Viveka listens to messy, real-world Hinglish insurance calls — 8 kHz, noisy, code-switched — and returns two machine-readable profiles per call. Every extracted fact carries a verbatim quote and a confidence level. Nothing is asserted without a receipt.
Neighbouring agents read the same script into the same open-plan mic. Viveka decides what's real by who actually responded — not by who's loudest — and drops the bleed-through.
Any field above low confidence must quote a verbatim substring of the transcript. Below that, the value is forced to not_disclosed and evidence is left empty. The model can't confidently assert what the customer never said.
A 20-second voicemail and a 12-minute discovery call are different problems. Each transcript is routed to a length-specialized extractor.
From a single transcript, Viveka builds an 18-group profile — then a deterministic layer computes BANT, bands and the lead grade in code, so the same call always grades the same way.
Most tools give you a flat label. Viveka gives you the reason, in the customer's own words, and how badly it matters. A dead label becomes a conversation the next agent can actually have.
"Guaranteed 35% return" is compliant on a non-par endowment and a violation on a market-linked ULIP. A naive keyword flagger fires on the word and mislabels most calls. Viveka classifies the product family first, then judges every claim in context.
Every call auto-graded A–D. 43% are A-grade leads to call back today; 12% are C/D to deprioritize.
Six coaching dimensions, averaged by grade. Watch where each collapses A → D.
Correlation of each signal with the overall call score.
The intelligence isn't the score — it's knowing what to coach. Each step down grade is a different failure.
Top performers by average score — with the signals that separate them.
Standards-compliant API — streaming, strict JSON-schema and tool calling. Quantized for high single-node throughput.
Multi-key rotation and thread-pool parallelism. Built to grind an entire call center's daily volume, unattended.
One call → one profile. It doesn't yet stitch a customer's calls into one journey.
It doesn't score calls against a specific company call-script.
Built for Indian life-insurance tele-sales. That focus is the source of the accuracy.
18 field groups. ~60 fields. Zero guesses. Every fact comes with the quote that proves it.