Twenty minutes, end to end: why the VoiceBot business stalled, what Sense changed, how it is built, what constrains it, and how it is sold today.
Everything in the next eighteen minutes is an answer to one question: where did those twenty-five points come from?
Three patterns where it reliably paid for itself, found across roughly eight months of pilots.
50,000 dialled, 25,000 connected, ~5,000 genuinely interested. Human agents only ever speak to the 5,000.
Same top line, 30–40% lower cost.
A client generates 50,000 leads a month and their agents can only work 25,000. The other 20,000 are never touched.
Pure incremental revenue.
Farmers, truck drivers, ride-hailing drivers. They do not recognise a bot, so they engage with it.
2min+ calls against 45–50 seconds.
A bot wins wherever the alternative is nobody calling at all, or a human wasting time on a lead that was never going to convert. It loses wherever it is competing directly with a good human agent on the same conversation.
Those leads are not merely lost, they are mislabelled. The bot records no interest, so the human agent never calls them either. A silent graveyard forms inside the client's own CRM.
Negotiation and persuasion. On a ₹5,000 or ₹10,000 purchase there is a human nuance the bot does not have, and that is a capability gap rather than a software one.
One of these is fixable in software. The other is not. Sense is what happens when you attack the fixable one properly.
At 90% of a human the argument works: take a 10% revenue hit, save 40% of cost. At 60% it does not, and no amount of discounting fixes it. That is why annual contracts churned at scale, and it is the entire commercial reason Sense exists.
The bot stops being a caller and becomes an agent that owns a lead until a goal is met.
The hang-up is no longer terminal. Call again, carrying what was said, until the goal is met or the window closes.
Voice, WhatsApp, SMS, email. If they will not take a call, message them. Same context on every surface.
Something decides which channel, at what time, with what content. That decision is the product.
The design brief was literally: replicate how a good salesperson operates. They call, they wait, they message, they try again at a better hour, and they remember the last conversation.
Omni-channel without shared context is just the same message on more surfaces. The context is the differentiator, which is why the full term is contextual omni-channel.
“I'm calling from Physicswallah about your recent website visit. Are you exploring JEE or NEET courses?”
“Yes, but I'm driving. Call me back at 5.”
“We spoke this morning. Can we talk now about whether the course is right for you?”
No pickup? Retry tomorrow, then the next day, until the window closes.
Under VoiceBot this lead produced a disposition and nothing else. Under Sense it produces an answer, because the callback was scheduled at the time the customer named and opened by referencing the earlier call.
The lead never repeats themselves. That is the whole reason the second call reads as a follow-up rather than a fresh cold call, and it is what converts a retry into a relationship.
Before every call or message, an LLM decides what to do next. Nothing here is rule-based.
everything said so far
campaign intent
the agent's prompt
an LLM call, per lead
channel · time · content
an AI call, or a WhatsApp message
why this channel, recorded
why now, recorded
Every action records why that channel and why now, visible per lead in the dashboard. The cooldown between actions is also LLM-set rather than configured. Two leads in the same campaign can be contacted on different channels at different intervals, without anyone configuring that.
A human replies in about a second. At three or four seconds the illusion breaks. Latency, transcription accuracy, response relevance and voice quality compound; get one wrong and the other three cannot rescue the call.
Cartesia replaced ElevenLabs because the quality delta did not justify the price delta at Convin's volume. TTS is billed per million characters, so prompt length feeds voice cost as well as model cost.
Leads, engagement days, channel limits, DND hours. The thing you actually run.
A goal, a personality, channels and tools. Created once, reused across campaigns.
One sentence: “qualify those interested in booking a medical visit.” Over-specify it and it never registers as achieved, so the agent keeps re-contacting the lead. An over-specified goal produces a spammy agent, and spam is what gets an account reported.
Meta integration and template configuration are secondary. Handed a platform and told to run a pilot, agent configuration is the first real work.
| 01 | Agent persona |
| 02 | Overall goal |
| 03 | State machine flow |
| 04 | Tone, style and language |
| 05 | Behavioural rules and guardrails |
| 06 | Task logic |
| 07 | Objection handling |
| 08 | Output formatting |
A client's script says what they intend to say. The recordings show what their best agents actually say, including the objection handling and the small acknowledging phrases nobody wrote down. Naturalness is not a model capability you buy; it is an authoring output.
A greeting node, a yes branch, a no branch. Then the customer asks “why are you calling me?” and there is no node for it. The bot jumps somewhere else and has to trace back. It demos beautifully and collapses on the first unscripted question.
The whole conversation design becomes a single prompt sent to the LLM for every response. An unexpected question is already answerable from inside the prompt, without leaving the flow.
Which makes prompt length a cost line, not a style preference. It also degrades answers: over-information is what causes the model to fail on something the prompt already contains.
Meta owns the account, approves every template, sets the daily limit, and can switch the whole thing off.
One reply, even a single dot, unlocks free-form messages for 24 hours. After that, a template again.
How many unique customers you may open a conversation with per day. A new account starts around 250.
Utility is defensible only with terms the customer accepted. Consent capture moves a message from ₹0.95 to ₹0.12.
| Line | Rate | Unit | Notes |
|---|---|---|---|
| Lead management | ₹1 | per lead uploaded | Covers the LLM cost of NBAs, metrics and entities. Charged whether or not anything is sent. |
| Voice | ₹1 | per 15-second pulse | Charged only on connect. An unanswered call costs nothing. |
| Utility template | ₹0.12 | per message | Paid by the client directly to Meta, not to Convin. |
| Marketing template | ₹0.95 | per message | Also to Meta. This is where a campaign accrues a real balance. |
WhatsApp bills on send, whether or not anyone reads it. Voice bills only on connect. Which is why a silent-delivery problem is almost always a lapsed card rather than a broken bot.
A brand-new business portfolio starts at roughly 500 conversations a day. A thousand leads were uploaded on day one. The limit was crossed and the entire portfolio was banned, taking down every WhatsApp sender the client owned for ten to fifteen days.
Control that came out of it: read the messaging limit before uploading.
Bought lead lists, used to recruit home-service workers. Much of the list turned out to be educated professionals, who reported the sender in volume. The account was blocked, appealed successfully, then the same campaign resumed. Within about eight days the whole portfolio was banned.
No configuration setting would have prevented this.
Message caps, engagement days, number rotation, DND hours. Recovery is asymmetric: a first block is usually appealable, a repeat offence takes the whole portfolio. That asymmetry should change how hard you push after any warning.
Proof arrived in the first fortnight anyway. Beyond that, a bigger lead set adds variance rather than proof: a different lead set behaves differently for reasons unrelated to the product.
₹10,000 was never revenue. It exists so companies with no intention of buying do not consume weeks of a PM's time.
Less money per pilot, far shorter time to proof, and more pilots closed. Pricing used as qualification.
Closure deck against the benchmarks, then handback to sales. 100 + 450 + 450 makes the thousand.
Before anything runs, capture what the client's own human agents achieve: connectivity, interest identification, conversion. A pilot returning 10x proves nothing if their agents were returning more. Matching the human benchmark is already a win, because Sense does it at a fraction of the cost of five or six agents.
Which turns the closing conversation from “was the bot good?” into “here is your number, and here is ours, on the same leads.”
Roughly three pilots running for every contract signed. Consumption pricing means a client who stops finding value stops spending, so the decline shows up in usage months before it shows up in a contract.
Sense qualifies leads; it does not close them. A team of ten becomes five people plus Sense, not zero people. Said at kickoff that sets a bar the pilot can clear. Said at closure it sounds like an excuse.
Which is the same conclusion Session 1 reached from the business side, arrived at again from the mechanics.
Points where the five recordings disagree, or where I could not tell from the material. Bringing the list seemed more useful than picking an answer.
| Free-form message rate | Session 3 gave ₹0.50; Session 5 gave ₹0.05. A tenfold gap on the message type sent most often inside the window. |
| Marketing template rate | ₹0.90, then ₹0.95, then ₹0.94–0.95 across three sessions. Converging, but worth pinning to a rate card. |
| LLM providers | Described once as open-source models, and later as OpenAI, Gemini, Claude or closed-source. Not the same claim. |
| The new dialer | A dialer purpose-built for voice AI was named as being trialled to replace Exotel. I could not make out the name. |
Happy to go deeper on any section. There is a full deck behind each of the five sessions.
| VoiceBot efficiency | 60% | of a human |
| Sense efficiency | 80–85% | of a human |
| First-10-second drop | 20–30% | of connected callers |
| Latency budget | ~2.5 s | one full turn |
| Voice billing | ₹1 / pulse | 15 s, on connect |
| Lead management | ₹1 / lead | NBA and metrics |
| Utility template | ₹0.12 · ~100% | cost, delivery |
| Marketing template | ₹0.95 · ~50% | range 30–70% |
| Free-form window | 24 h | from last customer msg |
| Starting WhatsApp limit | 250 / day | a new account |
| Transcripts for a prompt | ~20 | the client's best calls |
| Pilot today | ₹10,000 | 1,000 leads, two weeks |
| Pilot before | ₹1.5 lakh | 10,000 leads, one month |
| Pilot split | 100+450+450 | UAT, two campaigns |
| Business | 7–8 · 25+ | contracts, pilots |
| Strong pilot return | ~100x | ₹10k in, ~₹4L out |