Date: November 3, 2026
Time: 13:00 – 19:00
Location: AWS Office Stockholm
Overview
Most AI apps end up running on several databases: a vector store for embeddings, a relational database for application data, something else for conversation history, and glue code holding it all together. Every extra store adds another sync job and another thing that can break.
Join AWS and TiDB at the AWS office in Stockholm for an afternoon of building. We open with a short, interactive talk, then go hands-on: you’ll set up the runtime on AWS and build an AI customer support bot on top of it, with TiDB as the single data layer underneath. The engineers who built the workshop will be in the room with you.
Then we close the laptops for pizza, beer and conversation with Stockholm’s builders.
What you’ll build
Two hands-on labs, one working app. You’ll leave with an AI customer support bot running on AWS and TiDB.
Lab 1: Establish the runtime
Set up the foundation your bot will run on: Amazon Bedrock for the models, TiDB as the data layer, wired together on AWS. By the end of the lab you’ll have a working runtime ready to build on.
Lab 2: Build a customer support bot
Build an AI customer support bot on the runtime from Lab 1. TiDB holds what the bot needs in one place: product knowledge for vector search, customer and order data in SQL, and the conversation history it remembers between turns.
If you can write SQL and call an API, you can complete both labs.
Why attend
Meet Stockholm’s builders. Close the day with pizza, beer and the engineers building AI on AWS in the city.
Leave with a working bot, not a slide deck. You’ll go from an empty setup to a running AI customer support bot in one afternoon.
Learn from the people who built it. Engineers from AWS and TiDB designed the workshop and will be in the room to help you through it.
See one data layer replace four. Vectors, transactions and conversation history in a single database, so there’s nothing to keep in sync.
Programme
13:00 – Welcome
13:15 – PingCAP and TiDB
13:45 – AWS: how it fits, better together
14:15 – Fika
14:30 – Lab 1: Establish the runtime: Set up the foundation your bot will run on: Amazon Bedrock for the models, TiDB as the data layer, wired together on AWS. By the end of the lab you’ll have a working runtime ready to build
16:30 – Lab 2 Build a customer support bot: Build an AI customer support bot on the runtime from Lab 1. TiDB holds what the bot needs in one place: product knowledge for vector search, customer and order data in SQL, and the conversation history it remembers between turns
18:00 – Pizza and beer
19:00 – Close
Peter Anders Wihman, AWS EMEA North Data and GenAI Lead
I lead our Data and GenAI team across the Nordics and Benelux regions at Amazon Web Services (AWS), the world’s leading cloud provider. I have over 25 years of experience in the IT industry, with a focus on artificial intelligence, cloud computing, and digital transformation.
Bernard Kavanagh Principal Solutions Architectm Applied AI, TiDB
Bernard is a Principal Solutions Architect focused on Applied AI, designing production architectures for agentic and AI-native workloads. He turns the TiDB + AWS joint value into reference patterns engineering teams can actually deploy — collapsing the transactional database, vector store, cache and analytics stack into one engine on AWS, and showing where it fits for payments, multi-tenant SaaS, real-time risk and agentic features.
Fredrik Tormod, Solutions Architect at AWS
Versatile cloud engineer with a diverse background encompassing app development to big data, grounded in cloud technologies, especially AWS. Expertise aligned with the automotive industry, where skills meticulously refined.
Otso Juntunen, Building TiDB (PingCAP) in EMEA
Senior commercial executive with 20+ years building, scaling and turning around go-to-market organizations in cloud, AI and digital infrastructure across the Nordics and EMEA — from strategy consulting at BCG and Gartner to commercial leadership at Google Cloud, Oracle and AWS.