Excited to be speaking at Modal Runtime alongside an insanely stacked group of speakers!
Will be talking about how we're making agents on faster, cheaper, and more reliable using @modal!
If you’re wondering how Jev is scaling to meet insane demand they could not possibly have predicted, the answer appears to be @modal — one of only 4 subprocessors listed on
Alright I think I'm excited to ship "natural language triggers" for
Lets you pipe a super high-volume triggers (Slack messages, Datadog alerts, etc) into a natural language filter powered by Jev, that then dispatches the right agent/model/sandbox
No one wants to admit this – because doing it by hand is tedious – but models are also bad at writing prompts.
Models today use prompting "best practices" from 6-12 months ago.
We're launching @niteshiftdev – the full-stack cloud for coding agents
Verification is the new bottleneck.
Software teams can now define their dev environment and verification tools once. Then run any frontier agent in the cloud: Claude Code, Codex, or OpenCode