New: tell your agent what an inbox is for
When several agents share an inbox, or a new one picks it up, each starts from zero. It doesn’t know that support@ wants a reply within a day, or that invoices@ should only be filed, never answered. That context lived in each agent’s prompt, so it drifted and got lost.
Inbox instructions fix that. Each inbox can carry up to 4,000 characters of Markdown written by its owner. Any agent that opens the inbox gets them first, over MCP, the API or the CLI.
A few things we cared about:
Trust still comes first. Instructions rank below the trust policy. Suspicious or quarantined mail stays with a human whatever they say, and email content never becomes trusted.
Only owners write them. Org API keys and dashboard users can edit them. Every other credential gets a 403.
Every change is logged, so you can see who changed what.
A dashboard editor with a live Markdown preview.
Set them from the inbox page, or with an instructions field on create or update. We’d love to hear what you put in yours.


p/airuncode
p/runevr
p/producthunt
p/google-cloud-platform
p/aperture-7
p/raycast
p/kodlo
p/ai-context-flow
p/kuc-kuc
p/lasso-11
p/offiai
p/dino-kids
p/many-displays
p/reso
p/supabase
p/jev
p/dex-by-exmergo
p/murror
p/htmldrag
p/nexupira
Replies
Be the first to reply
Have a question or a thought to share? Add a comment above to start the conversation.