> ## Documentation Index
> Fetch the complete documentation index at: https://docs.emanate.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Account Enrichment
> Automatically enriching accounts with company, contact, and intelligence data
Account enrichment automatically appends company data, decision-maker contacts, verified addresses, and AI intelligence scoring to each account, giving your team the context they need to prioritize outreach and close deals.
**Updated in v2.8**: New domain-resolution pre-stage, verified billing addresses with alternate-address review, `needs_review` workflow, duplicate detection, and automatic phone-number lookup with built-in fallback. See [Release Notes](/about/release-notes) for details.
The enrichment pipeline is shared with [leads](/leads/enrichment): same stages, same behavior, same review tools. This page describes it from the account perspective.
## What Gets Enriched
### Company Data
| Field | Description |
| -------------------- | -------------------------------------------------------------------------------------- |
| **Company Name** | Official company name |
| **Domain** | Company website |
| **Industry** | Industry classification |
| **Employee Count** | Company size |
| **Revenue** | Estimated annual revenue |
| **Location** | Headquarters location |
| **Technologies** | Tech stack used |
| **Funding** | Recent funding info |
| **Verified Address** | Street, city, state, postal code, and country |
| **Segment** | Specific business classification (e.g., "Mid-market manufacturer of structural steel") |
### Contact Data
For each decision-maker contact discovered on an account:
| Field | Description |
| ------------------ | ------------------------------------------------ |
| **Title** | Job title (e.g., "VP of Operations") |
| **Department** | Function (Sales, Engineering, etc.) |
| **LinkedIn** | LinkedIn profile URL |
| **Direct Phone** | Direct dial number |
| **Mobile** | Direct mobile number (populated by phone reveal) |
| **Personal Email** | Additional email addresses |
### Account Intelligence
After company and contact data are populated, AI generates:
| Field | Description |
| -------------------- | ----------------------------------------------------------------- |
| **Fit Score** | How well the account matches your ICP (1–100) |
| **Heat / Grade** | Overall priority indicator (A / B / C) derived from the Fit Score |
| **Why This Account** | Plain-language summary of the firmographic match |
| **Why Now** | Timing signal: recent triggers (funding, hiring, news) |
| **Priority Action** | Recommended next step |
These appear on the **Intelligence** sub-tab of the account drawer.
#### How the Fit Score Is Calculated
The Fit Score is produced by an LLM synthesis pass over five weighted insight categories. Each category gets its own 1–100 sub-score and short reasoning paragraph; the headline Fit Score is the synthesis output, not a hand-tuned linear formula.
| Insight | What it measures |
| ------------------------- | -------------------------------------------------------------- |
| **Firmographic Fit** | Industry, employee count, revenue, growth stage vs your ICP |
| **Recent Activity** | Funding, hiring, product launches, news in the trailing window |
| **Pain Points / Needs** | Likely challenges inferred from industry, size, and tech stack |
| **Decision-Maker Access** | Who to contact, typical buying process for the account size |
| **Competitive Landscape** | Market position, competitors, differentiation angles |
Score-to-verdict mapping used across the UI:
| Score | Verdict | Grade |
| ---------- | ---------- | ----- |
| **80–100** | Strong fit | **A** |
| **60–79** | Good fit | **B** |
| **40–59** | Neutral | **C** |
| **1–39** | Weak fit | **C** |
Re-running enrichment (or any per-column Fill that changes a firmographic input) recomputes the Fit Score on the next pipeline pass. You can also re-compute the three intelligence explanations individually via [per-column Fill](#per-column-fill).
## Enrichment Triggers
### Auto-Enrichment on Import
When importing accounts via the Import Wizard, the **Auto-enrich imported accounts** toggle on the Column Mapping step runs enrichment automatically as soon as rows land. Matched/duplicate rows are skipped. You can run enrichment on them manually if needed.
### Manual
Enrich on demand from any account row:
1. Open the account drawer
2. Click **Enrich**
3. Wait for data to populate
### Bulk: Selection-Driven Enrich Button
The **Enrich** button at the top of the Accounts (and Leads) table retargets based on what's selected:
| Selection state | Button label | What gets enriched |
| -------------------------- | --------------------------------- | ----------------------------------------------------------------- |
| Nothing selected | **Enrich First 50 of N Filtered** | First 50 rows of the current filtered page (legacy default) |
| 1–50 rows checked | **Enrich N Selected** | Exactly those rows |
| 51+ rows checked | **Enrich First 50 of N Selected** | First 50 of the checked set |
| Select-all-across-pages on | **Enrich First 50 of N Selected** | First 50 across the whole session, minus any rows you've excluded |
Server-side `BATCH_LIMIT = 50` is intentional. Pick the 50 highest-priority rows and run again rather than raising the cap. The button is disabled while any visible row is already queued or enriching.
### Per-Column Fill
You don't have to re-run the whole pipeline to refresh a single value. Each enrichable column on the Accounts and Leads tables has its own **Fill** action: an icon next to the column header (and a per-row variant where available) that re-fills just that field for the targeted rows.
Four pipelines share the registry; each owns a distinct slice:
| Pipeline | Fields it owns |
| ------------------------------------------ | ------------------------------------------------------------------------ |
| **Web research** | `industry`, `revenue`, `employees`, `founded`, `segment`, `funding` |
| **Company resolver** (Claude 4.6 fallback) | `domain`, `website`, `companyName`, `address` |
| **GPT** | `whyThisAccount`, `whyNow`, `priorityAction` (intelligence explanations) |
| **Contact lookup** | `primaryContact` (name / email / phone discovered together) |
Each cell tracks its own lifecycle state in the DB (`_fill_status` = `queued` → `filling` → `NULL`) so the cell shows a **Queued…** or **Filling…** badge live without polling other columns. Each pipeline only asks for the slice it owns: "Fill domain" never touches website, name, or address; "Fill industry" never touches revenue.
#### Prerequisite Check
Per-column Fill only runs when each row has enough input for the pipeline to ground the lookup. The column-header button is **disabled with a tooltip** if any visible row is missing a prerequisite:
| Pipeline | Required input |
| ---------------- | ---------------------------------- |
| Web research | Company name **or** website/domain |
| Company resolver | Company name |
| GPT intelligence | Company name |
| Contact lookup | Company name **or** website/domain |
The tooltip names the missing field(s) so you can fix the gap or narrow the selection.
Use per-column Fill when you only need one field refreshed. Re-enriching a whole row costs a full pipeline pass and overwrites nothing that's already set. Targeted Fill is also the right tool when a single provider returned `—` and you want to retry just that slice.
### Hover for Source Citations
Enriched **Revenue**, **Employees**, and **Industry** cells carry per-field citations from the original lookup. Hover any of those cells to reveal a tooltip with:
* The **citation URL** that grounded the value (typically a LinkedIn company page or industry profile)
* The **page title** so you can confirm the source before clicking through
* The model's **confidence** when reported (high / medium / low)
If a row was enriched before the citations layer shipped, the tooltip stays hidden. There's no "Sources unavailable" placeholder cluttering the cell. Re-enriching (or per-column Fill) will populate citations going forward.
## The Enrichment Pipeline
Each enrichment run flows through several stages.
### Stage 0: Domain Resolution
Before any lookup runs, an AI step resolves messy company strings (abbreviations, misspellings, customer-list short codes) into a canonical domain. This dramatically improves match rates downstream and lets enrichment work on rows that only have a company name.
Internal acronyms in your customer list (e.g., "DOFASC" → "Dofasco") are auto-expanded during this stage so they match real company records.
### Stage 1: Decision-Maker Discovery
Searches the company for decision-makers and surfaces the most senior contact available, attaching them to the account's Contacts tab.
If a primary contact already exists on the account, newly discovered contacts land as **secondary contacts** rather than overwriting the primary. Phone-only primaries created from import are preserved.
### Stage 2: Company Data
Populates verified company data including industry, employee count, revenue, technologies, headquarters address, and a specific segment classification.
### Stage 3: Phone Reveal
Requests a direct mobile number for the primary contact. If the initial lookup doesn't return a number quickly, the system automatically falls back to a secondary source so the **Mobile** column populates reliably.
### Stage 4: CRM Sync, Intelligence & Embeddings
The pipeline finishes with CRM sync (if a CRM is connected), AI **intelligence scoring** (fit score, timing signal, and priority actions) and vector embeddings that power **natural-language semantic search** across your account base.
### Estimated Run Time
Enrichment runs in batches of **up to 100 leads or accounts** at a time, with the actual batch size adjusted in real time based on available resources. This applies to all enrichment: auto-enrichment on import, manual single-row enrichment, and bulk re-enrichment. Plan for roughly **12 minutes per batch** end-to-end. Rows that match an existing record (duplicates) are skipped by auto-enrichment but can be enriched manually.
## Revenue Formatting
Revenue is **stored as a raw integer** and rendered everywhere through a single `formatRevenue` helper:
| Raw value | Displayed |
| ------------------------ | --------- |
| `1_500_000_000` | `$1.5B` |
| `50_000_000` | `$50M` |
| `250_000` | `$250K` |
| `999` | `$999` |
| `0`, negative, or `null` | `—` |
The web-research prompt is constrained to return a clean integer (no `$`, no `K`/`M`/`B`, no ranges, no "approx") and Fill-revenue paths route through the same helper. Pre-EMA-263 rows with messy strings are normalized on read.
## Overwrite Behavior
Enrichment **never overwrites existing data**. If a field already has a value, it's preserved; if it's empty, enrichment fills it in. This applies to every enriched field: name, email, phone, title, LinkedIn URL, company info, and so on.
Addresses are handled with an extra layer: a verified billing address that differs from the existing one is stored as an [alternate address](#verified-addresses--alternate-addresses) for you to **Accept** or **Keep Existing** rather than being applied silently.
Decision-maker contacts follow the same principle: newly discovered contacts land as **secondary contacts** when a primary already exists, and never replace the primary automatically.
## Verified Addresses & Alternate Addresses
When enrichment returns a verified billing address that differs from the address already on the account, the new address is **stored as an alternate** instead of silently overwriting the existing one. The drawer's **Address** section grows an **Alternate Addresses** card with **Accept** and **Keep Existing** buttons so you can promote or dismiss each candidate.
| Action | Effect |
| ----------------- | ---------------------------------------------------------------------------------- |
| **Accept** | Promotes the alternate to be the primary address; the previous primary is archived |
| **Keep Existing** | Dismisses the alternate; the existing address remains |
## Enrichment Review
After a batch run completes, the **Enrichment Review** dialog highlights every account with discrepancies between previously stored data and the newly enriched values. Each row is tagged:
| Tag | Meaning |
| --------------- | -------------------------------------------------------------- |
| `match` | Existing data matched the enrichment result, no action needed |
| `auto_filled` | Field was empty before; enrichment populated it |
| `kept_existing` | Existing value was preserved (e.g., primary address protected) |
| `mismatch` | Existing value disagrees with enrichment; review recommended |
| `uncertain` | Enrichment could not establish high confidence |
Synthetic alternate-address cards are surfaced inline so you can resolve them in a single review pass.
## The `needs_review` Status
Accounts that require human attention move to a dedicated **`needs_review`** state, surfaced as an amber pill in the table and an **N need review** count badge next to the enrichment ETA. Filtering the status column shows friendly labels for each state.
Common reasons an account enters `needs_review`:
* Enrichment matched a domain already claimed by another account (potential duplicate)
* An alternate address was returned that disagrees with the existing primary
* Confidence on a critical field is below threshold
## Duplicate Detection
If enrichment resolves to a domain that's already claimed by another account, the second account is flagged `needs_review` and the **Duplicate Review** dialog gives you three choices:
| Option | Effect |
| ----------------- | -------------------------------------------------------------------------------------------- |
| **Keep Separate** | Treats both accounts as distinct; clears the review flag |
| **Merge** | Folds the new account into the existing record, preserving custom fields, tags, and contacts |
| **Delete** | Removes the duplicate account entirely |
Duplicate detection runs on **both leads and accounts**, with parity in the review experience.
## Semantic Search
Vector embeddings produced in Stage 4 power natural-language search across your account base. Type a query like "mid-market manufacturers in the Midwest hiring engineers" and the system returns the closest-matching accounts ranked by similarity.
## Enrichment Quality
### Match Confidence
Enrichment results carry a confidence label that's surfaced on alternate-address cards and contact matches:
| Label | Meaning |
| ---------- | --------------------------------------------- |
| **High** | Strong match, high reliability |
| **Medium** | Good match, review recommended |
| **Low** | Uncertain, review before relying on the value |
### Handling Low Confidence
Low-confidence fields are tagged `uncertain` in the [Enrichment Review](#enrichment-review) dialog, and accounts containing them move to the [`needs_review`](#the-needs_review-status) state so they're easy to spot and action manually.
## Monitoring Enrichment
### Dashboard Metrics
| Metric | Description |
| ------------------- | ------------------------------------- |
| **Enrichment Rate** | % of accounts enriched |
| **Match Rate** | % with high-confidence match |
| **Needs Review** | Accounts flagged for manual attention |
| **Failed** | Enrichment failures |
### Enrichment Status
| Status | Meaning |
| ---------------- | ---------------------------------------------------------------------------------------- |
| **Pending** | Queued for enrichment |
| **Processing** | Currently enriching |
| **Enriched** | Successfully completed |
| **Partial** | Some fields populated |
| **Needs Review** | Requires manual review (duplicate suspected, alternate address, or low-confidence field) |
| **Failed** | Could not enrich |
| **No Match** | No matching record found |
## Troubleshooting
* Verify the company name and domain are correct
* Try the canonical domain (e.g., `acme.com` rather than a regional subdomain)
* The company may not be in the enrichment provider's index
* Enrichment data can become stale over time
* Re-run enrichment from the account drawer to refresh
* Re-run enrichment from the account drawer or the **Bulk Actions** menu
* Check the account's status: `needs_review` accounts require manual action before re-enrichment will help
* If the failure persists across many accounts, contact support
## Best Practices
### Enrich Strategically
Use [duplicate detection](#duplicate-detection) and the `needs_review` queue to focus attention where it matters. The system already skips matched rows automatically.
### Review Alternate Addresses Promptly
When enrichment surfaces alternate addresses, action them quickly so your account records reflect ground truth. Stale alternates can clutter the drawer and obscure what's authoritative.
### Monitor Quality
Regularly review enrichment quality:
* Spot check enriched accounts
* Track match rates and the `needs_review` count
* Action `needs_review` accounts promptly so the queue doesn't pile up
## Next Steps
Custom fields, sessions, and duplicate detection
Manage contacts and primary contact
Convert qualified leads into accounts
Same pipeline on the lead side