使用Player FM应用程序离线!
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]
章节
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)
83集单集
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]
章节
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)
83集单集
Alle episoder
×欢迎使用Player FM
Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。