> ## Documentation Index > Fetch the complete documentation index at: https://docs.anycrm.anyreach.ai/llms.txt > Use this file to discover all available pages before exploring further. # Customer Intelligence > AI-driven account research: turn a handful of seeds into scored, enriched targets with ready-to-send collateral Customer Intelligence takes a small set of seed inputs — company names, exact websites, LinkedIn URLs, an uploaded lead list, or an ICP (ideal-customer-profile) filter to discover against — and turns them into researched, scored targets with generated outbound collateral. It's aimed at BPO-style outbound: "here are some leads/an ICP, tell me who's worth pursuing and why, and hand me something to send them." ## Runs A **run** is the unit of work. Creating one (`POST /customer-intelligence/runs`) starts a dedicated Temporal workflow (`CustomerIntelRunWorkflow`) that drives the whole pipeline for that batch of seeds. The run also carries the org's BPO positioning and ICP config (what you sell, who you sell to) — saved once via `GET`/`PUT /customer-intelligence/config` and reused as sensible defaults on every new run, overridable per run. The workflow moves through phases in order: ``` intake → resolution waterfall → [resolution gate] → light research & scoring → [shortlist gate, if deep deliverables requested] → deep deliverables → finalize ``` "Light" research and scoring runs for every resolved target and produces a pain/fit score plus a compact "why" breakdown (per-signal evidence, confidence, data sources). "Deep" deliverables — full reports, decks, models — are comparatively expensive, which is what the shortlist gate exists to control. ## Gates: human-in-the-loop checkpoints A gate is a point where the workflow pauses and genuinely waits for a person to decide, rather than guessing: * **Resolution gate** — fires when a seed can't be trusted to be correct on its own: a bare company name, a person/company LinkedIn URL that needs resolving, or the scope of an ICP/lookalike discovery search. An exact website is the only seed solid enough to skip this. You confirm or correct matches via `POST /customer-intelligence/runs/{run_id}/resolution`. * **Shortlist gate** — fires after light scoring, only when the run requested deep deliverables. You pick which scored companies get the full deep set via `POST /customer-intelligence/runs/{run_id}/shortlist`. Both gates are a durable, bounded wait: the run re-notifies on a reminder cadence and — if nobody responds by the deadline — hard-expires to a terminal `abandoned` status. It never silently proceeds without a decision. Even after a run finishes, you can promote any individually-researched result to the full deep deliverable set later via `POST /customer-intelligence/runs/{run_id}/results/{result_id}/build-report` — the shortlist gate only exists while the run itself is paused. ## Results and deliverables Each target in a run produces a **result**: the pain/fit score, a scoring rationale, and whatever deliverables were requested for it. Depending on the run's configuration, that ranges from a lightweight scored-lead row up to a full deep set — a CX intelligence report (PDF), a review-analysis spreadsheet, a sales deck, an ROI model, a company research brief, stakeholder/contact intelligence, a drafted outreach email, and an auto-provisioned interactive demo. Deliverables can be individually revised, hand-edited, or regenerated with feedback after the fact, and the CX report has its own shareable public link. ## Getting data in Seeds can be typed directly (company names, websites, LinkedIn URLs), expanded from "lookalike" seeds, discovered from an ICP filter, or extracted by Claude from an uploaded document (`POST /customer-intelligence/uploads` — PDF, CSV, DOCX, XLSX, TXT, or Markdown, capped at 15 MB) during intake. See the **Customer Intelligence** section of the APIs tab for endpoint-level detail.