Uploaded August 2026 | Updated September 2026, 2 weeks ago
π― Your pipeline treats human review as an exception. Netflix made it a worker type - same slot rules, ML models and AI agents plug into.
βοΈ Pratyusha Singaraju (Netflix) shows the two-tier architecture that makes it work: state and execution kept apart.
What's inside:
πΈ Why Conductor alone couldn't answer "how many tasks are waiting on a human right now?"
πΈ Human corrections stored as structured output, not notes - straight into retraining.
πΈ A sub-workflow and a config get you dashboards, QC and human review for free.
ποΈ Pratyusha Singaraju is a Senior Software Engineer at Netflix, where she architects and builds the backend services behind Netflix's content understanding infrastructure - the systems powering search, collections and ratings for millions of viewers. Before Netflix, she worked on Microsoft's data team for Bing, building knowledge graph initiatives across public domains including food, nutrition, politics and events, as well as an enterprise knowledge graph.
Connect with Pratyusha:
π linkedin.com/in/pratyusha-singaraju
π Talk: Orchestrating Content Workflows at Netflix Scale | Pratyusha Singaraju
This talk was recorded at JSNation Amsterdam 2026:
π jsnation.com/?utm_source=youtube&utm_medium=PratyushaSingaraju
π Follow the link to watch the full version of all the conference talks, QnAβs with speakers and hands-on workshop recordings:
π gitnation.com/events/jsnation-2026?utm_source=youtube&utm_medium=PratyushaSingaraju
π Timestamps:
00:00 - Intro: three kinds of decision-maker, one pipeline
01:12 - Your 20% Off π«£
01:34 - Rules break, models guess, humans don't scale
04:02 - Two custom workflows, 7 states and 9, nothing reusable
06:21 - The split that made everything else possible
07:35 - RAW Hollow: the entire dataset in every reader's heap
08:45 - Conductor: plug in your sub-workflow, inherit the rest
10:43 - Conductor is powerful. So why wasn't it enough?
11:26 - Onboarding a workflow with config and no code
13:16 - Human in the loop β and why the correction isn't a note
15:07 - The whole flow, end to end
16:29 - The AI agent that opened PRs on the framework running it
17:59 - Four principles that hold it together
π Weβve hidden a secret code for 20% off your next event.
Join our upcoming conferences!
π« JSNation US 2026 Nov 16 & 19, 2026 (NewYork & Online)
π jsnation.us/?utm_source=youtube&utm_medium=PratyushaSingaraju
π« React Summit US 2026 Nov 17 & 20, 2026 (NewYork & Online)
π reactsummit.us/?utm_source=youtube&utm_medium=PratyushaSingaraju
π« AI Coding Summit Nov 16 & 17, 2026 (New York & Online)
aicodingsummit.com/nyc/?utm_source=youtube&utm_medium=PratyushaSingaraju
and more!
π Check out all the upcoming events from GitNation:
π gitnation.com/events?utm_source=youtube&utm_medium=PratyushaSingaraju
Don't forget to use INSIDER20 promo code for 20% off on tickets.
#JSNation #GitNation #Netflix #NetflixEngineering #SoftwareArchitecture #SystemDesign #Backend #BackendEngineering #DistributedSystems #Orchestration #WorkflowOrchestration #ConductorOSS #NetflixConductor #RAWHollow #Hollow #StateManagement #EventDriven #EventDrivenArchitecture #Microservices #PlatformEngineering #DeveloperPlatform #InternalTools #HumanInTheLoop #HITL #MLOps #MachineLearning #MLInfrastructure #ModelRetraining #FeedbackLoop #AIAgents #AgenticAI #AIEngineering #ContentMetadata #Metadata #DataEngineering #ScalableSystems
π― Your pipeline treats human review as an exception. Netflix made it a worker type - same slot rules, ML models and AI agents plug into.
βοΈ Pratyusha Singaraju (Netflix) shows the two-tier architecture that makes it work: state and execution kept apart.
What's inside:
πΈ Why Conductor alone couldn't answer "how many tasks are waiting on a human right now?"
πΈ Human corrections stored as structured output, not notes - straight into retraining.
πΈ A sub-workflow and a config get you dashboards, QC and human review for free.
ποΈ Pratyusha Singaraju is a Senior Software Engineer at Netflix, where she architects and builds the backend services behind Netflix's content understanding infrastructure - the systems powering search, collections and ratings for millions of viewers. Before Netflix, she worked on Microsoft's data team for Bing, building knowledge graph initiatives across public domains including food, nutrition, politics and events, as well as an enterprise knowledge graph.
Connect with Pratyusha:
π linkedin.com/in/pratyusha-singaraju
π Talk: Orchestrating Content Workflows at Netflix Scale | Pratyusha Singaraju
This talk was recorded at JSNation Amsterdam 2026:
π jsnation.com/?utm_source=youtube&utm_medium=PratyushaSingaraju
π Follow the link to watch the full version of all the conference talks, QnAβs with speakers and hands-on workshop recordings:
π gitnation.com/events/jsnation-2026?utm_source=youtube&utm_medium=PratyushaSingaraju
π Timestamps:
00:00 - Intro: three kinds of decision-maker, one pipeline
01:12 - Your 20% Off π«£
01:34 - Rules break, models guess, humans don't scale
04:02 - Two custom workflows, 7 states and 9, nothing reusable
06:21 - The split that made everything else possible
07:35 - RAW Hollow: the entire dataset in every reader's heap
08:45 - Conductor: plug in your sub-workflow, inherit the rest
10:43 - Conductor is powerful. So why wasn't it enough?
11:26 - Onboarding a workflow with config and no code
13:16 - Human in the loop β and why the correction isn't a note
15:07 - The whole flow, end to end
16:29 - The AI agent that opened PRs on the framework running it
17:59 - Four principles that hold it together
π Weβve hidden a secret code for 20% off your next event.
Join our upcoming conferences!
π« JSNation US 2026 Nov 16 & 19, 2026 (NewYork & Online)
π jsnation.us/?utm_source=youtube&utm_medium=PratyushaSingaraju
π« React Summit US 2026 Nov 17 & 20, 2026 (NewYork & Online)
π reactsummit.us/?utm_source=youtube&utm_medium=PratyushaSingaraju
π« AI Coding Summit Nov 16 & 17, 2026 (New York & Online)
aicodingsummit.com/nyc/?utm_source=youtube&utm_medium=PratyushaSingaraju
and more!
π Check out all the upcoming events from GitNation:
π gitnation.com/events?utm_source=youtube&utm_medium=PratyushaSingaraju
Don't forget to use INSIDER20 promo code for 20% off on tickets.
#JSNation #GitNation #Netflix #NetflixEngineering #SoftwareArchitecture #SystemDesign #Backend #BackendEngineering #DistributedSystems #Orchestration #WorkflowOrchestration #ConductorOSS #NetflixConductor #RAWHollow #Hollow #StateManagement #EventDriven #EventDrivenArchitecture #Microservices #PlatformEngineering #DeveloperPlatform #InternalTools #HumanInTheLoop #HITL #MLOps #MachineLearning #MLInfrastructure #ModelRetraining #FeedbackLoop #AIAgents #AgenticAI #AIEngineering #ContentMetadata #Metadata #DataEngineering #ScalableSystems










