--- schema: 1 type: video title: 'Parsing the Epstein Files for JMail — Palak Agarwal & Omar Alhait, Reducto' description: >- Handwritten flight logs and heavily redacted PDFs stand between a pile of documents and a searchable product. Palak Agarwal and Omar Alhait show how Reducto turned the Epstein files into structured data for JMail and its related applications. Agarwal introduces the document processing layer; Alhait walks through the extraction pipeline behind JFlights, showing how a schema turns difficult pages into usable records. The workflow starts with parsing, tests extraction results in Studio, and exposes the configured pipeline through an API call or code snippet. The product demonstration makes the bottleneck visible: reading order, handwriting, layout, and inconsistent documents need to survive extraction before an interface can make them useful. A live resume example shows how to generate a JSON schema, upload documents, and inspect the resulting fields. The discussion distinguishes a quick schema from one informed by parsed document content, then explores nested fields, citations, figures, and the choice between OCR and PDF metadata. Alhait also describes why drawing a black box over text can leave information exposed, and how the team handled material intended to remain redacted. Questions move from model training and document specific configurations to practical evaluation: inspect a small sample first, then build a representative benchmark before scaling. The recording ends with instructions for an interactive extraction exercise, connecting the JMail case study to participants' own document workflows. Speaker info: - https://palakagarwal.me/ - https://www.linkedin.com/in/palak06/ - https://www.linkedin.com/in/oalhait - https://github.com/oalhait - https://docs.reducto.ai/overview Timestamps: 0:00 - Document processing and Reducto 2:02 - The JMail case study 3:10 - Omar on the parsing challenge 5:27 - JFlights and handwritten logs 6:35 - Configure and inspect extraction 7:41 - Scaling the document pipeline 9:07 - Deploy an API pipeline 10:14 - Generate a resume schema 12:38 - Schemas informed by document content 13:48 - Redaction and PDF metadata 15:34 - Nested schemas and citations 17:41 - Figures and hybrid OCR 19:23 - Parsing as the foundation 21:30 - Benchmarks and practical evaluation 23:44 - Product design and training data 26:12 - Tailor document configurations 27:59 - Interactive exercise instructions --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/HGfsfKaVuGY-youtube-79b0f112f4cbb4109538 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/parsing-the-epstein-files-for-jmail-palak-agarwal-o-4b05db2c3bdc markdown: >- https://liquidgold.cc/channel/aidotengineer/video/parsing-the-epstein-files-for-jmail-palak-agarwal-o-4b05db2c3bdc.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:19:19.886Z' language: null children: [] videoId: HGfsfKaVuGY durationSeconds: 1769 publishedAt: '2026-10-11T11:30:30.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 24 endSeconds: 131 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=24' heldReason: rights - ordinal: 1 text: null startSeconds: 131 endSeconds: 142 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=131' heldReason: rights - ordinal: 2 text: null startSeconds: 131 endSeconds: 142 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=131' heldReason: rights - ordinal: 3 text: null startSeconds: 142 endSeconds: 197 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=142' heldReason: rights - ordinal: 4 text: null startSeconds: 142 endSeconds: 197 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=142' heldReason: rights - ordinal: 5 text: null startSeconds: 335 endSeconds: 346 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=335' heldReason: rights - ordinal: 6 text: null startSeconds: 405 endSeconds: 418 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=405' heldReason: rights - ordinal: 7 text: null startSeconds: 467 endSeconds: 479 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=467' heldReason: rights - ordinal: 8 text: null startSeconds: 557 endSeconds: 624 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=557' heldReason: rights - ordinal: 9 text: null startSeconds: 767 endSeconds: 780 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=767' heldReason: rights - ordinal: 10 text: null startSeconds: 837 endSeconds: 849 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=837' heldReason: rights - ordinal: 11 text: null startSeconds: 946 endSeconds: 1061 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=946' heldReason: rights - ordinal: 12 text: null startSeconds: 1073 endSeconds: 1163 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=1073' heldReason: rights - ordinal: 13 text: null startSeconds: 1173 endSeconds: 1290 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=1173' heldReason: rights - ordinal: 14 text: null startSeconds: 1300 endSeconds: 1433 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=1300' heldReason: rights - ordinal: 15 text: null startSeconds: 1445 endSeconds: 1574 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=1445' heldReason: rights - ordinal: 16 text: null startSeconds: 1585 endSeconds: 1679 watch: 'https://liquidgold.cc/watch/HGfsfKaVuGY?t=1585' heldReason: rights --- # Parsing the Epstein Files for JMail — Palak Agarwal & Omar Alhait, Reducto Handwritten flight logs and heavily redacted PDFs stand between a pile of documents and a searchable product. Palak Agarwal and Omar Alhait show how Reducto turned the Epstein files into structured data for JMail and its related applications. Agarwal introduces the document processing layer; Alhait walks through the extraction pipeline behind JFlights, showing how a schema turns difficult pages into usable records. The workflow starts with parsing, tests extraction results in Studio, and exposes the configured pipeline through an API call or code snippet. The product demonstration makes the bottleneck visible: reading order, handwriting, layout, and inconsistent documents need to survive extraction before an interface can make them useful. A live resume example shows how to generate a JSON schema, upload documents, and inspect the resulting fields. The discussion distinguishes a quick schema from one informed by parsed document content, then explores nested fields, citations, figures, and the choice between OCR and PDF metadata. Alhait also describes why drawing a black box over text can leave information exposed, and how the team handled material intended to remain redacted. Questions move from model training and document specific configurations to practical evaluation: inspect a small sample first, then build a representative benchmark before scaling. The recording ends with instructions for an interactive extraction exercise, connecting the JMail case study to participants' own document workflows. Speaker info: - https://palakagarwal.me/ - https://www.linkedin.com/in/palak06/ - https://www.linkedin.com/in/oalhait - https://github.com/oalhait - https://docs.reducto.ai/overview Timestamps: 0:00 - Document processing and Reducto 2:02 - The JMail case study 3:10 - Omar on the parsing challenge 5:27 - JFlights and handwritten logs 6:35 - Configure and inspect extraction 7:41 - Scaling the document pipeline 9:07 - Deploy an API pipeline 10:14 - Generate a resume schema 12:38 - Schemas informed by document content 13:48 - Redaction and PDF metadata 15:34 - Nested schemas and citations 17:41 - Figures and hybrid OCR 19:23 - Parsing as the foundation 21:30 - Benchmarks and practical evaluation 23:44 - Product design and training data 26:12 - Tailor document configurations 27:59 - Interactive exercise instructions --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/HGfsfKaVuGY-youtube-79b0f112f4cbb4109538 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/parsing-the-epstein-files-for-jmail-palak-agarwal-o-4b05db2c3bdc · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.