The Cognition team released an article describing the challenges of building an in-house AI agent.
A big challenge is ensuring your agent can complete real work. Securely and at scale. That requires proper isolation and running agents in specialized machines.
The good news: if you run your agents on @e2b, you get over three years of work on this problem out of the box. Hard won lessons and integrated into your agent in an afternoon.
$NOW CEO on how companies are funding AI:
"What I'll tell you is that from a budget perspective, we're seeing it come from a lot of different places, right? It's not one place. A lot of people are funding it because labor budgets are coming down. A lot of people are reallocating technology spend and eliminating more point solutions and really leaning into platform consolidation and platforms like ServiceNow"
the question I keep coming back to w/NOW is why will ticketing workflows existing in like 10yrs? they mostly solve for humans being a bottleneck to complete menial tasks.
Given Anthropic's reported limitations on inference, it's pretty straightforward to imagine them competing directly with their API customers for the rest of 2026. OpenAI and Google could gain meaningful ecosystem share.