{"podcast":{"title":"Scaling DevTools","slug":"scaling-devtools","podcast_index_feed_id":5370747,"rss_url":"https://feeds.transistor.fm/scaling-devtools","website_url":"http://scalingdevtools.com","image_url":"https://img.transistorcdn.com/HkfKelaid_fFruHof3T1113FnoaMA6qHS5kMN568xTo/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzI5MTkzLzE2NDk3/Nzk2NDAtYXJ0d29y/ay5qcGc.jpg","author":"Scaling DevTools","episode_count":188,"summary":"We investigate what it takes to grow developer tools and AI DevTools. Topics include developer marketing, DevRel, developer advocacy and developer experience. Featuring founders and key people from the likes of Vercel, ElevenLabs and OpenAI. Scaling DevTools is sponsored by WorkOS.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/scaling-devtools"},"episode":{"title":"Matt Aitken from Trigger.dev @ AIE","slug":"matt-aitken-from-trigger-dev-aie","published_at":"2026-04-16T15:27:49+00:00","page_url":"https://stenobird.com/podcast/scaling-devtools/matt-aitken-from-trigger-dev-aie","show_page_url":"https://stenobird.com/podcast/scaling-devtools","url":"https://podcast.scalingdevtools.com/episodes/matt-aitken-from-trigger-dev-aie","audio_url":"https://media.transistor.fm/745e5ae9/dc0770b4.mp3","summary":"Building sophisticated AI agents requires moving beyond stateless APIs to manage long-running execution state and context. Matt Aitken explains how Trigger.dev uses VM snapshotting to handle durable agents and secure code execution.","meta_description":"Learn how to build durable, long-running AI agents using VM snapshotting, Firecracker micro-VMs, and advanced execution state management.","key_points":["Main idea: Moving from stateless LLM calls to durable agents requires managing both conversation context and execution state","Technical approach: Using VM snapshots of CPU, memory, and filesystem allows agents to pause and resume without losing progress","Practical takeaway: Snapshotting allows developers to avoid paying for compute while waiting for human feedback or external events","Security challenge: Executing LLM-generated code requires robust sandboxing, such as using Firecracker micro-VMs, to prevent unauthorized credential access","Failure mode: Relying solely on message history leads to bloated context and high costs as conversation length increases"],"chapters":[{"start_ms":60000,"title":"The Problem with Stateless LLM APIs","summary":"Discussing the limitations of simple request-response patterns and the growing complexity of managing massive conversation histories."},{"start_ms":110000,"title":"Defining Durable Agents","summary":"An exploration of the trade-offs involved in building agents that require persistent memory and long-running processes."},{"start_ms":160000,"title":"Step-based Execution vs. State Management","summary":"Comparing traditional step-based caching methods with more advanced approaches for handling extremely long agent runs."},{"start_ms":260000,"title":"VM Snapshotting for Execution State","summary":"How Trigger.dev snapshots the entire machine state to handle context, files, and memory across different servers."},{"start_ms":310000,"title":"Handling Latency and Human-in-the-loop","summary":"Managing the cost and efficiency of agents that must wait for external events, other agents, or human approvals."},{"start_ms":405000,"title":"Sandboxing with Firecracker","summary":"The move toward using Firecracker micro-VMs to provide secure, high-performance sandboxes for untrusted, LLM-generated code."},{"start_ms":505000,"title":"Security and Observability in AI","summary":"Addressing the challenges of fine-grained permissions and the need for queryable execution logs in production environments."}],"topics":["AI Agents","Durable Execution","LLM Orchestration","Micro-VMs","Firecracker","Software Sandboxing","Serverless Computing","Observability"],"duration_seconds":710,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/scaling-devtools/episodes/matt-aitken-from-trigger-dev-aie/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/scaling-devtools/matt-aitken-from-trigger-dev-aie.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}