# Matt Aitken from Trigger.dev @ AIE

Page: https://stenobird.com/podcast/scaling-devtools/matt-aitken-from-trigger-dev-aie
Text version: https://stenobird.com/podcast/scaling-devtools/matt-aitken-from-trigger-dev-aie.md
Podcast: [Scaling DevTools](https://stenobird.com/podcast/scaling-devtools)
Published: 2026-04-16T15:27:49+00:00
Episode link: https://podcast.scalingdevtools.com/episodes/matt-aitken-from-trigger-dev-aie
Audio file: https://media.transistor.fm/745e5ae9/dc0770b4.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/scaling-devtools/episodes/matt-aitken-from-trigger-dev-aie
Duration seconds: 710

## Resource

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.

## Highlights
- 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

## Topics

AI Agents, Durable Execution, LLM Orchestration, Micro-VMs, Firecracker, Software Sandboxing, Serverless Computing, Observability

## Chapters
- 1:00 — The Problem with Stateless LLM APIs: Discussing the limitations of simple request-response patterns and the growing complexity of managing massive conversation histories.
- 1:50 — Defining Durable Agents: An exploration of the trade-offs involved in building agents that require persistent memory and long-running processes.
- 2:40 — Step-based Execution vs. State Management: Comparing traditional step-based caching methods with more advanced approaches for handling extremely long agent runs.
- 4:20 — VM Snapshotting for Execution State: How Trigger.dev snapshots the entire machine state to handle context, files, and memory across different servers.
- 5:10 — Handling Latency and Human-in-the-loop: Managing the cost and efficiency of agents that must wait for external events, other agents, or human approvals.
- 6:45 — Sandboxing with Firecracker: The move toward using Firecracker micro-VMs to provide secure, high-performance sandboxes for untrusted, LLM-generated code.
- 8:25 — Security and Observability in AI: Addressing the challenges of fine-grained permissions and the need for queryable execution logs in production environments.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/scaling-devtools/episodes/matt-aitken-from-trigger-dev-aie/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/scaling-devtools/matt-aitken-from-trigger-dev-aie.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.