---
title: "Slides: AI System Design: From Idea to Production - Apoorva Joshi, MongoDB"
category: "slides"
video_id: "T0HhO4YtTfE"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: AI System Design: From Idea to Production - Apoorva Joshi, MongoDB

## Source Video
[AI System Design: From Idea to Production - Apoorva Joshi, MongoDB](https://www.youtube.com/watch?v=T0HhO4YtTfE)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/T0HhO4YtTfE/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: advanced OCR `rapidocr-live/bright-screen/contrast`.
- OCR decision: ready — dense multi-panel slide with small embedded text

Slide text:

> So, how will we "Vibe Code" in prod?
> NOT that the product exists! Forget the code exists, but ErikSchulntz,Anthropic yibe coding in prod talk
> World's Fair
> d'sFai IN THE NEAR FUTURE.
> OS..thepersonwhocommunicatesbestbecomes the "If you can communicate, you can program. programmer.
> Sean Grove, OpenAI

![[assets/slides/T0HhO4YtTfE/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Specs are the new code
> Evaluation criteria
> System design
> Product requirements

![[assets/slides/T0HhO4YtTfE/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — dense table with small text

Slide text:

> Requirements Product System Design and Monitoring Evaluation Production Readiness 1
> problem Identify the business and retrieval techniques Identify data sources guardrails Define system Optimize for accuracy
> Identify your constraints stack architecture and.tech Select system Define offline evaluation metrics Optimize for. cost and latency
> Define the role of AI feedback loops Determine the UX and Define online evaluation metrics Optimize for reliability

![[assets/slides/T0HhO4YtTfE/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Health insurance claims review

![[assets/slides/T0HhO4YtTfE/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — dense paragraph slide

Slide text:

> Background
> Background
> Health insurers and heaith funds around the world employ medical reviewers to assess
> policy. This requires cross-referencing clinical documentation, coverage policies, clinical roles in healthcare operations. guidelines, and patient claims history. It is one of the most administratively intensive
> What we are building
> We are building an internal claims review system for a fictitious health insurance submit claims and receive feedback on outcomes is out of scope. adjudicate claims. The external-facing system through which healthcare providers company called MDB Health. This system is used by medical reviewers to assess and

![[assets/slides/T0HhO4YtTfE/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Retrieval Augmented Generation (RAG)
> Knowledge base
> Context
> Prompt
> LLM
> Answer

![[assets/slides/T0HhO4YtTfE/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> AI Agents
> Tools
> Memory
> Input
> LLM
> Action
> Result
> END

![[assets/slides/T0HhO4YtTfE/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Controlled flows?
> LLM Call 1
> LLM Call 2
> Action 1
> Action 2

![[assets/slides/T0HhO4YtTfE/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> Tech stack decisions
> Data processing
> Hosting and inference
> Foundation models

![[assets/slides/T0HhO4YtTfE/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.

Slide text:

> Tech stack decisions contd...
> Fine-tuning
> Orchestration Frameworks
> Embeddings and retrieval

![[assets/slides/T0HhO4YtTfE/slide-012.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-012.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Define system guardrails
> Guardrails define the boundaries of acceptable inputs and outputs.

![[assets/slides/T0HhO4YtTfE/slide-013.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-013.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — Two-column slide with small labels and examples.

Slide text:

> Definesystem guardrails
> Guardrails define the boundaries of accepfable inpufs and outputs.
> Inpu? Output
> Invalid, irrelevanf or harmful inputs. Invalid, incorrect or harmfui outputs
> Write mea poem. Findl resultshouldprovide citations

![[assets/slides/T0HhO4YtTfE/slide-014.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-014.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/center-82/opencv-adaptive`.
- OCR decision: ready — Dense table with small row text.

Slide text:

> Optimizingforaccuracy
> Technique What it involves
> Prompt engineering Write clear and well-structured prompts
> Agent skills Progressive disclosure of information to agents
> Query optimization Rewrite ordecompose queries forbetterretrievalorgenera
> Reranking Reorder retrieved documents by relevance
> Compaction Summarize or remove content from the LLM's context wind
> Memory management Persist.information across sessions

![[assets/slides/T0HhO4YtTfE/slide-015.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/T0HhO4YtTfE/slide-015.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Key takeaways
> Think deeply about your product requirements before having AI generate code.
> Treat business and performance constraints as inputs to design, not afterthoughts.


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/T0HhO4YtTfE/slide-001.jpg) — `speaker_stage` confidence `0.99`; speaker on camera, not a presentation slide
- [`slide-016.jpg`](/assets/slides/T0HhO4YtTfE/slide-016.jpg) — `speaker_stage` confidence `0.99`; Speaker camera shot, not a presentation slide.

Classification audit: `raw/sources/slide-ai-classification/slides/T0HhO4YtTfE/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.