A guided video lesson

Agentic SDLC at Uber: From Platform Building Blocks to a Managed Software Factory

A source-grounded lesson on Uber's six-layer agent platform and the end-to-end loop it supports: research, design, coding, early validation, CI, review, and maintenance. The central idea is that useful agentic engineering depends less on a lone coding model than on controlled access, relevant context, prepared execution environments, reusable skills, staged evidence, and feedback loops.

Open the complete source

日本語版を読む

Chapter pages

Choose where to begin

  1. 01The Software-Factory Thesis and Operating Baseline0:14 - 1:48
  2. 02Model Gateway: Controlled Model Access at Scale1:48 - 3:48
  3. 03MCP Gateway and Token-Efficient Tool Access3:48 - 5:43
  4. 04Pre-Provisioned Agent Execution Environments5:43 - 6:35
  5. 05DevPods Subcapability: A Unified Multi-Repository Workspace6:35 - 7:12
  6. 06Managed Skills and Their Improvement Lifecycle7:12 - 8:39
  7. 07Context Graphs for Faster, More Predictable Retrieval8:39 - 10:21
  8. 08Packaging the Platform in Cortana10:21 - 11:34
  9. 09From an Idea to Business Research11:34 - 12:32
  10. 10Requirements, Design, and Rapid Prototyping12:32 - 13:18
  11. 11Building with Minion Before CI13:18 - 14:15
  12. 12Densifying Validation into the Inner Loop14:15 - 14:59
  13. 13Self-Healing CI and Evidence-Bearing Code Review14:59 - 15:54
  14. 14Managed Maintenance and Feedback Loops15:54 - 17:16
  15. 15Scale Bottlenecks and the Build-Versus-Should-Build Decision17:16 - 18:22