Siddhant Jindal

ABM Associate Manager - BFSI @ | Driving Sales with Innovative Marketing

[Apurv Agrawal @apurv_agrawal]

Day 5 of 5: Introducing Inline PII Redaction

@SquadStackAI redacts customer PII in real time, before it reaches the LLM.
The calls that drive the most revenue in BFSI are the ones where customers speak Aadhaar numbers, PAN, bank details out loud.

In most voice AI systems, that data sits in plain text across the full stack. STT output, transcript, LLM prompt, model provider's API, logs, QA dashboard. No redaction at any step.

The hard part: PII on voice calls doesn't arrive in one clean line. A customer spells their PAN across four turns. They switch between Hindi and English mid-sentence. Single-turn detection misses most of it.

So we built inline PII redaction, a 6-turn rolling window between the STT engine and the LLM that catches PII split across fragments. 16 entity types, tuned for Indian voice conversations.

A regulated brokerage's compliance team recently reviewed this and signed off for production at scale.

To learn more: https://t.co/q5TcJjYOnB

[Apurv Agrawal @apurv_agrawal]

Day 1 of 5: Introducing Lift

In voice AI, the agent that improves fastest wins.

Today we're introducing Lift, the self-improvement layer for our Voice AI Agent. It learns from every call and makes the next one better.

The result is a conversion rate that keeps increasing, with no one rewriting the prompt.

Five years of running contact centres for India's largest brands taught us exactly where a call leaks conversion. Lift puts that to work. It analyses live calls, finds the changes that lift conversion, and proves it on live traffic before it scales, so nothing reaches full volume until it has beaten the current agent head to head.

We're already running it in production, and the results are holding up across campaigns.
Work that took a team weeks now happens in hours, so the agent reaches its best far faster, and stays there as objections shift, offers change, and new patterns surface in the calls.

Building the agent was only ever the start. Keeping it at its best, on every call, while everything around it keeps changing, is the real work. That's what we built Lift to do.

Learn more here: https://t.co/T5T8hVsoRY

[Apurv Agrawal @apurv_agrawal]

Day 2 of 5: Introducing Vernacular Voice AI Agents

Every voice AI platform lists a dozen Indian languages on the feature page. The count keeps climbing.

But deploy these agents in production and the conversations fail. The agent speaks “correct” Tamil. It sounds like a textbook. The customer knows in three seconds. They hang up.

We found that naturalness splits roughly 20/80 between TTS configuration and dialogue engineering. The 80% is the part nobody wants to do.

We mine fillers from real human agent calls, test every filler against every voice on real 8kHz telephonic calls, maintain a kill list of phrases that signal AI, and write every line of dialogue by hand.

No LLM generates this. That's the point.

We've launched vernacular voice AI agents across India's top languages.
They’re live across large-scale enterprise campaigns.

We wrote about how we built it: https://t.co/f9mGRaMUX2

[Apurv Agrawal @apurv_agrawal]

Day 3 of 5: Introducing Overwatch

A question I hear from leaders running voice AI at scale: how do we know what's actually happening on the calls?

The most expensive problems never throw an error. If the greeting has a two-second lag, or the agent fumbles a rebuttal on a specific objection, or it marks a lead as qualified without capturing the right entity. You find out days later, when the numbers slip.

That's why we built Overwatch.

A call slows down? Overwatch tells us whether it was the STT, TTS, LLM, or a tool call.

A campaign stops connecting? We see the telephony vendor, the drop reason and the DND status before anyone files a ticket.

A metric spikes? You go straight from the number to the exact calls it touched, by ID, ready to open and listen to.

Every problem you miss on the first call repeats on the next thousand. At ten thousand calls a day, seeing it early is the difference between scaling and quietly leaking revenue.

Overwatch is now live inside our Humanoid Voice AI Agent.

Full story here: https://t.co/KxVz1UjK3H

[SquadStack @SquadStackAI]

India's largest enterprises are sitting on a ₹50,000 crore revenue leak.

Nobody in the boardroom is talking about it.

Here's what's actually happening and why fixing it is the biggest revenue unlock left on the table:

[Apurv Agrawal @apurv_agrawal]

The wrong question: "Will AI replace contact center agents?

The right question: "What does a contact center agent become when AI handles the routine?"

We're seeing it in our own deployments. The agents who work alongside AI don't do less. They do things differently. They handle escalations. They coach the AI on new objection patterns. They own outcomes, not just conversations.

The job didn't disappear. It moved up the value chain.
That shift is uncomfortable to manage and extraordinary to watch.

[SquadStack @SquadStackAI]

Introducing Optimize, the multivariate testing engine that turns every experiment into compounding conversion gains.

Optimize is built directly into the https://t.co/s93m8hMMOH platform. Pick the variable, set a traffic split, run variants on a live lead sample.

#Voiceai

[Apurv Agrawal @apurv_agrawal]

Most startup growth charts look beautiful on LinkedIn.

Ours right now looks like Everest.
A steep, unreal curve.
Record-breaking months.
Large enterprise deals landing fast.

From the outside, it looks legendary.
But when you’re actually on the mountain… it feels very different.

Every milestone brings a problem you’ve never solved before.

Every step comes with thinner air.

Systems pushed to their limits.

Teams running without proper weekends.

Business models evolving mid-flight.

This is the part no one sees in the growth chart.

Because Everest doesn’t test your ambition.
It tests your character.

And on climbs like this, things will break. Plans will collapse. Some problems we’ll fix fast. Some will be outside our control.

But you still take the next step.
Because you chose the mountain.

@SquadStackAI

[SquadStack @SquadStackAI]

→ 60% lower CAC
→ 1.5x conversions
→ 3x faster handle time
Negotiating. Building trust. Closing deals. AI used to support these moments. Now it delivers them.
From first touch to final conversion, no leakage, no delays, no missed follow-ups.
https://t.co/ZfRnc6w7CH
#VoiceAI

[Apurv Agrawal @apurv_agrawal]

https://t.co/AUhgZXrOZC

[Apurv Agrawal @apurv_agrawal]

We just had our biggest month ever. Again.

February saw our highest volume of autonomous AI conversation minutes, with more enterprises going live than ever before.

Every month at @SquadStackAI internally we say “best month ever”, and the next one outperforms it.

Enterprises aren't piloting AI anymore. They're trusting us to own revenue outcomes at scale.

The graph reflects that shift, and we're just getting started!

[SquadStack @SquadStackAI]

We’re grateful for comments like this from leaders building at scale. Thank you, Vishal and the @jd_justdial team for the continued trust.

#squadstack #justdial #reviews #CustomerSuccess #EnterpriseAI #AIinSales #VoiceAI

[SquadStack @SquadStackAI]

India doesn’t have a deep-tech innovation problem.
It has a market creation problem.
Startups don’t fail at ideas. They fail between research and customers.

Read more: https://t.co/0Lo1hb4a1l

#DeepTech #IndiaAI #StartupIndia #AIInfrastructure #Innovation

[SquadStack @SquadStackAI]

Marketing got personalized years ago.
Sales is next.
Our AI voice agents are turning data into conversations that convert at scale. This is what the future of consumer sales looks like. ⚡

#IndiaAIImpactSummit2026

[DD News @DDNewslive]

#WATCH | At SquadStackAI, we are transforming consumer sales through AI-driven personalization. While marketing has been personalized for years, sales calls often remain repetitive and generic. We aim to change that by using AI and data to tailor every customer conversation. Our AI voice agents enable personalized, data-backed sales interactions at scale. We work with leading enterprises across India, including IndiaMART, BankBazaar, NIIT, Tata Digital, PhonePe, and Paytm, supporting use cases such as credit card sales and lead qualification across industries: Sanchit Gupta, AVP Marketing, @SquadStackAI

@GoI_MeitY @OfficialINDIAai @IndiaAiExpo #IndiaAIImpactSummit2026 #IndiaAISummit2026 #IndiaAIExpo

[SquadStack @SquadStackAI]

Merry Christmas from SquadStack 🎄

Secret Santa brought plenty of laughs, thoughtful surprises, and great energy across the office.

Moments like these remind us how special it is to build alongside people who care, create, and have fun together.

#SquadStack #Christmas

[Apurv Agrawal @apurv_agrawal]

We did it. 🚀
https://t.co/ej5leMgoMk agents have officially passed the Turing Test for contact centers.

[SquadStack @SquadStackAI]

Day 1 of SquadStack at Global Fintech Fest 2025!

I’m SquadStack’s Humanoid Voice AI. Before lunch, I interacted with 1,283 bankers, insurers & NBFCs.

Many asked if I was human. Cute, right?

Catch us at Booth R25, Jio World Centre, Mumbai.

#GFF #VoiceAI #SquadStack

[SquadStack @SquadStackAI]

India is leading the AI revolution. 🇮🇳

From Make in India to AI for India, SquadStack is proud to power this vision and is redefining customer experience with human-like Voice AI.

We’d be honored to host @PMOIndia @narendramodi at our booth during #GFF2025.

[SquadStack @SquadStackAI]

📍 Jio World Centre, Mumbai | Oct 7–9, 2025

Don’t miss your chance to shape the next era of CX with us at #GFF2025.