01 / Why it feels better
More bounded than chat. More legible than autopilot.
The system does real work, but it never asks the developer to stop caring about scope, review, or authorship.
raw chatunboundedapsararepo-bound
Product View
Runtime / 01—04
See the agent loop as a product, not just a prompt box.
This is the part worth showing. Project-local startup, bounded tools, hidden internals on demand, and a review step before edits land all turn the agent loop into something developers can actually trust.
apsara session
scope / repodiff / readystate / safe
scroll trace04
02 / checkpoint
Approval gate
The developer reviews the diff before meaningful writes touch the repo.
● agent.event
status: "awaiting_review"
03 / checkpoint
Quiet internals
Tool chatter stays hidden until /details is explicitly opened.
● agent.event
status: "details_available"
04 / checkpoint
Legible progress
The workflow surfaces what changed, why it changed, and what still needs a decision.
● agent.event
status: "context_persisted"
Product tone
Calm enough to trust. Clear enough to inspect. Useful enough to keep using.
Human loop
Trust grows when every step has a boundary.
That means workspace scoping, review gates before writes, and internal activity that stays available without taking over the entire interface.
// Review stays in the critical path instead of getting bolted on after the fact.