AI Agents Have the Microservices Tax, Only Worse
Episode eight, with Jason Patel: exited CTO of Ensighten, now building his own side project in Chicago, and someone Matt knows from enterprise engineering. A skeptical, experienced-engineer look at the AI rush: always-on agent servers versus a Lambda and a few API calls, why multi-agent orchestration pays the same tax as microservices, whether small businesses can really afford AI enablement agencies, and Jason's case that a lot of it is just standard automation. Plus the Claude Code fix that cleared one failing Docker pull and left another one further down the same script.
Episode eight, with Jason Patel: exited CTO of Ensighten, now building his own side project in Chicago. A skeptical, experienced-engineer look at the AI rush.
What we talked about:
- 0:00 Meet Jason Patel, exited CTO of Ensighten
- 1:35 Always-on agent servers vs. a Lambda and a few API calls
- 5:23 Multi-agent orchestration frameworks: where’s the benefit?
- 8:45 A new framework every week, like early Node.js
- 10:07 Agents pay the same tax as microservices
- 13:50 AI math proofs and the demand for people who validate
- 15:51 AI enablement agencies
- 20:11 Can a small business afford an AI retainer?
- 24:16 Do you really need AI, or just automation?
- 33:44 Where AI adoption goes from here
- 39:36 Will AI really automate 90% of white-collar work?
- 41:45 Where AI coding falls apart
- 42:36 Claude Code fixed one pull and missed the other
- 45:37 Memory files, harnesses, and keeping it simple
Mentioned in this episode: