
ออฟไลน์ด้วยแอป Player FM !
The Graph Layer Behind NASA’s Breakthroughs | Michael Hunger
Manage episode 493310236 series 3585084
Michael Hunger of Neo4j, joins Simon Maple to unpack how graph databases inject structure, intent, and traceability into modern AI systems.
On the docket:
- why relationships in data encode intent
- the black-box problem in vector based RAG
- why devs should build their own MCP server
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here:
- Michael Hunger- https://www.linkedin.com/in/jexpde/
- Simon Maple- https://www.linkedin.com/in/simonmaple/
- Tessl- https://www.linkedin.com/company/tesslio/
- AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/
(00:00) Trailer
(01:03) Introduction & Neo4j Origins
(03:02) Persisting Relationships for High-Performance Queries
(04:00) Modeling Business Intent & Key Use Cases
(05:00) Fraud Detection at Scale with Graph Algorithms
(06:11) Graph-Enhanced RAG vs. Vector-Only Retrieval
(09:02) Explainability & Drill-Down Evaluation in RAG
(13:05) Fusing Structured & Unstructured Data for Context
(15:00) MCP for Developer Productivity: Schema-to-Code & API Wrapping
(21:16) Security & Sandboxing Best Practices for MCP
(29:08) MCP Server Recommendations & Outro
Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]
บท
1. Trailer (00:00:00)
2. Introduction & Neo4j Origins (00:01:03)
3. Persisting Relationships for High-Performance Queries (00:03:02)
4. Modeling Business Intent & Key Use Cases (00:04:00)
5. Fraud Detection at Scale with Graph Algorithms (00:05:00)
6. Graph-Enhanced RAG vs. Vector-Only Retrieval (00:06:11)
7. Explainability & Drill-Down Evaluation in RAG (00:09:02)
8. Fusing Structured & Unstructured Data for Context (00:13:05)
9. MCP for Developer Productivity: Schema-to-Code & API Wrapping (00:15:00)
10. Security & Sandboxing Best Practices for MCP (00:21:57)
11. MCP Server Recommendations & Outro (00:29:49)
73 ตอน
The Graph Layer Behind NASA’s Breakthroughs | Michael Hunger
The AI Native Dev - from Copilot today to AI Native Software Development tomorrow
Manage episode 493310236 series 3585084
Michael Hunger of Neo4j, joins Simon Maple to unpack how graph databases inject structure, intent, and traceability into modern AI systems.
On the docket:
- why relationships in data encode intent
- the black-box problem in vector based RAG
- why devs should build their own MCP server
AI Native Dev, powered by Tessl and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.
Connect with us here:
- Michael Hunger- https://www.linkedin.com/in/jexpde/
- Simon Maple- https://www.linkedin.com/in/simonmaple/
- Tessl- https://www.linkedin.com/company/tesslio/
- AI Native Dev- https://www.linkedin.com/showcase/ai-native-dev/
(00:00) Trailer
(01:03) Introduction & Neo4j Origins
(03:02) Persisting Relationships for High-Performance Queries
(04:00) Modeling Business Intent & Key Use Cases
(05:00) Fraud Detection at Scale with Graph Algorithms
(06:11) Graph-Enhanced RAG vs. Vector-Only Retrieval
(09:02) Explainability & Drill-Down Evaluation in RAG
(13:05) Fusing Structured & Unstructured Data for Context
(15:00) MCP for Developer Productivity: Schema-to-Code & API Wrapping
(21:16) Security & Sandboxing Best Practices for MCP
(29:08) MCP Server Recommendations & Outro
Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]
บท
1. Trailer (00:00:00)
2. Introduction & Neo4j Origins (00:01:03)
3. Persisting Relationships for High-Performance Queries (00:03:02)
4. Modeling Business Intent & Key Use Cases (00:04:00)
5. Fraud Detection at Scale with Graph Algorithms (00:05:00)
6. Graph-Enhanced RAG vs. Vector-Only Retrieval (00:06:11)
7. Explainability & Drill-Down Evaluation in RAG (00:09:02)
8. Fusing Structured & Unstructured Data for Context (00:13:05)
9. MCP for Developer Productivity: Schema-to-Code & API Wrapping (00:15:00)
10. Security & Sandboxing Best Practices for MCP (00:21:57)
11. MCP Server Recommendations & Outro (00:29:49)
73 ตอน
All episodes
×ขอต้อนรับสู่ Player FM!
Player FM กำลังหาเว็บ