{"podcast":{"title":"Just Now Possible","slug":"just-now-possible-7481489","podcast_index_feed_id":7481489,"rss_url":"https://justnowpossible.podigee.io/feed/mp3","website_url":"https://justnowpossible.com","image_url":"https://images.podigee-cdn.net/0x,sE3DpK6ye22MceFW24luiwKIEBIkAbv9w3bVVaFUvtQU=/https://main.podigee-cdn.net/uploads/u78902/19a97a2f-6164-40f9-8ff0-c2480f4e273a.png","author":"Teresa Torres","episode_count":28,"summary":"How AI products come to life—straight from the builders themselves. In each episode, we dive deep into how teams spotted a customer problem, experimented with AI, prototyped solutions, and shipped real features. We dig into everything from workflows and agents to RAG and evaluation strategies, and explore how their products keep evolving. If you’re building with AI, these are the stories for you.","last_synced_at":"2026-06-25T18:17:48.296419+00:00","page_url":"https://stenobird.com/podcast/just-now-possible-7481489"},"episode":{"title":"Building Todoist Ramble: How Doist Turned Voice Braindumps into Real-Time Task Capture","slug":"building-todoist-ramble-how-doist-turned-voice-braindumps-into-real-time-task-capture","published_at":"2026-04-16T08:00:00+00:00","page_url":"https://stenobird.com/podcast/just-now-possible-7481489/building-todoist-ramble-how-doist-turned-voice-braindumps-into-real-time-task-capture","show_page_url":"https://stenobird.com/podcast/just-now-possible-7481489","url":"https://justnowpossible.podigee.io/23-building-todoist-ramble","audio_url":"https://audio.podigee-cdn.net/2441829-m-15d6c9fbd26df14c4e433c4736b6e992.mp3?source=feed","summary":"How do you turn a rambling stream of consciousness into a clean task list — while the person is still talking? That's the core challenge Doist solved with Ramble, a voice-to-task feature inside Todoist that uses live audio AI to capture tasks in real time, no transcription step required. In this episode of Just Now Possible, Teresa Torres talks with Ernesto Garcia (Front-end Product Engineer), Thomas Jost (Backend Software Engineer), and Hugo Fauquenoi (Product Manager) from Doist about how they built Ramble — Todoist's first pure AI feature. What started as a two-to-three month AI exploration phase became one of the most technically deliberate features they've shipped: a Gemini-powered pipeline that makes tool calls while the user is still speaking, surfacing tasks on screen in real time without any text output from the model. You'll hear how they designed around the \"brain dump\" behavior they found in user research, why they chose direct context injection over RAG for project and label matching, the surprising complexity of date handling in a live audio pipeline, and how they built a multi-language eval system using real employee recordings across 35 countries. It's a detailed look at the discipline of keeping AI features simple, constrained, and genuinely useful.","meta_description":"How do you turn a rambling stream of consciousness into a clean task list — while the person is still talking? That's the core challenge Doist solved with…","key_points":[],"chapters":[],"topics":[],"duration_seconds":3640,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/just-now-possible-7481489/episodes/building-todoist-ramble-how-doist-turned-voice-braindumps-into-real-time-task-capture/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/just-now-possible-7481489/building-todoist-ramble-how-doist-turned-voice-braindumps-into-real-time-task-capture.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}