AI and Agentforce
Three telephony feeds joined on one key, and every answered call turned into a speaker-labelled transcript with owned action items for fractions of a cent.
01Key numbers
02The situation
Calls happened in a telephony system and stopped there. Nothing joined a call to the account, the order or the person who owed a follow-up.
Conversation intelligence products solve this at over $100 per seat per month, which is a reasonable price for a product and an unreasonable one for a lookup.
Recognise this in your own org?
03What we built
Three feeds joined on one unique external identifier, then one model pass per answered call against a fixed JSON schema.
Click-to-dial, a five-minute analytics poll and a real-time per-rep socket for screen-pop all resolve to the same call record through one unique external identifier. Three sources cannot produce three versions of the same call.
Internal calls and unanswered inbound calls from unknown numbers are not logged, because robocalls and hang-ups would be the majority of the data. What is excluded is stated rather than discovered later by someone reading a count.
Every answered call’s audio goes to a fast model with a JSON schema, returning a speaker-labelled transcript, a summary, a category, sentiment, action items with an owner and a due date, amounts, people and the site address. A schema is what makes the output writable to a record.
Three of this account’s four open orders are past their scheduled end date with no billing window set. The pattern matches two orders that later needed a change request.
Generated from order records in this org. Not a measurement. Users cannot edit this text.
We will demonstrate any of these live, on the real org,.
The model did its job. The CRM could not say who most of these calls were with, because the contact and lead data did not have the numbers. We reported that as the finding rather than quietly matching on a fuzzy rule and reporting a high match rate.
04Outcome
Call intelligence runs at model cost, and the gap it exposed in the contact data is on the report rather than papered over.
Measured on a live seven-day import of 56 calls across 8 reps, with every skipped call attributed to a stated rule.
Keep reading
Point agents at an org overnight and get back findings anchored to a file and a line, a costed backlog, and the exact click path to verify each item as the real user.
The client told us the tax was calculating by product instead of by province. We tested that against all 2,335 order line items and it was not true. Six other defects were, and we priced each one.
Tell us what is broken. You get a written read on it within one business day, before any money changes hands.