---
title: "Slides: Realtime Data Connectivity for AI: Tanmai Gopal"
category: "slides"
video_id: "himhGiWJXjo"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Realtime Data Connectivity for AI: Tanmai Gopal

## Source Video
[Realtime Data Connectivity for AI: Tanmai Gopal](https://www.youtube.com/watch?v=himhGiWJXjo)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/himhGiWJXjo/slide-001.jpg]]

OCR text:

> INNOVATION SPONSOR
> aws
> PLATINUM SPONSORS
> MongoDB.
> Google Cloud
> neo4j

![[assets/slides/himhGiWJXjo/slide-002.jpg]]

OCR text:

> Embrace the
> AI overlords
> Give them the data they
> need.
> Pacha DDN

![[assets/slides/himhGiWJXjo/slide-003.jpg]]

OCR text:

> P oe ae ee oe TR a se 2O2 RLS eo erelil
> -_ World's Fair ee World
> anlore! a aor World's Fair e
> re
> a Lambda ent
> PN Sees gered
> $ cf
> World's Fair |
> Presented by World's Fair a
> Z...
> —g Microsoft

![[assets/slides/himhGiWJXjo/slide-004.jpg]]

OCR text:

> Why is the deal with
> ACME stuck in stage 3?

![[assets/slides/himhGiWJXjo/slide-005.jpg]]

OCR text:

> We solved this.
> Make your data & business logic available as
> a tool for your LLM.

![[assets/slides/himhGiWJXjo/slide-006.jpg]]

OCR text:

> CoCO:Lac:al-engine:(ain)SIOGEIHER-API_KEY-$IOGEIHER API-KEY: poetrY Arun chatr-d POstgreSN-CASPOSI6RES

![[assets/slides/himhGiWJXjo/slide-007.jpg]]

OCR text:

> coco-aac:af-engine(eain)s
> Press double Enter after you are done entering your query
> User:hlp ee vrit
> AIE
> Worid'sF
> Microsoft
> smol"

![[assets/slides/himhGiWJXjo/slide-008.jpg]]

OCR text:

> executor.output('No
> else:
> recent.novies-[novie["title]for novieInrecent.rentals]
> executor.output（f'Tcpcustooer:[custoer_naee]
> （[customer_enall])\nRecentsovies:[,".join（recent_movies）]'）
> Query: SELECT first_nao,last_nae,eail FROM public.custoer WHERE customer_id(SELECI customer_id FRO publlc.rental GouP BY custo
> AIE
> r_idORDERBY COUNT（rental_id)DESCLIKIT1）
> ELEANOR.HUNTBsakSIacuStomar.org'
> Quory:SELECT f.title FROM public.rentalr JoINpublic.inventoryONr.inventory-idi.inventory.ld JoINpublic.filn fONi.fila.id
> filidHEREr.customer_id(SELECT customer_id FROK public.renta】 GROUP BY custoer_id ORDER BY COUNT（renta].id) DESC LINIT 1) ORDER BY
> .rental.date DESC LIHITS
> RespOnS:[Eitle':'RACER EGG],'title:NUMY CREATURES'},'tItleHELLFIGHTERS SIERRA},'title:WIZARD COLDBLOOOED'},tit
> 1e:'DINOSAURSECRETARY]
> tionResult:
> NT（ELEANOR.HUNTBsakilacUstomer.org)
> MURKY CREATURES,HELLFIGHTERS SIERRA,WTZARD COLDBLOODED,DINOSAUR SECRETARY
> Worke'sFai
> Microsoft
> .lows

![[assets/slides/himhGiWJXjo/slide-009.jpg]]

OCR text:

> LLMs don't know what your API is.
> But LLMs know what SQL is.
> What if everything was SQL?

![[assets/slides/himhGiWJXjo/slide-010.jpg]]

OCR text:

> Property of the data. property of the
> session.
> | . WHY. IS. THIS. SO. COMPLEX.
> ite aws

![[assets/slides/himhGiWJXjo/slide-011.jpg]]

OCR text:

> #3. Get LLMs to figure out the plan of how to
> access data.

![[assets/slides/himhGiWJXjo/slide-012.jpg]]

OCR text:

> Write a python program to figure out a plan to
> retrieve multiple pieces of data required.
> PachaDDN

![[assets/slides/himhGiWJXjo/slide-013.jpg]]

OCR text:

> AIE
> AI Engineer
> World's Fair
> Microsoft
> smol ai

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.