Every support team retypes the same answers all day, and the macro library never keeps up because writing macros is its own chore that always gets deprioritized.
sonnet4 daysZendeskOpenAIGoogle Sheets
Claude
83ROI
70Scale
$4.2k93Saved
ROI for
README.md
Why this subagent
Every support team retypes the same answers all day, and the macro library never keeps up because writing macros is its own chore that always gets deprioritized.
This agent reads resolved tickets, finds the answers agents keep writing by hand, and drafts ready-to-use macros for the lead to approve. Each one comes with a suggested trigger and title, so adding it is a yes-or-no decision instead of a writing task. The macro library finally reflects what your team actually says, and the repetitive typing drops off.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Group near-identical answers and detect the questions that trigger them.
pending
Draft a reusable macro for each recurring answer with a suggested trigger and title.
pending
Send the proposed macros for a lead to approve before they go into the help desk.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
From resolved tickets, cluster repeated agent replies and return draft macros with a title, trigger condition, and the canonical answer text.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.