The Pushary blog
Engineering
How Pushary is built: delivery, policy, and the human in the loop.
Your agent retried. Your customer should not have to approve twice.
Give the operation a stable identity, save the decision, and resume from the answer. A practical example of the part that comes after sending an approval request.
Approve refunds over $500: the four things that decide whether a threshold holds
Picking the number is the easy part. Rule ordering, a missing field, a numeric string, and a retry are the four places a threshold leaks.
Build vs buy: the real cost of a human-in-the-loop approval loop
The prototype takes a weekend. The system that will not silently approve a refund takes a quarter. An honest itemization, including when building is right.
Fail-closed by default: why agent approvals should block instead of fire and forget
The failure case for approvals is not exotic. It is a phone in a pocket. Fail-closed design decides in advance that the ordinary case means stop.
The gap between notifying a human and getting a decision back
Both start with a push message. The difference is everything after the tap, and it is the difference between an agent that announced and an agent that asked.
Stop making your agent ask permission for everything. Or nothing.
Reads run free. The irreversible slice is small, and it is the only thing that should be allowed to interrupt you.
Claude Code hooks explained: PreToolUse, PostToolUse, and Stop
All 33 hook events in one table, the JSON each one receives, the exact output fields, and how PreToolUse blocks a tool call before it runs.
Let your agents work. Stay in control.
Get the questions that need you on your phone or Mac. Approve, reject, or answer so your agent knows what to do next.