Support Agent
Answers a client employee's question in seconds, on whichever channel they used, and never states a benefit no policy document backs. Written for an org where the record is the point: every reply carries the passage it came from, every handoff carries the whole conversation, and the only things left for a person are the customers the bot genuinely cannot settle and the articles it wants to answer from next month. Five stations, run as a loop: what station 5 approves is what station 2 answers from.
{{ g.n }}
{{ g.name }} · {{ g.sub }}
{{ g.desc }}
Subagents ({{ g.acount }}) {{ a.name }}{{ a.code }}{{ a.name }}{{ a.auto }}{{ tk }}
{{ g.title }}{{ g.chip }}
{{ tb.name }}
{{ r.tag }} {{ r.name }} {{ r.meta }} {{ r.badge }}
{{ g.footer }}
The workbench · subagents send notes, you make the human calls
SUBAGENTS AT WORK
W
{{ d.ini }}
{{ g.acount }} subagents · 1 agent
SUBAGENT NOTES
{{ nt.ini }}{{ nt.who }} {{ nt.text }}
YOUR TASKS · HUMAN IN THE LOOP
{{ g.t1 }}
{{ g.t2 }}
{{ g.tnote }}
{{ g.btn }}
{{ g.wait }}
YOUR TASKS · NONE AT THIS STEP
{{ g.was }}
{{ g.ev1L }}{{ g.ev1V }}
{{ g.ev2L }}{{ g.ev2V }}
{{ g.ev3L }}{{ g.ev3V }}
✓ Cleared for full autonomy{{ g.sign }}
Put a person back on this step
How to read this map
{{ lg.code }}{{ lg.text }}
A person is in the loop wherever a customer is upset, an identity is being changed, or the bot would teach itself. Two of the five stations refuse to proceed on their own, Escalation Handling and Knowledge Upkeep, and those are the two a person carries. Everywhere else the agents run at volume and reach you only when they cannot settle something.
The loop closes