⚠️ Disclaimer: This podcast is for educational and building purposes only. We do not provide financial or tax advice—always consult a certified CPA for official filings!

Data Party: Season 2: A New Hope 🚀Ok, ok ok. It's been a while, and I have not being posting consistnFor the last two years, we've talked about data trends and industry movements. But the world has changed. Thanks to large language models and advanced evaluation tools, data professionals don't need to just provide insights and try to "influence" stakeholders anymore. We have the power to build end-to-end products ourselves.This season is all about moving from spectators to builders. No more endless frustrations—just pure execution.What to Expect This Season:Building E2E: How to take your data skills and turn them into functional AI products.Mastering LLMs: Practical approaches to leveraging language models in production.Rigorous Evaluation: Building the guardrails and evaluation metrics that make AI products actually work.Hit subscribe, get ready to build, and let’s get this party started. 💻✨New episodes drop every week!

Remember that article from 2012? That one that talked about the "hottest" job of the century. If you can't remember, allegedly it was data science!

But how much has changed since then? Is data science still a career worth pursuing? How does it compare to data engineering or ML engineering, or the many other data roles that have sprouted in it's place?

Join me with Timothy Chan, head of data at StatSig, for the first ever... LIVE DATA PARTY!

I don’t know if you’ve heard, but there is this cool, new thing out there called…AI, and, it’s changing everything! But one big, extremely important, question remains unanswered: how will it transform data work? (of course because this is a data podcast, data is ALL that matters!)

Many data startups have keyed in on using AI to generating insights. There is only one problem, insights based on bad data are just… bad insights.

What if AI could revolutionize not just analytics, but the way we get clean, reliable data in the first place? Today, I’m talking with Shinji Kim, founder of Select Star, about her bold bet on AI and the future of data quality.

Credit to @freesound_community for the sound effects!

I recently read an article that talked about the first ⁠10 hires⁠ in various startups. None were data people. More interestingly, of the 19 companies interviewed, more than 30% were data companies, yet even among these, only 50% of those companies recruited a data person. In today's podcast, I'm incredibly excited to be speaking with Kevin Hu, CEO of Metaplane, a data startup that (I believe) has data people on the team, to understand why exactly don't startups hire data teams?

Music by ⁠Ievgen Poltavskyi⁠ from ⁠Pixabay

Considering a move into data management?

Transitioning to management can be annoying. You are the best IC in town, and now, suddenly, you have to replicate yourself in your team without doing the work yourself. Or is that even true? Join me and Mengying Li, an impressive data leader that has made the switch 2x, offering the highlights of her experience in data management at Meta and Notion.

Curious to hear more of Mengying's thoughts? Subscribe to her substack here

Music by Christoph Scholl from Pixabay

“Can you just put this into a stacked bar chart?” A question data analysts hear millions of times. Low and behold, once our 5 category chart is built, everyone marvels at it beauty but wait, there is 1 problem, what on earth is it telling us?

Join us as Weronika Gawarska, a known voice in the Tableau community shares her views on some of the best and worst data visualizations she has encountered and gives invaluable insights on creating impactful data visualizations that truly tell a story.

Music by Vincent from Pixabay" target="_blank" rel="noopener noreferer">Vincent from pixabay

Napoleon's Invasion of Russia, for those that want to see the disaster in action