Identity resolution
One person and one company, however many systems they appear in. Resolved before anything is derived, so nobody works from a near-duplicate.
Connect your GTM stack with the REST API, MCP or the Claude Code plugin, and work with the context graph inside your agents.
GET /v2/accounts/meridian-health.com
{
"icp": 82,
"people": 6,
"claims": 18,
"sources": ["gmail","granola","hubspot","posthog"]
}Resolved, sourced, dated and permissioned before a person or an agent reads it.
One person and one company, however many systems they appear in. Resolved before anything is derived, so nobody works from a near-duplicate.
Budget, authority, competitors, adoption and risk, read out of what was actually said and dated to the day it was said.
Every answer returns the call, email or record behind it. Your team checks a claim rather than believing one.
A private thread stays private. Facts inherit the visibility of the record they came from, for people and for agents alike.
Each fact carries the date of the record it came from, so a stale answer is visible as stale rather than quietly wrong.
Open source under AGPL. Self-host the whole engine, or keep the raw records in a database you own.
One account record, served the same way to a script, an agent and the workspace.
Read the API docs →{
"entity": { "id": "ent_meridian", "type": "company" },
"summary": "Pilot at $40k for Q1. Priya Nair is the
economic buyer. DPA review open with IT.",
"claims": [
{ "property": "deal.budget", "value": "$40k for Q1",
"confidence": 0.94, "freshness": "fresh" }
],
"icp": { "score": 82 },
"meta": { "token_estimate": 1200 }
}REST: summary, claims with confidence and freshness, people and timeline. focus takes a domain, an email, a LinkedIn URL or an id.
Give Claude, ChatGPT, Cursor or your own agent the account, on a schedule or on demand.
Ask across the whole book in one call, with a question for ranking and one row per account back.
Briefs, follow-ups and pipeline reviews as slash commands.
An agent records what it learned against a precise person or account, with its source, for every other agent and person.
Start building on the context graph
Connect your systems, take an API key, and read your first account.
The same record in the terminal, in a chat and in Slack.