Skip to content
aiva
  • Product
  • Languages
  • Customers
  • Pricing
Sign inStart free
Product›Languages›Customers›Pricing›Start free
Already have an account? Sign in →

Ready when your customers are.

Start free, live in under four minutes. Or get a walkthrough in your inbox.

aiva

AI that answers every call, chat and text — in every Indian language.

All systems answering

Product

  • Voice
  • Web widget
  • SMS
  • Analytics
  • Integrations
  • Solutions

Company

  • Customers
  • About
  • Careers
  • Contact

Resources

  • Help center
  • Changelog
  • Status
  • Book a demo
  • Pricing

Legal

  • Privacy
  • Terms
  • DPA
  • GDPR
  • Cookies
  • Sub-processors
  • Security
© 2026 AIVA Technologies Pvt. Ltd.·Made with care in Rajkot, answering in 12 languages.
‹ All customer stories
FeaturedSaaS · developer tools·Bengaluru, India·62 employees·Since 2025·5 min read
V
Vellum
Workflow automation for engineering teams · 1,800 paying companies · Series A

How Vellum runs 2,400 customer conversations a day — and retired the support on-call rotation.

Vellum sells workflow automation to engineering teams — meaning their customers are engineers, their bugs are intricate, and their support load is technical. They embedded AIVA directly into their product. Six months later, the entire on-call rotation got shut down.

Monthly spend
~₹19,999/mo
Channels
Web + embed
Time to live
1 afternoon
Embedded in
The product itself
“

We embedded AIVA inside the workflow editor itself. When an engineer hits a wall, AIVA is right there — with access to their actual workflow, their actual error, their actual logs.

P
Priya Subramanian
Head of Product · Vellum

The challenge

Support for engineers is a different beast.

Vellum's customers ship production workflows that touch payment APIs, internal systems, and live data pipes. When something breaks, they're not asking where the unsubscribe button is — they're pasting stack traces, JSON payloads, and asking why a webhook fired twice.

Generic chat widgets are useless here. By the time a customer has explained the context, a senior engineer has already lost 20 minutes. And every reply requires reading their workflow first.

Until mid-2025, Vellum had four engineers on a rotating on-call schedule, splitting the support inbox alongside their day job. Average first response: 47 minutes. Worst-case: 14 hours overnight. And growing.

Before AIVA · what wasn't working
1

4 engineers on rotation, each losing ~6 hours/week to support triage.

2

Tickets were technically rich — workflow JSON, error traces, account state — but had to be reconstructed by hand every time.

3

47-minute median first response. Customers either gave up or posted in the public Slack.

4

Generic chatbots couldn't see the workflow — they'd just hand off immediately, defeating the point.

The setup

An afternoon. In-product.

The Vellum team didn't want a chat bubble in the corner. They wanted AIVA to live inside the workflow editor — same surface the customer was already looking at, with full access to the workflow definition and recent execution logs.

AIVA's in-product embed made this trivial. Their senior engineer wrote a 40-line integration that (a) embeds the AIVA pane next to the editor, (b) passes the active workflow JSON as context, and (c) wires three custom tools: fetchWorkflowLogs,retryExecution, and escalateToHuman.

From clone to demo: one afternoon. They piloted internally for two days, then rolled to 5% of customers, then 100% within a week. The team picked the model and escalation rules; AIVA handled the rest.

What they deployed
Web embedIn-product embed · custom tools · streamingAnalyticsResolution rate · escalation patterns
How it rolled out
WED · morning
Set up the in-product embed; wired workflow context
WED · afternoon
Three custom tools shipped; first internal demo
THU · all day
Internal dogfood · 28 dev questions answered, zero misses
FRI · evening
Rolled to 5% of paying customers
WK 1
100% rollout · 1,600 conversations resolved · no escalations dropped

The outcomes

Six months in: on-call cancelled.

2.4k
Conversations / day
91.2% resolved without human intervention. Most include in-context workflow fixes AIVA proposes directly.
↓92%
First-response time
From 47 min → 3.8 seconds. AIVA reads the workflow before the customer finishes typing.
0
Active on-call rotation
Four engineers reclaimed ~24 hours/week of focused time. Two shipped features that had been backlogged for months.
+38pts
Support NPS
From +19 → +57. Customers regularly comment that AIVA understands their workflow better than the docs.

AIVA pays for itself before lunch. Our engineers got their week back. Our customers got answers faster than they expected. The only complaint we've had is that people now expect this from every other tool they use.

— Priya Subramanian, Head of Product, Vellum

More customer stories

Browse all
N
Northwind Traders
E-commerce · Bengaluru

Cut wait time by 84% without growing the support team.

Voice + WebRead
L
Lumen Labs
Healthcare · Mumbai

Handles 12k patient calls a month, autonomously.

Voice + SMSRead
F
Flux & Co.
Fintech · Singapore

Launched in 3 markets, 3 languages, 3 minutes.

Web + SMSRead

Want results like Vellum's?

Try AIVA with ₹500 free credit. No card. Live in four minutes.

Get started free →Or talk to sales ›