Join the Databricks and Mayfield team for a dinner on Wednesday, March 18 in San Jose โ a night designed exclusively for startup leaders and executives who are shaping the future of data & AI. ๐
โโWeโre bringing together the boldest minds in the AI startup ecosystem for an intimate dinner where youโll have the chance to network, share best practices, and learn how others are using Databricks.
Seats are limited. Donโt miss this opportunity to join one of the most vibrant founder communities around GTC!
๐ Secure your spot at the table here: events.databricks.com/FY27Q1โฆ
#Databricks #Founders #Startups #DatabricksForStartups
1
83
Calling all LA food-tech builders & operators! ๐ด
Weโre excited to partner with Topi for "Topi Topics Live." Itโs a day for restaurant operators, founders, and the AI-curious to get into the weeds of how tech is changing culture.
Whatโs happening:
๐ป ๐ฉ๐ถ๐ฏ๐ฒ ๐๐ผ๐ฑ๐ถ๐ป๐ด: Prototype tools live with Databricksโno coding skills needed.
โก ๐๐ถ๐ด๐ต๐๐ป๐ถ๐ป๐ด ๐ง๐ฎ๐น๐ธ๐: Fast-paced, high-signal PechaKucha-style insights (20 slides ร 20 seconds).
๐ค ๐๐ผ๐ป๐ป๐ฒ๐ฐ๐๐ถ๐ผ๐ป๐: Real talk and real time to build community.
๐๏ธ Monday, March 2nd
๐ Los Angeles, CA
๐ RSVP: luma.com/uhacglc9?tk=hqF9Tt
Food and drinks will be served throughout, but space is limited. Hope to see you there! ๐
#Databricks #FoodTech #Hospitality #Startups #DatabricksForStartups
46
๐ฃ Join the @databricks VC-Backed Startups team and SignalFire on Thursday, March 12 in downtown NYC!
Weโre hosting an intimate dinner designed specifically for the founders and execs who are actually shaping the future of data & AI. ๐ Network, share best practices, and learn what others are who are using data to build whatโs next.
โโSeats are limited โ and this community moves fast. Donโt miss this opportunity to join one of the most vibrant founder communities in NYC. ๐๏ธ
Register here ๐ luma.com/nyc-startupdinner31โฆ
#Databricks #SignalFire #NYCStartups #DatabricksForStartups
Weโre proud to be a Founding Host of Bostonโs first-ever Tech Week! ๐
Databricks for Startups is joining 75+ innovative companies to bring a massive week of programming to Boston from ๐๏ธ May 26 โ May 31.
Want to host an event alongside top companies and leaders shaping the future of tech? Event submissions are open now at ๐ tech-week.com/host
#Databricks #DatabricksForStartups #BOSTechWeek @Techweek_
32
We were thrilled to be part of the 4th Global AI Hackathon, the world's premier AI innovation challenge! ๐ It was a privilege to watch brilliant minds converge to build the future of AI in just one weekend.
Judging at Stanford and MIT, our team was blown away by the creativity, the technical depth of the projects, and the incredible geographical diversity of the participants. ๐
Congratulations to every team that participated! The speed and innovation we saw in just 24 hours prove that the next generation of AI startups is already building the future. ๐
#Databricks #Stanford #MIT #GlobalAIHackathon #AIInnovation #Startups #DatabricksForStartups #Hackathon
43
Join the @databricks VC-Backed Startups team and @jpmorgan for an intimate dinner on ๐ง๐ต๐๐ฟ๐๐ฑ๐ฎ๐, ๐๐ฒ๐ฏ๐ฟ๐๐ฎ๐ฟ๐ ๐ญ๐ต, in central Manhattan, NYC. ๐๏ธ
Weโre bringing together the boldest minds in NYCโs startup ecosystem. ๐ Expect honest conversation, shared war stories, and perspectives from an array of industries and backgrounds.
Who's this for?
โ๐น ๐ฉ๐ถ๐๐ถ๐ผ๐ป๐ฎ๐ฟ๐ถ๐ฒ๐: Early-stage startup founders at the cusp of innovation
โ๐น ๐๐๐ถ๐น๐ฑ๐ฒ๐ฟ๐: Technical leaders in fast-scaling companies
๐น โ๐ฆ๐ฒ๐ฎ๐๐ผ๐ป๐ฒ๐ฑ ๐ฃ๐ฟ๐ผ๐ณ๐ฒ๐๐๐ถ๐ผ๐ป๐ฎ๐น๐: Entrepreneurs passionate and involved in NYC's data, AI, and open source tech scene
โโSeats are limited โ and this community moves fast. Donโt miss this opportunity to join one of the most vibrant founder communities in NYC. ๐
๐ Register: luma.com/nyc-startupdinner21โฆ
#databricksforstartups #startups #databricks #nyc
41
๐จ New Blog: ๐๐ถ๐ฑ๐ฑ๐ฒ๐ป ๐ง๐ฒ๐ฐ๐ต๐ป๐ถ๐ฐ๐ฎ๐น ๐๐ฒ๐ฏ๐ ๐ผ๐ณ ๐๐ฒ๐ป๐๐ ๐ฆ๐๐๐๐ฒ๐บ๐
Classical ML and GenAI are different flavors of the same domain. While you may be used to spending weeks on data cleaning, GenAI flips the script, shifting effort toward subjective evaluation and stakeholder management.
In this blog, youโll learn:
๐ย ๐๐ฒ๐๐ฒ๐น๐ผ๐ฝ๐บ๐ฒ๐ป๐ ๐๐น๐ถ๐ฝ: Why GenAI development time is dominated by evaluation and gathering human-in-the-loop feedback
โ ๏ธย ๐ฑ ๐๐ถ๐ฑ๐ฑ๐ฒ๐ป ๐๐ฒ๐ฏ๐๐: Dive deep into Tool Sprawl, Prompt Stuffing, and Opaque Pipelinesโplus the risks of inadequate feedback loops and stakeholder silos
โ
ย ๐ช๐ถ๐ป๐ป๐ถ๐ป๐ด ๐ฆ๐๐ฟ๐ฎ๐๐ฒ๐ด๐ถ๐ฒ๐: Why clear communication and robust monitoring remain the only ways to build clean, maintainable systems
๐ Dive in: databricks.com/blog/hidden-tโฆ
#Databricks #Startups #GenAI #LLMOps
18
As AI-native products transition from pilots to mission-critical workflows, the competitive advantage is shifting towards data and AI workflow architecture.
Join us for an evening of networking and discussion, co-hosted with G2C Ventures, for GenAI founders and senior product, data, and engineering leaders to go deeper on how modern data lakes enable scalable, cost-efficient, and defensible Data + AI strategies. ๐ก
๐๏ธ When:ย Thursday, January 15th at 5:00 PM
๐ฅ Who:ย GenAI Native founders, Directors/VPs at <$200M ARR ISVs
๐ Where:ย Palo Alto, CA
Why attend?
๐น Learn how leading teams are structuring their data foundations for GenAI=
๐น Pressure-test your Data + AI roadmap with peers at a similar stage
๐น Exchange ideas on whatโs working and whatโs not
๐น Build relationships with founders and executives solving adjacent problems
๐ REGISTER: luma.com/kcmmmf7j
#genai #databricks #databricksforstartups #datalakes
24
๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐ณ๐ผ๐ฟ ๐ฆ๐๐ฎ๐ฟ๐๐๐ฝ๐ ๐ค๐ฐ, ๐ฎ๐ฌ๐ฎ๐ฑ ๐ฅ๐ฒ๐๐ถ๐ฒ๐ ๐
Our latest quarterly recap covers the launch of the Databricks AI Accelerator, our founder dinner series, and more.
See what weโve been up to! โก๏ธ linkedin.com/pulse/databrickโฆ
#databricks #databricksforstartups #founders #startups
56
๐ฆ๐ฎ๐ป๐๐ฎ ๐ฑ๐ผ๐ฒ๐๐ป'๐ ๐ฐ๐ต๐ฒ๐ฐ๐ธ ๐๐ต๐ฒ ๐น๐ถ๐๐ ๐๐๐ถ๐ฐ๐ฒ ๐ฎ๐ป๐๐บ๐ผ๐ฟ๐ฒ. ๐๐ฒ ๐ฐ๐ต๐ฒ๐ฐ๐ธ๐ ๐ฎ ๐ฑ๐ฎ๐๐ต๐ฏ๐ผ๐ฎ๐ฟ๐ฑ. ๐
We have reached the finish line! Itโsย ๐๐ฎ๐ ๐ญ๐ฎ of the ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐, and we are replacing manual checks with real-time visibility at the North Pole.
Over the last 11 days, we ingested streaming data, built vector indexes, deployed AI agents, managed Postgres instances, and more. But the North Pole leadership team doesn't look at raw tables or Python notebooks. They look atย ๐๐ฎ๐๐ต๐ฏ๐ผ๐ฎ๐ฟ๐ฑ๐.
Usually, this is where you move dataย outย of your platform into a third-party BI tool, rebuilding logic with complex semantic models and losing governance along the way.
๐ง๐ผ๐ฑ๐ฎ๐, ๐๐ฒ ๐๐ถ๐๐๐ฎ๐น๐ถ๐๐ฒ๐ฑ ๐ฒ๐๐ฒ๐ฟ๐๐๐ต๐ถ๐ป๐ด ๐ฟ๐ถ๐ด๐ต๐ ๐๐ต๐ฒ๐ฟ๐ฒ ๐ถ๐ ๐น๐ถ๐๐ฒ๐. Using ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐๐/๐๐ ๐๐ฎ๐๐ต๐ฏ๐ผ๐ฎ๐ฟ๐ฑs, we build a view into operations for North Pole leadership.
๐ช๐ต๐ ๐๐ต๐ถ๐ ๐ถ๐ ๐๐ต๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ฒ๐ฐ๐ ๐ฒ๐ป๐ฑ ๐๐ผ ๐๐ต๐ฒ ๐๐๐ฎ๐ฐ๐ธ:
๐น ๐๐๐๐ ๐ฆ๐ค๐:ย No complex semantic modeling layers. If you can query it, you can graph it.
๐น ๐๐๐ถ๐น๐-๐ถ๐ป ๐๐:ย We used the AI_FORECAST function to predict toy production trends directly on the chart.
๐น ๐๐ผ๐๐ฒ๐ฟ๐ป๐ฒ๐ฑ:ย We didn't have to recreate security rules. The dashboard respects the exact same Unity Catalog permissions as the rest of the Lakehouse.
๐ง๐ต๐ฒ ๐๐ฎ๐ธ๐ฒ๐ต๐ผ๐๐๐ฒ ๐ถ๐ ๐ฐ๐ผ๐บ๐ฝ๐น๐ฒ๐๐ฒ.ย From raw letters to AI agents to executive dashboards: one platform, one governance model, zero silos. Oh, and all of this is ready to consume through the newย ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐ข๐ป๐ฒย business-facing hub of the platform (more in the article).
Thank you for following along with the North Pole Modernization Office!
๐๏ธ Start Day 12:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Databricks #DataVisualization #BI #AI #Lakehouse #DataEngineering #DatabricksOne
14
๐ช๐ฒ ๐ฏ๐๐ถ๐น๐ ๐ฎ ๐๐ผ๐บ๐บ๐ฎ๐ป๐ฑ ๐๐ฒ๐ป๐๐ฒ๐ฟ ๐ฎ๐ฝ๐ฝ ๐ณ๐ผ๐ฟ ๐๐ต๐ฒ ๐ก๐ผ๐ฟ๐๐ต ๐ฃ๐ผ๐น๐ฒ ๐๐ถ๐๐ต๐ผ๐๐ ๐๐ฟ๐ถ๐๐ถ๐ป๐ด ๐ฎ ๐๐ถ๐ป๐ด๐น๐ฒ ๐๐ผ๐ฐ๐ธ๐ฒ๐ฟ๐ณ๐ถ๐น๐ฒ ๐ผ๐ฟ ๐บ๐ฎ๐ป๐ฎ๐ด๐ถ๐ป๐ด ๐ฎ๐ป๐ ๐ถ๐ป๐ณ๐ฟ๐ฎ๐๐๐ฟ๐๐ฐ๐๐๐ฟ๐ฒ.
Itโsย ๐๐ฎ๐ ๐ญ๐ญย of theย ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐. ๐
Data pipelines are great, but the Elves can't use a SQL notebook to mark a package as "Delivered." They need buttons. They need maps. Usually, building this means spinning up external infrastructure and wrestling with authentication.
๐ง๐ผ๐ฑ๐ฎ๐, ๐๐ฒ ๐ฏ๐๐ถ๐น๐ฑ ๐ฎ๐ป๐ฑ ๐ฑ๐ฒ๐ฝ๐น๐ผ๐ ๐๐ต๐ฒ "๐ก๐ผ๐ฟ๐๐ต ๐ฃ๐ผ๐น๐ฒ ๐๐ผ๐บ๐บ๐ฎ๐ป๐ฑ ๐๐ฒ๐ป๐๐ฒ๐ฟ" ๐ฎ๐ฝ๐ฝ ๐ฑ๐ถ๐ฟ๐ฒ๐ฐ๐๐น๐ ๐ถ๐ป๐๐ถ๐ฑ๐ฒ ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐.
Usingย ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐๐ฝ๐ฝ๐, we took a standard Python (Dash) app script and deployed it as a secure, serverless web application.
This is not a read-only dashboard. Because we connected it toย ๐๐ฎ๐ธ๐ฒ๐ฏ๐ฎ๐๐ฒ (๐ฃ๐ผ๐๐๐ด๐ฟ๐ฒ๐)ย from Day 10, the app is fullyย ๐ฅ๐ฒ๐ฎ๐ฑ/๐ช๐ฟ๐ถ๐๐ฒ ๐๐ถ๐๐ต ๐ฏ๐๐ถ๐น๐-๐ถ๐ป ๐ด๐ผ๐๐ฒ๐ฟ๐ป๐ฎ๐ป๐ฐ๐ฒ.
Zero Dockerfiles. Zero external hosting. Just App and Lakehouse working together.
๐๏ธ Start Day 11:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Dash #Python #FullStack #DataEngineering #Databricks
๐ง๐ต๐ฒ ๐ก๐ผ๐ฟ๐๐ต ๐ฃ๐ผ๐น๐ฒ ๐ถ๐ ๐ฏ๐๐๐ ๐ฒ๐ป๐ผ๐๐ด๐ต ๐๐ถ๐๐ต๐ผ๐๐ ๐ฑ๐ฒ๐ฏ๐๐ด๐ด๐ถ๐ป๐ด ๐ฐ๐น๐๐ป๐ธ๐ ๐ฅ๐ฒ๐๐ฒ๐ฟ๐๐ฒ ๐๐ง๐ ๐ฝ๐ถ๐ฝ๐ฒ๐น๐ถ๐ป๐ฒ๐.
Itโsย ๐๐ฎ๐ ๐ญ๐ฌย of theย ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐, and we have a classic integration problem at the North Pole.
The Data Science team loves Spark. The Workshop Operations team needs a database connection. Usually, this means building a brittle "Reverse ETL" pipeline to shove data out of a secure platform into a siloed database.
Today, we simplified the story with ๐๐ฎ๐ธ๐ฒ๐ฏ๐ฎ๐๐ฒ, fully managed Postgres from @databricks. The real magic: Instead of writing complex sync code, we justย ๐ฑ๐ฒ๐ฐ๐น๐ฎ๐ฟ๐ฒย a Synced Table (from a Delta table to Lakebase Postgres).
Analytical power and operational speed, all in one platform.
๐๏ธ Start Day 10:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Databricks #Lakebase #ETL #DataEngineering #FullStack
12
๐ง๐ต๐ฒ ๐ก๐ผ๐ฟ๐๐ต ๐ฃ๐ผ๐น๐ฒ ๐ถ๐ ๐ฎ ๐ฐ๐ผ๐บ๐ฝ๐น๐ฒ๐
๐ผ๐ฟ๐ด๐ฎ๐ป๐ถ๐๐ฎ๐๐ถ๐ผ๐ป. ๐ฌ๐ผ๐ ๐ฐ๐ฎ๐ป'๐ ๐ฒ๐
๐ฝ๐ฒ๐ฐ๐ ๐๐ต๐ฒ ๐ ๐ฎ๐ถ๐น๐ฟ๐ผ๐ผ๐บ ๐๐น๐ณ ๐๐ผ ๐ธ๐ป๐ผ๐ ๐๐ต๐ฎ๐'๐ ๐ต๐ฎ๐ฝ๐ฝ๐ฒ๐ป๐ถ๐ป๐ด ๐ผ๐ป ๐๐ต๐ฒ ๐๐ฎ๐ฐ๐๐ผ๐ฟ๐ ๐๐น๐ผ๐ผ๐ฟ.
Itโsย ๐๐ฎ๐ ๐ต of the ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐, and we are applying that same logic to our AI.
A single AI agent can't be an expert at everything. If you ask one model to analyze theย sentimentย of a letter and thenย queryย a production database, it often gets confused. Itโs too much context switching and optimization gets difficult.
๐ง๐ต๐ฒ ๐๐ผ๐น๐๐๐ถ๐ผ๐ป? ๐ช๐ฒ ๐ป๐ฒ๐ฒ๐ฑ ๐ฎ ๐ฆ๐๐ฝ๐ฒ๐ฟ๐๐ถ๐๐ผ๐ฟ.
Today, usingย ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐๐ด๐ฒ๐ป๐ ๐๐ฟ๐ถ๐ฐ๐ธ๐, we built aย ๐ ๐๐น๐๐ถ-๐๐ด๐ฒ๐ป๐ ๐ฆ๐๐๐๐ฒ๐บย that acts as an Operations Manager. It doesn't do the work; it delegates.
๐น ๐ง๐ฎ๐๐ธ ๐:ย "Find letters that sound grateful." โ Routed to theย ๐๐ป๐ผ๐๐น๐ฒ๐ฑ๐ด๐ฒ ๐๐๐๐ถ๐๐๐ฎ๐ป๐.
๐น ๐ง๐ฎ๐๐ธ ๐:ย "Check the Coal Warning List." โ Routed to theย Ops Agent.
The Supervisor combines the intel into one perfect answer. We didn't write any complex routing code, we just defined the team, and Agent Bricks handled the rest.
๐๏ธ Start Day 9:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Databricks #AgentBricks #MultiAgent
9
Itโsย ๐๐ฎ๐ ๐ดย of theย ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐, and we are solving the "last mile" problem between Santa's data and his AI agents. ๐
Usually, if you want an AI to check "Toy Inventory" or "Reindeer Health," you have to build a custom API layer. You write the SQL, then you write the Python wrapper, then you deploy the container. Itโs heavy, slow, and brittle.
Today, we remove the middleware.
Usingย ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐ ๐ฎ๐ป๐ฎ๐ด๐ฒ๐ฑ ๐ ๐๐ฃ (๐ ๐ผ๐ฑ๐ฒ๐น ๐๐ผ๐ป๐๐ฒ๐
๐ ๐ฃ๐ฟ๐ผ๐๐ผ๐ฐ๐ผ๐น), we took 20+ SQL functions and instantly turned them into callable AI tools. We gave the AI "hands" to help run the North Pole, without building a single server.
๐๏ธ Start Day 8:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Databricks #Startups #AI #ManagedMCP #DatabricksForStartups #MCP
9
๐ฅ๐ฒ๐ณ๐น๐ฒ๐ฐ๐๐ถ๐ป๐ด ๐ผ๐ป ๐ฎ๐ป ๐ถ๐ป๐ฐ๐ฟ๐ฒ๐ฑ๐ถ๐ฏ๐น๐ฒ ๐ป๐ถ๐ด๐ต๐ ๐ผ๐ณ ๐ฐ๐ผ๐ป๐ป๐ฒ๐ฐ๐๐ถ๐ผ๐ป ๐ฎ๐ ๐๐ช๐ฆ ๐ฟ๐ฒ:๐๐ป๐๐ฒ๐ป๐ ๐ถ๐ป ๐๐ฎ๐ ๐ฉ๐ฒ๐ด๐ฎ๐!ย ๐
Databricks Ventures, Wipro Ventures, and Capital One Ventures brought together a powerhouse group of founders and VCs to discuss the evolving landscape of the data and AI ecosystem.
Grateful to our partners and every founder who took the time to step away from the conference for a night of community and collaboration.
#Founders #Startups #DataAI #AWSreInvent #DatabricksForStartups #Databricks
33
โย ๐๐ณ ๐ฎ ๐๐ถ๐๐ต ๐น๐ถ๐๐ ๐ฐ๐ผ๐ป๐๐ฎ๐ถ๐ป๐ "๐ผ๐ถ๐น ๐ฝ๐ฎ๐ถ๐ป๐๐", ๐ฎ ๐ธ๐ฒ๐๐๐ผ๐ฟ๐ฑ ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต ๐ณ๐ผ๐ฟ "๐ฐ๐ฟ๐ฒ๐ฎ๐๐ถ๐๐ฒ ๐ด๐ถ๐ณ๐๐" ๐๐ถ๐น๐น ๐ฟ๐ฒ๐๐๐ฟ๐ป ๐๐ฒ๐ฟ๐ผ ๐ฟ๐ฒ๐๐๐น๐๐.
That is a data retrieval failure. And itโs exactly why we are upgrading the North Poleโs search engine onย ๐๐ฎ๐ ๐ณย of ourย ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐.
Standard text search is brittle. It relies on exact matches. If the user doesn't guess the exact keyword the writer used, the insight is lost.
๐ง๐ผ๐ฑ๐ฎ๐, ๐๐ฒ ๐ฎ๐ฟ๐ฒ ๐ฟ๐ฒ๐ฝ๐น๐ฎ๐ฐ๐ถ๐ป๐ด ๐ธ๐ฒ๐๐๐ผ๐ฟ๐ฑ๐ ๐๐ถ๐๐ต ๐๐ฎ๐๐ฎ๐ฏ๐ฟ๐ถ๐ฐ๐ธ๐ ๐ ๐ผ๐๐ฎ๐ถ๐ฐ ๐๐ ๐ฉ๐ฒ๐ฐ๐๐ผ๐ฟ ๐ฆ๐ฒ๐ฎ๐ฟ๐ฐ๐ต.
In this demo, we build a pipeline that automatically converts millions of letters into vector embeddings, allowing Santa to search for concepts.
๐๏ธ Start Day 7:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Databricks #Startups #VectorSearch #MosaicAI #DatabricksForStartups
3
๐ฌ "๐๐ฒ๐ ๐๐ฒ๐ป๐ถ๐ฒ, ๐๐ต๐ผ๐ ๐บ๐ฒ ๐๐ต๐ฒ ๐๐ผ๐ฝ ๐ด๐ถ๐ณ๐๐ ๐ถ๐ป ๐ค๐๐ฒ๐ฏ๐ฒ๐ฐ."
Welcome to Day 6 of the 12 Days of Demos. Today, we stop forcing the logistics team to write SQL, and we start letting them speak their own language.
We just deployed @Databricks AI/BI Genie to the North Pole operations floor. Now, instead of filing a ticket and waiting 3 days for a report, an elf can simply ask:ย "๐๐ฉ๐ช๐ค๐ฉ ๐ฑ๐ณ๐ฐ๐ท๐ช๐ฏ๐ค๐ฆ๐ด ๐ข๐ณ๐ฆ ๐ณ๐ฆ๐ฒ๐ถ๐ฆ๐ด๐ต๐ช๐ฏ๐จ ๐ต๐ฉ๐ฆ ๐ฎ๐ฐ๐ด๐ต ๐ฃ๐ช๐ค๐บ๐ค๐ญ๐ฆ๐ด?"ย and get a visualization instantly.
But is it safe? If an Elf asks:ย "๐๐ฉ๐ฐ๐ธ ๐ฎ๐ฆ ๐ต๐ฉ๐ฆ ๐ณ๐ฆ๐ข๐ญ ๐ฏ๐ข๐ฎ๐ฆ๐ด ๐ฐ๐ง ๐ต๐ฉ๐ฆ ๐ค๐ฉ๐ช๐ญ๐ฅ๐ณ๐ฆ๐ฏ ๐ช๐ฏ ๐๐ฐ๐ณ๐ฐ๐ฏ๐ต๐ฐ,"ย what happens? Genie refuses.
Not because of a prompt instruction like "๐๐ญ๐ฆ๐ข๐ด๐ฆ ๐ฃ๐ฆ ๐ฏ๐ช๐ค๐ฆ," but because of architecture. Give your business users answers grounded in your data.
๐๏ธ Start Day 6:ย medium.com/startups-at-databโฆ
๐ Missed previous days? Catch all the demo drops here:ย medium.com/startups-at-databโฆ
๐ป Get the Code:ย github.com/arjuncode/12daysoโฆ
#Genie #BusinessIntelligence #ConversationalAnalytics #12DaysOfDemos #Databricks
35
Itโsย ๐๐ฎ๐ ๐ฑ of theย ๐ญ๐ฎ ๐๐ฎ๐๐ ๐ผ๐ณ ๐๐ฒ๐บ๐ผ๐, and we are fixing a problem every data engineer knows too well:ย ๐๐ผ๐ด๐ถ๐ฐ ๐ฆ๐ฝ๐ฟ๐ฎ๐๐น.
The North Pole had a "single source of truth" for their data, but they didn't have one for their logic. The code to mask sensitive names or calculate regional metrics is copy-pasted across 50+ different notebooks. If you fix a bug in one notebook, itโs still broken in 49 others. Thatโs not just tech debt, thatโs a security risk.
๐ง๐ต๐ฒ ๐ฆ๐ผ๐น๐๐๐ถ๐ผ๐ป: Unity Catalog Functions. โ
In todayโs demo, we stop writing code in silos. We elevate our SQL functions to beย ๐ณ๐ถ๐ฟ๐๐-๐ฐ๐น๐ฎ๐๐ ๐ฐ๐ฎ๐๐ฎ๐น๐ผ๐ด ๐ฎ๐๐๐ฒ๐๐โgoverned, permissioned, and versioned just like our tables.
๐๏ธ ๐ฆ๐๐ฎ๐ฟ๐ ๐๐ฎ๐ ๐ฑ:ย medium.com/startups-at-databโฆ
๐ ๐ ๐ถ๐๐๐ฒ๐ฑ ๐ฝ๐ฟ๐ฒ๐๐ถ๐ผ๐๐ ๐ฑ๐ฎ๐๐? ๐๐ฎ๐๐ฐ๐ต ๐ฎ๐น๐น ๐๐ต๐ฒ ๐ฑ๐ฒ๐บ๐ผ ๐ฑ๐ฟ๐ผ๐ฝ๐ ๐ต๐ฒ๐ฟ๐ฒ:ย medium.com/startups-at-databโฆ
๐ป ๐๐ฒ๐ ๐๐ต๐ฒ ๐๐ผ๐ฑ๐ฒ:ย github.com/arjuncode/12daysoโฆ
#Databricks #DataGovernance #DataEngineering #UnityCatalog #SQL #12DaysOfDemos
13
























