Every order question resolved before it becomes a ticket

Where is my order, can I return it, does it come in blue. Spark answers with live order and stock data, and issues refunds and exchanges inside the rules you set.

Get a demoSee the playbook
The atrium of a bright shopping mall, with shopfronts on several floors
of contacts resolved without an agent
78%
cost per contact in the first quarter
−41%
median reply on chat
0.6s
from contract to live traffic
4 wks

The conversations that fill an e-commerce queue

Seven intents make up almost every e-commerce contact. Each one maps to a playbook that ships with the commerce pack, and you can change any of them.

  • Where is my order“It said Tuesday and it is Thursday”34% of contacts92% resolvedOrder status
  • Returns and exchanges“Can I swap this for a medium?”21% of contacts81% resolvedReturns
  • Product questions“Is the jacket waterproof or just resistant?”15% of contacts88% resolvedCatalogue answers
  • Delivery changes“Can you leave it with a neighbour?”11% of contacts74% resolvedDelivery update
  • Payments and promo codes“My discount code did not apply”9% of contacts69% resolvedPayment check
  • Account and loyalty“Where did my points go?”6% of contacts77% resolvedAccount lookup
  • Everything else“Complaints, press, the unexpected”4% of contactsTo a person resolvedHand-off

Spark writes the reply. The playbook moves the money.

Returns run as steps you can read. Spark understands the customer and writes in your voice, but whether a refund is allowed is decided by a rule, every time.

  • Return windows, final-sale items and refund limits set per market
  • Exchanges checked against live stock before they are offered
  • Labels created with your carrier, refund released on first scan
  • Anything outside policy handed to a person with the case attached
A woman packing an order into a cardboard box beside a rail of colourful shirts

Customer: The jacket is a bit small. Can I swap it for a medium?

Exchange placedInside the window, medium in stock

Black Friday without the hold queue

Contacts tripled across peak week at one fashion retailer. The agent took the extra volume and the support team stayed the size it was in October.

19,600contacts on Cyber Monday, 82% resolved by the agent

  • All contacts
  • Handed to a person
Contacts per day across peak week
DayContactsHanded to a person
Nov 216,2001,400
Nov 225,8001,300
Nov 237,1001,600
Nov 248,4001,800
Nov 259,9002,100
Nov 2611,6002,300
Nov 27, Black Friday18,9003,400
Nov 2816,2003,000
Nov 2914,1002,700
Nov 30, Cyber Monday19,6003,600
Dec 115,3002,900
Dec 212,2002,400
Dec 310,1002,100
Dec 48,7001,900

Connected to the systems that hold the answers

The commerce pack comes with connectors for the usual stack. Each one lists exactly what the agent can read and what it is allowed to change.

Storefront
Reads Catalogue, prices, stock by size
Writes Nothing
Order management
Reads Orders, fulfilment, tracking
Writes Delivery notes, exchanges
Payments
Reads Charges and refund status
Writes Refunds inside policy
Returns portal
Reads Open returns and labels
Writes New returns, labels
Loyalty
Reads Points, tier, history
Writes Goodwill points, capped
Helpdesk
Reads Past tickets
Writes Hand-offs with a summary
Portrait of Priya Raman
parcelry
“We expected Spark to deflect the easy tickets. It ended up closing refunds and delivery changes end to end, and our team finally has time for the conversations that need a person.”
Priya RamanVP Customer Operations, Parcelry84%resolved end to end

E-commerce FAQ

Questions commerce teams ask

Contact us

Or email hello@example.com

Which commerce platforms does Spark connect to?

The major hosted storefronts and order management systems have ready-made connectors. Anything with an API can be added as a custom connector in a day or two, with the same read and write permissions as the built-in ones.

Can the agent issue refunds on its own?

Only inside the rules you write. Refund limits, return windows and final-sale exclusions are fixed steps in the returns playbook, so Spark can never talk itself into a refund the policy does not allow.

How does it handle peak season?

The agent scales with traffic, so there is no queue to join. Most teams also add peak-only rules, such as extended return windows, and switch them on and off by date.

Does it answer product questions from our catalogue?

Yes. The catalogue, size guides and care instructions sync from your storefront and help centre, and stock is checked live before anything is recommended.

Put Spark on your busiest queue

Send us a month of transcripts and we will show you which conversations an agent could have finished, and how.

Get a demoSee pricing