# Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut - #769

Page: https://stenobird.com/podcast/twiml-ai-podcast/is-rag-dead-lessons-from-building-ai-for-tax-law-with-alex-bowcut-769
Text version: https://stenobird.com/podcast/twiml-ai-podcast/is-rag-dead-lessons-from-building-ai-for-tax-law-with-alex-bowcut-769.md
Podcast: [The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)](https://stenobird.com/podcast/twiml-ai-podcast)
Published: 2026-06-09T19:25:00+00:00
Episode link: https://twimlai.com/podcast/twimlai/rag-dead-lessons-building-ai-tax-law
Audio file: https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN3192814886.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/is-rag-dead-lessons-from-building-ai-for-tax-law-with-alex-bowcut-769
Duration seconds: 3092

## Resource

As context windows grow into the millions of tokens, many AI practitioners are questioning whether retrieval-augmented generation (RAG) is still necessary. If modern models can ingest entire libraries of documents, why bother with retrieval at all? In this episode, Alex Bowcut, Head of Engineering at Sphere, explains why the answer depends on the application. Sphere uses AI to automate global tax compliance—an environment where getting the answer right isn’t enough. Every conclusion must be backed by the correct legal citation, and every decision must withstand expert review. We explore how Sphere built TRAM (Tax Review and Assessment Model), a production AI system that combines retrieval, reasoning models, legal review workflows, reinforcement learning, and deterministic systems to help tax experts move nearly two orders of magnitude faster while maintaining accuracy. Along the way, we discuss why RAG remains critical in high-stakes domains, how Sphere processes legal and regulatory documents from jurisdictions around the world, retrieval architectures, semantic chunking, dense versus sparse retrieval, expert feedback loops, and the challenges of building AI systems that people can actually trust. 🗒️ Full show notes: https://twimlai.com/go/769.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/is-rag-dead-lessons-from-building-ai-for-tax-law-with-alex-bowcut-769/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/twiml-ai-podcast/is-rag-dead-lessons-from-building-ai-for-tax-law-with-alex-bowcut-769.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.