amrutha
@amruthagujjar.bsky.social
I <3 data | founder of structuredlabs.com | building an AI data engineer | yc | sf | #datasky
AI codegen feels magical, until you try to build on top of it. It’s not that the code is broken. It just doesn’t fit. The abstractions are off. The state is scattered. You end up rewriting it all. AI needs opinionated defaults.
Read more: www.preswald.com/blog/opensrc...
Read more: www.preswald.com/blog/opensrc...
Open source frameworks as a solution to ambiguity in AI code gen
A deep dive into how structured, opinionated frameworks reduce ambiguity in AI-generated code, and why open source plays an important role.
www.preswald.com
April 3, 2025 at 6:59 PM
AI codegen feels magical, until you try to build on top of it. It’s not that the code is broken. It just doesn’t fit. The abstractions are off. The state is scattered. You end up rewriting it all. AI needs opinionated defaults.
Read more: www.preswald.com/blog/opensrc...
Read more: www.preswald.com/blog/opensrc...
🚀Preswald OSS Launch Week Day 1: API data sources
Connect any REST API from config
→ response is parsed + loaded into DuckDB
→ query it like a database
Thanks to Lokesh Velayudha (github.com/lokeshvelayu...) for the contribution!
github.com/StructuredLa...
Connect any REST API from config
→ response is parsed + loaded into DuckDB
→ query it like a database
Thanks to Lokesh Velayudha (github.com/lokeshvelayu...) for the contribution!
github.com/StructuredLa...
March 24, 2025 at 5:36 AM
🚀Preswald OSS Launch Week Day 1: API data sources
Connect any REST API from config
→ response is parsed + loaded into DuckDB
→ query it like a database
Thanks to Lokesh Velayudha (github.com/lokeshvelayu...) for the contribution!
github.com/StructuredLa...
Connect any REST API from config
→ response is parsed + loaded into DuckDB
→ query it like a database
Thanks to Lokesh Velayudha (github.com/lokeshvelayu...) for the contribution!
github.com/StructuredLa...
March 17, 2025 at 2:31 AM
We put together a step-by-step guide on using Preswald to turn raw chatbot logs into an interactive debugging dashboard.
www.preswald.com/blog/ai-chat...
www.preswald.com/blog/ai-chat...
March 11, 2025 at 7:28 PM
We put together a step-by-step guide on using Preswald to turn raw chatbot logs into an interactive debugging dashboard.
www.preswald.com/blog/ai-chat...
www.preswald.com/blog/ai-chat...
Pyodide lets you run Python right in the browser. No installs, no setup, just open a link and go. It makes sharing and running data apps so much easier. Try it out with Preswald today: github.com/StructuredLa...
March 4, 2025 at 11:13 PM
Pyodide lets you run Python right in the browser. No installs, no setup, just open a link and go. It makes sharing and running data apps so much easier. Try it out with Preswald today: github.com/StructuredLa...
CSVs Are Not Databases
The challenges of local data exploration
open.substack.com
February 23, 2025 at 11:13 PM
@Structured teamed up with @MotherDuck to show how you can analyze massive public health datasets 4x faster and turn them into live, interactive data apps in just a few lines of Python, using our OSS framework Preswald.
Faster health data analysis with MotherDuck & Preswald - MotherDuck Blog
Faster health data analysis with MotherDuck & Preswald | Reading time: 6 min read
motherduck.com
February 14, 2025 at 6:18 PM
@Structured teamed up with @MotherDuck to show how you can analyze massive public health datasets 4x faster and turn them into live, interactive data apps in just a few lines of Python, using our OSS framework Preswald.
Reason I don’t believe in the Mon-Fri, 9-5 life: I’ll often have bursts of inspiration/creativity that sometimes last 4-5 days, where I can’t sleep, can’t eat. I have to build. Then, ofc I’ll crash for 24 hrs after.
February 12, 2025 at 4:23 AM
Reason I don’t believe in the Mon-Fri, 9-5 life: I’ll often have bursts of inspiration/creativity that sometimes last 4-5 days, where I can’t sleep, can’t eat. I have to build. Then, ofc I’ll crash for 24 hrs after.
B2A: The future of analytics isn’t human
For the agents. By the agents.
Read more: blog.structuredlabs.com/p/b2a-the-fu...
For the agents. By the agents.
Read more: blog.structuredlabs.com/p/b2a-the-fu...
February 10, 2025 at 10:04 PM
B2A: The future of analytics isn’t human
For the agents. By the agents.
Read more: blog.structuredlabs.com/p/b2a-the-fu...
For the agents. By the agents.
Read more: blog.structuredlabs.com/p/b2a-the-fu...
We’re used to thinking of software as something permanent: bought, maintained, and scaled. But what if it didn’t have to be? The cost of writing code has plummeted, making it easier than ever to build ephemeral software
open.substack.com/pub/structur...
open.substack.com/pub/structur...
The rise of DIY software (and why developer tools matter more than ever)
Personal. Local. Ephemeral.
open.substack.com
February 3, 2025 at 1:14 AM
We’re used to thinking of software as something permanent: bought, maintained, and scaled. But what if it didn’t have to be? The cost of writing code has plummeted, making it easier than ever to build ephemeral software
open.substack.com/pub/structur...
open.substack.com/pub/structur...
Enjoying a no-meeting Sunday to build. Lots of exciting stuff shipping soon :D
February 2, 2025 at 11:56 PM
Enjoying a no-meeting Sunday to build. Lots of exciting stuff shipping soon :D
Debugging AI voice agents is way easier when you have the right dashboards. With DuckDB & Structured, you can pull logs locally, run instant SQL queries, and turn messy data into clear, interactive dashboards.
blog.structuredlabs.com/p/debugging-...
blog.structuredlabs.com/p/debugging-...
January 30, 2025 at 8:12 PM
Debugging AI voice agents is way easier when you have the right dashboards. With DuckDB & Structured, you can pull logs locally, run instant SQL queries, and turn messy data into clear, interactive dashboards.
blog.structuredlabs.com/p/debugging-...
blog.structuredlabs.com/p/debugging-...
We present a comparative evaluation of two state-of-the-art language models, DeepSeek-R1 and OpenAI-GPT, focusing on their generative performance in a specialized domain: knock-knock joke creation. While traditional benchmarks evaluate language models on metrics such as perplexity or BLEU scores
January 28, 2025 at 10:09 AM
We present a comparative evaluation of two state-of-the-art language models, DeepSeek-R1 and OpenAI-GPT, focusing on their generative performance in a specialized domain: knock-knock joke creation. While traditional benchmarks evaluate language models on metrics such as perplexity or BLEU scores
Excited to speak at the AITinkerers San Francisco meetup on Jan 29! I'll be showing how to set up lightweight local analytics dashboards w/ Python. Don't miss it!
sf.aitinkerers.org/p/ai-tinkere...
sf.aitinkerers.org/p/ai-tinkere...
AI Tinkerers - San Francisco - January 2025 Meetup [AI Tinkerers - San Francisco]
AI Tinkerers SF is back on January 29th, 2025! Get ready for another exciting gathering of active builders. Join us for the AI Tinkerers San Francisco January Meetup, generously sponsored and hosted b...
sf.aitinkerers.org
January 26, 2025 at 9:58 AM
Excited to speak at the AITinkerers San Francisco meetup on Jan 29! I'll be showing how to set up lightweight local analytics dashboards w/ Python. Don't miss it!
sf.aitinkerers.org/p/ai-tinkere...
sf.aitinkerers.org/p/ai-tinkere...
Structured blog is now officially live: blog.structuredlabs.com
We’re sharing technical deep dives, real-world challenges, and how we’re building Structured to solve complex AI and analytics problems.
If that’s your thing, check it out and subscribe today. 👉
We’re sharing technical deep dives, real-world challenges, and how we’re building Structured to solve complex AI and analytics problems.
If that’s your thing, check it out and subscribe today. 👉
January 26, 2025 at 12:41 AM
Structured blog is now officially live: blog.structuredlabs.com
We’re sharing technical deep dives, real-world challenges, and how we’re building Structured to solve complex AI and analytics problems.
If that’s your thing, check it out and subscribe today. 👉
We’re sharing technical deep dives, real-world challenges, and how we’re building Structured to solve complex AI and analytics problems.
If that’s your thing, check it out and subscribe today. 👉
We recently explored Ibis, a Python library designed to simplify working with data across multiple storage systems and processing engines. Wrote up some learnings here: open.substack.com/pub/structur...
A technical intro to Ibis: The portable Python DataFrame library
How Ibis simplifies analytics across multi-backend systems with a unified Python API
open.substack.com
January 25, 2025 at 11:58 PM
We recently explored Ibis, a Python library designed to simplify working with data across multiple storage systems and processing engines. Wrote up some learnings here: open.substack.com/pub/structur...
In 2022, “chat-with-your-data” tools felt like magic. Type a question, get a SQL query, and watch insights flow. But now it’s 2025, and we know better: SQL generation is the easiest part of analytics.
open.substack.com/pub/structur...
open.substack.com/pub/structur...
LLMs for Analytics is more than ‘text2sql’
Sure that chat-with-your-data app was cute in 2022. But the real breakthroughs in analytics are still ahead.
open.substack.com
January 10, 2025 at 8:51 AM
In 2022, “chat-with-your-data” tools felt like magic. Type a question, get a SQL query, and watch insights flow. But now it’s 2025, and we know better: SQL generation is the easiest part of analytics.
open.substack.com/pub/structur...
open.substack.com/pub/structur...
In 2025, analytics will no longer be an isolated function. It will be the operating system of the modern org, powering decisions, automating processes, predicting the future. Treat analytics as a product asset. Scalable, modular, actionable - not a passive reporting tool
January 8, 2025 at 9:52 AM
In 2025, analytics will no longer be an isolated function. It will be the operating system of the modern org, powering decisions, automating processes, predicting the future. Treat analytics as a product asset. Scalable, modular, actionable - not a passive reporting tool
Launches always require a tremendous amount of effort, and this one is no exception. We've poured so much heart into everything we've built and shared with the world. This launch has gotten overwhelming love from our users- a good reminder of why we do what we do. github.com/StructuredLa...
January 8, 2025 at 12:52 AM
Launches always require a tremendous amount of effort, and this one is no exception. We've poured so much heart into everything we've built and shared with the world. This launch has gotten overwhelming love from our users- a good reminder of why we do what we do. github.com/StructuredLa...
Analytics success depends on asking the right questions upfront. Many projects fail because they start with vague goals like “We need a dashboard” without understanding the problem they’re solving.
open.substack.com/pub/structur...
open.substack.com/pub/structur...
Why good analytics starts with better questions
No one-size-fits-all analytics, thanks
open.substack.com
January 3, 2025 at 12:49 AM
Analytics success depends on asking the right questions upfront. Many projects fail because they start with vague goals like “We need a dashboard” without understanding the problem they’re solving.
open.substack.com/pub/structur...
open.substack.com/pub/structur...
We just released an open source SDK for Preswald. Preswald is a lightweight Python framework that makes it easy to build, visualize, and deploy data apps—all in one place.
⭐ Star the repo and let us know what you think!
github.com/StructuredLa...
⭐ Star the repo and let us know what you think!
github.com/StructuredLa...
GitHub - StructuredLabs/preswald: AI data app builder
AI data app builder. Contribute to StructuredLabs/preswald development by creating an account on GitHub.
github.com
December 31, 2024 at 8:19 PM
We just released an open source SDK for Preswald. Preswald is a lightweight Python framework that makes it easy to build, visualize, and deploy data apps—all in one place.
⭐ Star the repo and let us know what you think!
github.com/StructuredLa...
⭐ Star the repo and let us know what you think!
github.com/StructuredLa...
Designing SDKs for AI Agents vs Humans open.substack.com/pub/structur...
Designing SDKs for AI Agents vs Humans
How designing developer facing interfaces changes when the consumers are AI agents
open.substack.com
December 28, 2024 at 11:06 PM
Designing SDKs for AI Agents vs Humans open.substack.com/pub/structur...
TensorFlow organizes computations as a DAG: nodes represent operations, and edges define their dependencies. This structure enforces order, ensures reproducibility, and provides transparency. shorturl.at/f42JQ
Applying computational graph principles to notebooks 📓
Bringing order to the chaos of notebooks with DAG thinking
open.substack.com
December 21, 2024 at 10:18 AM
TensorFlow organizes computations as a DAG: nodes represent operations, and edges define their dependencies. This structure enforces order, ensures reproducibility, and provides transparency. shorturl.at/f42JQ
December 20, 2024 at 7:24 AM
What if building data apps was as easy as snapping a photo on an iphone? Once expensive and rare, apps would become abundant and instinctive. Personal/hyper-local dashboards, or event-specific tools built at the speed of thought. When cost & effort drop 100x, everything changes. shorturl.at/EUsB2
If Data Apps Were 10x or 100x Easier to Build, What Would Get Built?
If you could build data apps at the speed of thought—what would happen?
shorturl.at
December 13, 2024 at 12:55 AM
What if building data apps was as easy as snapping a photo on an iphone? Once expensive and rare, apps would become abundant and instinctive. Personal/hyper-local dashboards, or event-specific tools built at the speed of thought. When cost & effort drop 100x, everything changes. shorturl.at/EUsB2