AI booking assistant

Pilot · Augusta Labs

Four siloed systems, one human-approved offer.

3t Global trains offshore and industrial crews. Coordinators re-key every booking across four systems that share no IDs. This assistant reads them all and drafts dated, prerequisite-checked offers — a coordinator approves every send and every booking.

I built the intake that turns two request sources into one case shape, the prerequisite engine — rule checks plus an LLM reader whose every point must quote the source text — e-learning routing, and the whole certificate-expiry agent, including a port of the legacy SQL procedure that reproduces its output row for row.

Piloting on live requests; writes to 3t’s systems stay held back until a person releases them.

of pilot cases (714 of 855) needed no human read of prerequisite text
83%
expiry pickup, down from a 19–36-day cycle
Daily
rows matched when porting the legacy procedure
43 / 43

How it works

Certificate-expiry agent
  1. daily sweep
    • legacy TMSported SQL procedure
    • training platformexpiries export
  3. groupone case per delegate
  4. refresher resolverfrom prerequisite rules
    • already handled?bookings · newer certs
    • prerequisite check
  6. dates before expirylast 90 days first
  7. coordinator gate
Request pipeline
    • legacy TMSrequest forms
    • training platformrequest export
  2. intake & dedupeone case shape
    • course resolver
    • e-learning router
  4. prerequisite readerLLM, quote-verified
  5. date searchlive runs
  6. draft reply
  7. coordinator gate