If you do:
- What's the setup: two humans + one agent, or two humans + two agents
- What do you actually pair on?
- Do you find it more (or less) valuable than before?
- And many more questions...
I encourage my teams to pair as often as possible. Usually the format is "two humans, as many agents as necessary". From what I've seen the outcomes are better than anything one human could do, and faster. I have no real data to prove that though.
source & further reading
news.ycombinator.com — original article
Ask HN: Would you pay for an AI API that guarantees zero prompt retention?
PaaS IaaS GaaS all in one. And 2 AI <compound> models
Taalas API Anyone?