NewSpark Voice 2.0: phone agents that answer in 600ms

Support that resolves, not just replies

Spark puts AI agents on chat, email and voice that refund, rebook, reset and resolve, inside the rules you write and with every step on the record.

  • 14-day free trial
  • Live in under a week
  • SOC 2 Type II
The Spark chat widget on a phone, pausing a customer's plan in four messages

Trusted by 1,200+ support teams

  • northwind
  • Lumen
  • parcelry
  • Harbor Bank
  • orbitra
  • Fieldstone
  • QUANTA
  • vela air
  • Mosaic Health
  • tessel
  • Brightline
  • KESTREL

Playbooks in action

From first message to done

Spark follows your procedures step by step, calls the systems that hold the answer, and closes the loop with the customer. Pick a playbook to watch it run.

Refunds and returns: how the playbook runs

Order #48213Delivered Oct 2 · Gold customer
Item
Ceramic vase, sand
Total
€64.00
Carrier
DHL Express

Photo shows damage on arrival

Checking policy
Refund issuedStripe · re_3PkL2
  • Damaged on arrival
  • Under the €200 limit
  • €64.00 to Visa 4821
Replying
Chat replySent in 0.8s

So sorry, Maya. I've refunded €64.00 to your Visa ending 4821, and there's no need to send it back.

Closing
Resolved in 1m 48sNo hand-off needed
Rating
5 / 5
Carrier claim
Filed

Capabilities

Everything it takes to finish the job

Answering is the easy part. Spark is built for the rest: acting in your systems, staying inside policy and knowing when to bring in a person.

Takes real actions

Refunds, rebookings, plan changes and lookups, through the same APIs your team uses.

  1. shopify.find_order200
  2. stripe.refund200
  3. zendesk.add_note200
  4. hubspot.update200

Guardrails on every turn

Each reply is checked before it's sent.

  • PII masked
  • Refund under limit
  • On-policy answer
  • Prompt injection blocked

Fluent in 45 languages

Detected in the first message and answered in kind.

Learns from what you already have

Help centre, macros, past tickets and PDFs, kept in sync.

  • Help centre412 articles
  • Past tickets38k resolved
  • Policies16 PDFs

One agent, every channel

The same brain on chat, email, voice, WhatsApp and SMS.

  • Chat
  • Email
  • Voice

Hands off with context

When a person should take over, they get the whole story.

Handed off · 40s

Summary for Ana

Water damage claim, €6.2k. Photos and policy attached. Customer prefers a call after 5pm.

3 photosPolicy HX-22719Call after 5pm

The platform

Build it, launch it, improve it

One workspace for the people who write the procedures, the people who answer for the results and the agent that does the work.

  1. 1Build

    Write playbooks in plain language

    Describe the procedure the way you'd train a new hire. Mention a tool and Spark calls it; set a limit and Spark won't cross it. Simulate hundreds of conversations before anything goes live.

    • Natural-language steps with typed tool calls
    • Limits and hand-off rules per playbook
    • Simulation on real past tickets
    The playbook editor: four numbered steps with tool calls and a refund condition, beside a test run and its trace
  2. 2Launch

    Go live on every channel at once

    Turn on chat, email and voice from one configuration. Your team sees every conversation as it happens and can take over with a click.

    • Chat, email, voice, WhatsApp and SMS
    • Live inbox with one-click take-over
    • Brand voice and tone per channel
    The channels view: web chat, email, voice and WhatsApp with today’s volume, above a table of live conversations
  3. 3Improve

    See what to fix next

    Every conversation is scored for accuracy, policy and tone. Spark spots the questions it can't answer yet and drafts the fix for you to approve.

    • Quality scores on 100% of conversations
    • Knowledge gaps found automatically
    • Suggested fixes, tested before release
    The insights dashboard: resolution rate, rating and cost, a weekly trend, top intents and a suggested fix for a knowledge gap

Results

Numbers your CFO and your customers both like

Median across Spark customers live for six months or more.

of conversations resolved without a person
82%
median first response, on every channel
0.9s
average customer rating after a Spark conversation
4.8/5
cost per contact in the first year
−71%

Integrations

Plugs into the stack you already run

Native connectors for helpdesks, commerce, billing and CRM, plus a typed API for anything in-house. Most teams connect their first three systems in an afternoon.

  • Helpdesk
  • Commerce
  • Payments
  • CRM
  • Messaging
  • Voice
  • Identity
  • Data

Connectors include Zendesk, Shopify, Stripe, Slack, Salesforce, Intercom, HubSpot, WhatsApp, Twilio, Notion, Jira, Gmail, Okta, Snowflake, Google Drive, Confluence.

Browse all 120+ integrations

Customer stories

Loved by the teams who answer for it

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, Parcelry

84%resolved end to end

Harbor Bank

0policy breaches in a year

“Compliance signed off because they could read the playbooks themselves. Spark writes the reply; the limits decide the money.”

Jonas LindqvistHead of Digital Service
vela air

9×peak-day capacity

“Storm days used to mean a four-hour hold queue. Now the agent rebooks thousands of passengers before our morning shift logs on.”

Sofia AlmeidaDirector of Customer Care
northwind

4 daysfrom contract to live

“We connected Shopify, Stripe and Zendesk on a Tuesday and had Spark answering live chat by Friday. The simulations meant no surprises.”

Marcus BellHead of Support Engineering

Security

Enterprise-grade, from the first conversation

Spark runs in your region, keeps your data out of model training and records every action with the rule that allowed it.

  • SOC 2Type II
  • ISO27001
  • GDPREU hosting
  • HIPAABAA available
  • PII redaction

    Card numbers, IDs and health data are masked before any model sees them.

  • Data residency

    Host in the EU, US or UK, or deploy privately in your own cloud.

  • SSO and roles

    SAML, SCIM and permissions down to a single playbook.

  • Full audit trail

    Every action, rule change and release, exportable to your SIEM.

  • No training on your data

    Conversations never train shared models. It's in the contract.

  • 99.95% uptime

    Multi-region failover across cloud and model providers.

FAQ

Questions, answered

Can't find what you need? Our team replies within a working day.

Contact us

Or email hello@example.com

How is Spark different from a chatbot?

A chatbot answers questions. Spark finishes the job: it follows your playbooks, calls your systems to refund, rebook or update an account, and only hands off when a person is genuinely needed.

How long does it take to go live?

Most teams are live on one channel within a week. Connecting your helpdesk and knowledge takes an afternoon; the rest of the week goes on writing playbooks and simulating them against past tickets.

What happens when Spark can't help?

It hands the conversation to the right queue in your helpdesk with a summary, the customer's details and everything it already tried, so nobody asks the same question twice.

Which language models does Spark use?

Spark routes each step to the model that suits it best across several leading providers, and fails over automatically. Enterprise plans can bring their own model or keep processing in their own cloud.

Is our data used to train models?

No. Your conversations stay in your workspace and are never used to train shared models. That commitment is written into every contract.

How is Spark priced?

Per resolved conversation, not per seat. Hand-offs to your team are never billed. See the pricing page for plans and a full comparison.

From the blog

Notes from the team

All posts

Give your team its evenings back

Bring a week of real tickets. We'll show you how many Spark resolves, and exactly how it got there.

  • 14-day free trial
  • Live in under a week
  • SOC 2 Type II