Your first enrichment

What an enrichment is

You send an identifier. You get back facts.

Send an email, a LinkedIn URL, or a company domain. abm.dev resolves it across ten data sources — LinkedIn, Companies House, Perplexity, Tavily, Hunter, and others — into a single answer: eighty-nine canonical fields (forty-three about the person, forty-six about the company) and forty signals.

Every value arrives with three things attached: its source (which provider it came from), a confidence between 0 and 1, and a selection_reason telling you why that value was chosen. Higher confidence means more of the sources agreed.

No per-source bills. No per-field charges. No silent fallbacks. A value is cited or it is not returned. Nothing is invented.

More on the model: /docs/concepts/enrichment, /docs/concepts/canonical-fields, /docs/concepts/data-sources, and /docs/concepts/confidence-scores.

Step 1 — Get a key

Sign up, then open your dashboard. Create an API key.

Want to try before wiring anything up? The Playground is free — run an enrichment in the browser, no code.

New accounts can redeem free launch credits with the code LAUNCHCODES.

Step 2 — Run your first enrichment

One request. Set your key, point it at a person, send.

curl https://api.abm.dev/api/v2/enrichments \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "targets": [
      { "type": "person", "email": "[email protected]" }
    ]
  }'

Each target also accepts a linked_in_url or a company domain instead of an email. Up to three targets come back synchronously in the { data, actions, meta } envelope; larger batches queue and return a job id.

To read back an enrichment later:

curl https://api.abm.dev/api/v2/enrichments/{id} \
  -H "x-api-key: YOUR_API_KEY"

Full request and field details live at /api-reference/enrichment.

Step 3 — Read the response

The response carries the canonical fields and signals abm.dev resolved. For each value, look at the three things that come with it:

• source — which provider supplied it.
• confidence — a number from 0 to 1. The closer to 1, the more the sources agreed.
• selection_reason — why that value was chosen.

That is the whole contract: cited, scored, and explained. Trust the high-confidence values, scrutinise the rest, and discard nothing silently.

For exact field names and the response layout, read the API reference. Treat that as the source of truth over any example here.

If you are an AI agent

Two ways in.

Claude (Connectors). Add the MCP server. Settings → Connectors → Custom → paste:

https://mcp.abm.dev/mcp

The server exposes abm.dev’s enrichment tools inside Claude. The exact tool list is unverified here — see /for-agents.

Cursor, Claude Code, Windsurf. Paste a prompt telling the agent to read /docs and the machine-readable llms.txt, request an API key, save it to a .env, run a test enrichment, and report back with citations. The agent can do the rest itself.

Scripts and terminals. Call the REST API directly, as in Step 2.

For agent loops, abm.dev streams results in real time over SSE; for batch jobs, a webhook fires when the job finishes. Setup specifics for streaming and webhooks are not documented here — see /for-agents and /api-reference/jobs.

What it costs

Per enrichment. No subscription. Credits never expire, and all ten sources are included in every call.

From about €0.29 per enrichment. Packs:

The Playground is free. Details at /#pricing.

Where to go next

• /api-reference — the full reference; treat it as canonical.
• /docs/cli — the command-line tool. Commands and install specifics are unverified here; read the page.
• Integrations: Claude connector, LinkedIn, HubSpot.
• Audience guides: /for-developers, /for-agents, /for-marketers.

Stuck? Open a support ticket.

abm.dev is operated by Foxley Farm Operations Ltd (UK Company No. 16392009), Oakham, United Kingdom. GDPR-compliant.