Can’t Apps and Databases All Just Get Along?

Availability is a tricky thing. In order for your tier 0 endpoints to be available all their hard dependencies have to be available. For Stytch that means basically network, compute, database, and messaging providers. For many of these things there are degraded experiences we can provide that are better than being hard down, but for a fair assessment of availability we have to define some minimum standard of functionality and measure our availability against that standard. In this session we'll cover all the measures we take to ensure that our databases stay up at least 99.999% of the time and that we can recover them gracefully in the event of many different disaster scenarios.


Joshua Hight

Software Engineer @Stytch

Joshua started his career at IBM automating build and release processes for z/OS mainframe database software. He then spent some time at ThinAir Labs (a security startup) building a secure real-time document parsing and ingestion engine that could run on a laptop without activating the fan.

Afterwards he went to Rubrik (a backup and recovery company) and built out a more efficient alternative to MS SQL Server Log Shipping, then picked up a couple patents building an even more efficient alternative to that with a file-system filter driver and “synthetic snapshots” that – with some state machine abuse, can be taken on a secondary and restored to the primary.

Joshua then moved over to Doordash where he built a microservice generator that transpiled protobufs to service skeletons, architected Doordash’s first production Cassandra schema, and designed a new traceable asynchronous dependency resolution framework for the search service that more than halved the latency.

And finally, Joshua joined Stytch on the Infrastructure team and is currently working to level up our database infrastructure to ensure our performance and resilience lift up our developers and more importantly our customers.

Read more

Session Sponsored By

The most powerful identity platform built for developers.


Wednesday Oct 4 / 11:45AM PDT ( 50 minutes )


Pacific LM


Video is not available


Slides are not available


From the same track


Introduction to Real-Time Training and Scoring in AI/ML

Wednesday Oct 4 / 01:35PM PDT

In the rapidly evolving landscape of AI/ML, the shift from batch to real-time data processing is significant. It impacts how quickly and dynamically we can learn from data, leading to more responsive AI applications.

Speaker image - Wes Wagner

Wes Wagner

Solutions Engineer @Redpanda


Simple Platform Engineering and Simply High Cardinality Observability

Wednesday Oct 4 / 02:45PM PDT

Platform engineering transforms repetitive Engineering requirements into standardised and dependable services, or "paved roads". These paved roads offer engineering teams a smooth way to develop and deploy business logic layers continuously.

Speaker image - Piyush  Verma

Piyush Verma

Co-Founder and CTO @Last9


LLMs + Knowledge Graphs = Better Together

Wednesday Oct 4 / 03:55PM PDT

LLMs are often like the know-it-all at a bar - they can quickly and confidently produce realistic sounding answers to just about any question - even if the answers are complete fabrications.

Speaker image - Mark Quinsland

Mark Quinsland

Senior Field Engineer @Neo4j


Designing AI Agents with System Thinking

Wednesday Oct 4 / 10:35AM PDT

AI agents are a perfect fit for serverless environments, as they can leverage the power of the cloud and the edge for fast and accurate decision making.  It is often the case that AI applications do not require the costly vector database and compute solutions which are often used today, to s

Speaker image - Logan Grasby

Logan Grasby