CRM Account Research Agent

CRM Account Research Agent enriches account records into structured, evidence-backed account briefs. It is built for sales, RevOps, partnerships, account-based marketing, and research workflows where a team already has a list of target accounts but needs faster context before outreach or planning.

The actor reads account names, domains, LinkedIn URLs, CRM IDs, and optional CRM notes. It visits public company web pages when a domain is available, extracts compact evidence, classifies account signals, scores fit and urgency, and writes one structured brief per account to the Apify dataset.

What it gives you

• Account identity fields for CRM joins
• Public website evidence URLs and snippets
• Firmographic hints such as industry, company type, location, and employee range when observable
• Products and services inferred from public messaging
• Growth, buying, and risk signals
• Fit and urgency scores
• Outreach hooks, open questions, and next-best actions
• Validation warnings when evidence is thin or confidence is low

This actor does not write back to Salesforce, HubSpot, or another CRM in v1. Use the dataset output, API, or datasetId append mode to connect it to your own CRM workflow.

Input

Paste one account per line. Use this simple format:

Company | domain | notes

The domain and notes are optional, but a domain improves public web research quality.

{
  "accountList": "Apify | apify.com | Developer platform account. Interested in web data, automation, and AI agent workflows.\nOpenAI | openai.com | AI platform account for developer and enterprise workflows.",
  "researchGoal": "sales_outreach",
  "marketContext": "B2B software teams evaluating web data and automation workflows.",
  "maxAccounts": 5
}

Input fields

• accountList - One account per line. Use Company | domain | notes. You can also paste comma-separated or tab-separated rows.
• researchGoal - Changes the brief angle and recommendations. Supported values are sales_outreach, account_planning, partnership_research, and risk_review.
• marketContext - Optional ICP, product, geography, campaign, or offer context.
• maxAccounts - Cost and runtime cap for the number of account records researched in one run.
• datasetId - Optional existing Apify dataset to append results to.
• runId - Optional pipeline ID copied to output rows.

Output

The actor writes one dataset row per account.

{
  "crmAccountId": "demo-apify",
  "companyName": "Apify",
  "domain": "apify.com",
  "canonicalUrl": "https://apify.com/",
  "researchGoal": "sales_outreach",
  "industry": "Artificial intelligence and automation",
  "shortDescription": "Apify is a platform for web scraping, browser automation, and web data workflows.",
  "productsServices": ["APIs and developer workflows", "Data products or analytics"],
  "growthSignals": ["Product or platform expansion mentioned"],
  "buyingSignals": ["Public messaging mentions data, automation, workflow, API, or integration themes."],
  "riskSignals": null,
  "fitScore": 80,
  "urgencyScore": 55,
  "researchConfidence": "high",
  "recommendedAngle": "Lead with a practical operational improvement for Apify in artificial intelligence and automation.",
  "outreachHooks": ["Reference public evidence: Apify helps developers build reliable web data pipelines."],
  "openQuestions": ["What internal CRM context, opportunity stage, or last-touch note should shape the next action?"],
  "nextBestActions": ["Review the evidence URLs before copying claims into CRM notes or customer messaging."],
  "evidenceUrls": ["https://apify.com/"],
  "validationWarnings": null,
  "error": false
}

How to use the result

Use the Account Briefs view for sales or account planning. Sort by fitScore, urgencyScore, and researchConfidence to prioritize accounts.

Use the Prioritization view to compare growth, buying, and risk signals across a target list.

Use the Evidence & Warnings view when you need to audit the source URLs, snippets, and warnings before copying claims into CRM notes or outbound messaging.

API example

curl -X POST "https://api.apify.com/v2/acts/trovevault~crm-account-research-agent/runs" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "accountList": "Apify | apify.com | Developer platform account",
    "researchGoal": "sales_outreach",
    "maxAccounts": 1
  }'

Evidence and confidence

Public web content can be incomplete, blocked, outdated, or ambiguous. The actor therefore exposes:

• evidenceUrls and evidenceSnippets so users can audit claims
• sourceCoverage to show which pages were used
• researchConfidence to separate strong briefs from thin ones
• validationWarnings when source coverage is weak, the website cannot be fetched, or the supplied account identity is not strongly confirmed

The actor should not be treated as a legal, financial, or compliance-grade source of truth. It is a research accelerator for CRM workflows. Review important claims before sending them to customers or using them in high-stakes account decisions.

Limitations

• v1 does not authenticate into private CRM systems.
• v1 does not use paid enrichment providers.
• Results depend on public website availability and may be weaker for blocked, sparse, or newly launched sites.
• Company location, employee count, and company type are only returned when observable from available text.
• The actor avoids dumping raw HTML and instead keeps compact evidence for auditability.