A conversational analytics agent for Sooka's content team.
Descriptive watchers tell you something moved. Diagnostic work starts the moment the Head of Content asks why. This agent takes the question in plain English, picks the right slice of Sooka's content-performance scoring framework, runs the comparison across languages and titles, picks a chart, writes the narrative — and ships a one-page brief to the exec who asked, before standup.
Every “why did Korean drama retention drop?” lands in the analyst queue. By the time the answer arrives — three hours later in deck form — the content team has moved to the next licensing call.
The agent decomposes the question into a plan: which library, which cohort, which comparison, which chart. It runs the slice across the multilingual content scoring framework and writes the narrative in the team’s internal voice.
Routine “why” questions never reach a human analyst. The team gets back to commissioning calls and licensing strategy — the upper half of the AAM curve, where their judgement actually compounds.
One question. Three artifacts. No analyst.
Now ask it yourself.
Pick a question — or paste your own (4 KB cap) — and watch the agent plan, slice, narrate, and emit the same one-page brief format you just saw above. Live model call. Cached replay if the rate-limit fires.
waiting for verification token…