References:
Block’s “From Hierarchy to Intelligence”: block.xyz/inside/from-hierar…
Ramp’s Glass post: xitter.cf/eglyman/status/2043362…
99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone.
so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350+ reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive.
the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.
Peak AI agent management:
I asked my current Product COO agent to write the onboarding prompt for its replacement because it had become too confused.
The first line:
“The previous Product COO was fired today for not knowing how the product actually works after weeks in the seat. Don’t repeat that.”
😂
Did Claude Code regress? Today it feels like the version from months ago - less mature logic, weaker reasoning, and much harder to work with. (╯°□°)╯︵ ┻━┻
@AnthropicAI @claudeai
5/5
If you want to try it + tell me what’s missing for you:
apps.apple.com/us/app/health…
(You can also tell the coach “send feedback to the team” and it’ll send it to me :) )
(Wellness guidance, not medical advice.)
Train. Fail. Repeat. Upgrade. 🤖
Practice makes perfect - for robots, too.












