ICSS

ICSS (Intent-Conditioned Silicon Sampling) samples synthetic respondents from intent states observed in search behavior (CEP, nano intent, KBF, constraint, avoidance, consideration, journey stage) instead of demographics, and runs surveys, FGDs and 1:1 chats with them. Marketers and researchers use it to test hypotheses before real fieldwork. Data comes from ListeningMind search data (DaaS, SERP) plus stored CEP Finder and Intent KG runs, for Korea, Japan and the US. It also includes a distinctive brand asset (DBA) recognition test.

How a result is made

get_config: Check that the LLM and data back-ends are on.
analyze_topic: Get search-behavior data for each keyword; merge several keywords yourself.
find_cep_run: Look for a stored CEP Finder run for the topic (free).
get_cep_states: Load that run as the intent-state distribution P(IntentState).
start_cep_build: Only if none exists, start a new CEP analysis (spends credits, needs confirmation).
get_cep_job: Poll until done, then load the result with get_cep_states.
get_grounding_pack: Check for a stored grounding pack.
build_grounding_pack: If missing, build one from stored runs only (0 credits).
get_grounding_job: Poll the grounding job until done.
get_evidence: Get the CEP and KG evidence summary for persona grounding.
probe_ai_overview: Probe AI Overviews to fill category-specific avoidance and criteria.
get_cluster_serp: For a custom panel on one cluster, collect that cluster's SERP evidence.
get_keyword_info: Add gender/age and volume for the chosen keywords.
ask_llm: Generate question ideas, survey batches, FGD turns and summaries with state-first persona prompts.
save_run: Save the snapshot on the server so it opens at #run=ID.
list_runs: Find saved stories to reopen.

Agents: llms.txt · agents.md · MCP · OpenAPI. Every page also answers Accept: text/markdown.

ICSS at a glance

ICSS (Intent-Conditioned Silicon Sampling) samples synthetic respondents from intent states observed in search behavior (CEP, nano intent, KBF, constraint, avoidance, consideration, journey stage) instead of demographics, and runs surveys, FGDs and 1:1 chats with them. Marketers and researchers use it to test hypotheses before real fieldwork. Data comes from ListeningMind search data (DaaS, SERP) plus stored CEP Finder and Intent KG runs, for Korea, Japan and the US. It also includes a distinctive brand asset (DBA) recognition test.

Key ideasSynthetic consumer panel Search intent CEP · Buying situation KBF · Choice criteria Distinctive brand assets (DBA)

Works well withFunnel Leak Finder Prompt Builder Smart Store Suite

MoreAbout the app All 16 apps Glossary For agents

ContactContact us Talk to our API team