--- title: "Reconstructed Slides: Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior" category: "slides" video_id: "MRM7oA3JsFs" sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"] --- # Reconstructed Slides: Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior ## Source Video [Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior](https://www.youtube.com/watch?v=MRM7oA3JsFs) ## Method This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck. ## Reconstructed Slides ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-002.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-002.html) - AI slide classifier: `content_slide` confidence `0.91` - Text source: agent_vision. Slide text: > Own your vertical: A playbook for building a domain-native LLM application > Dr Christopher Lovejoy, MD > Head of Clinical AI > 2025-06-04 > Anterior ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-003.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-003.html) - AI slide classifier: `content_slide` confidence `0.93` - Text source: advanced OCR `rapidocr-live/left-72/contrast`. - OCR decision: ready — small body text and logos are better handled by OCR Slide text: > Anterior > Were a New York-based, clinician-led > AIE reasoning tools andsolutions to accelerate andautomatehealthcare company thatprovides clinical > administration > BACKEDBY NEA SEQUOIA > andFOUNDERSOF > DoosMad GoogleAi > Google ALUMRECE mMeta > Microsoft amazon MeKnecy &Company > IMPERIAL NHS > aws ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-004.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-004.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > OUR BET FOR VERTICAL AI APPLICATIONS: system for incorporating domain insights > the sophistication of your models and pipelines ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-005.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-005.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > Why is it hard to successfully apply LLMs to specialized industries? ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-006.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-006.html) - AI slide classifier: `content_slide` confidence `0.95` - Text source: advanced OCR `rapidocr-live/left-72/contrast`. - OCR decision: ready — small case details and question text are better handled by OCR Slide text: > An example clinical case processed by Florence > AIE Doctor recommends a knee arthroscopy Presents with right knee pain 78-year-old female > Q: Is there documentation of unsu > conservative therapy for at least 6 > Microsoft ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-007.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-007.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > KLAS CASE STUDY > We achieved a baseline performance of 95% for approving care... > 95.73% ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-008.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-008.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > KLAS CASE STUDY > We achieved a baseline performance of 95% for approving care... > then iterated with a specific customer to >99% within 8 weeks > 95.73% > 99.24% ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-009.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-009.html) - AI slide classifier: `content_slide` confidence `0.96` - Text source: advanced OCR `rapidocr-live/left-72/contrast`. - OCR decision: ready — Dense diagram labels and small node text are better suited for OCR than direct transcription. Slide text: > AIE maintain a failure mode ontology (2) Empower domain experts to define citraetion Photo ortastion Tae > 1ozruoievy location > Handuriting ertraction Medealrecord extract'on > extraction checkbox Medical Necessity Review Failure Modes reasontg > chrorolog' > mtereretotion Rles > Ruhe courct > seeetion > Microsoft ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-010.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-010.html) - AI slide classifier: `content_slide` confidence `0.95` - Text source: advanced OCR `rapidocr-live/bright-screen/contrast`. - OCR decision: ready — The slide contains a product screenshot with dense small UI text that OCR can extract more reliably than direct vision transcription. Slide text: > (3) Measure metrics and failure modes together > AIE on production data to unlocktargeted insights > ToooTe > Fax > Microsoft smol 3i ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-011.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-011.html) - AI slide classifier: `content_slide` confidence `0.94` - Text source: advanced OCR `rapidocr-live/bright-screen/contrast`. - OCR decision: ready — Flowchart-style slide with many small labels and arrows is OCR-suitable. Slide text: > AIE > MEASURE Review AI outouts AralyTe perfornarce to prioritise work Specify failure mode' to fix and perforrance threshold Make changes > opplcation Producton Perfornance insights ChnicaPx engineer(s) Chnico! enginear(s) AI datoset'eval "Failure mode > about naking Iive Make decisions Subnit inproverents See inpact of changes > aws > S ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-012.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-012.html) - AI slide classifier: `content_slide` confidence `0.97` - Text source: agent_vision. Slide text: > Failure mode datasets enable targeted product iteration ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-013.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-013.html) - AI slide classifier: `content_slide` confidence `0.97` - Text source: advanced OCR `rapidocr-live/bright-screen/contrast`. - OCR decision: ready — Dense diagram slide with multiple small labels and arrows; OCR is likely better than manual transcription here. Slide text: > Empower your domain experts to make > AIE improvements directly with tooling and evals Application Pipelines > P45366 deternie vhether to make live Ewlate to > changes > domain cxperts Tooling for of releunt donin Reatns retreunl baocdedge Domain evals > Lonain deternine Vhether Mgoo Evohiate to > to pipebnes > Knowdedae Base uIOwOq > Microsoft smol ai ![[assets/reconstructed-slides/MRM7oA3JsFs/slide-015.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/MRM7oA3JsFs/slide-015.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > Takeaways > To build domain-native LLM applications you need to solve the last mile problem. > Using the best models isn't enough - you should build an adaptive domain intelligence engine. > Domain experts power this system by reviewing AI outputs to generate performance metrics, failure modes and suggested improvements. > This takes production data and uses it to give your LLM product a nuanced understanding of customer workflows. > The result is a self-improving, data-driven process that can be managed by a domain expert PM. ### Hidden Non-Slide Evidence - [`slide-001.jpg`](/assets/reconstructed-slides/MRM7oA3JsFs/slide-001.jpg) — `sponsor_logo` confidence `0.99`; sponsor/logo wall, not a presentation slide - [`slide-014.jpg`](/assets/reconstructed-slides/MRM7oA3JsFs/slide-014.jpg) — `title_card` confidence `0.99`; Section divider / title-only slide with no substantive content. - [`slide-016.jpg`](/assets/reconstructed-slides/MRM7oA3JsFs/slide-016.jpg) — `title_card` confidence `0.94`; Closing thank-you/contact slide. Classification audit: `raw/sources/slide-ai-classification/reconstructed/MRM7oA3JsFs/audit.json`