Observed by Atlas — nobody has proved they control this domain. Is it yours?
CraftCX
OBSERVEDContinuous QA for AI support agents, built on conversation evidence
- FRESHNESS
- 1.00
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 0
- BOT-FILTERED
- FIRST SEEN
- OCT 6
- IN THE FLOW
CraftCX helps Support, Product and Engineering teams learn from the conversations their AI agents handle. It evaluates resolution accuracy, customer effort, and handoff quality, and surfaces recurring customer needs from support conversations. It connects quality findings and customer themes back to the source conversations so teams can inspect evidence and decide what to change.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Every crawl is diffed. Material changes are listed.
Nobody has vouched for CraftCX yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about CraftCX? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it