{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"START","title":"START: Thomas Karatzas, Co-Founder & CEO, Terse \"Durable Agent Infra\"","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/5d9ca024\"></iframe>","width":"100%","height":180,"duration":748,"description":"A user running one AI agent had no problems.\nRunning 10 at once exposed a problem that would change the direction of an entire startup.\nThe issue started with something simple.\nA workflow automation tool let users take a CSV containing a list of people and run automated tasks on portions of that list.\nWhen someone ran a workflow once, everything worked.\nBut some users wanted to run 10 workflows simultaneously.\nThat's when things broke.\nEach agent would read the same saved position in the CSV before the others could update it.\nInstead of processing different records, multiple agents ended up doing the same work.\nFor Thomas Karatzas, Co-Founder & CEO of Terse (YC F26), the problem revealed a much bigger opportunity.\nCoordinating multiple AI agents that share state requires infrastructure that handles concurrency, persistence, and recovery.\nRather than continuing to build workflow automation tools, the team decided to build the underlying infrastructure.\nThat became the new direction for Terse.\nIts solution is Durable Actors.\nEach actor gets its own persistent state and SQLite database, with requests coordinated to prevent the race conditions that caused the original problem.\nConsider an AI evaluation that takes 10 hours to complete.\nIf the process crashes halfway through, developers without durable execution may lose their progress or struggle to recover it.\nWith Terse, applications can persist state as work progresses, allowing interrupted tasks to recover without starting over.\nThe same infrastructure supports coordinating large numbers of AI agents, managing shared application state, and building real-time applications where humans and agents work together.\nAnd Terse is making its actor runtime open source, giving developers the option to run the infrastructure themselves rather than relying exclusively on a hosted service.\nWhat began as a problem with 10 agents processing a CSV helped reveal an infrastructure challenge that becomes increasingly important as AI...","thumbnail_url":"https://img.transistorcdn.com/q-E1hh7K6IS4AfZiNy2p4MYVGcUOO8lQP92h8QbOEOA/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS80NzVj/MDEzNjkxNjU1N2Uy/NDFhMDQ3M2ZhNWI3/NWY0MS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}