YourKith is an intelligence cycle.

Somebody has to say what matters

You define who you're trying to reach, and you set one number, the "working with" window, that decides what counts as close. Every band below it is a fixed multiple, never a second dial that can drift out of agreement with the first.

Which modules run, which sources connect, and what the platform is allowed to spend are deliberate, admin-set decisions, and the governing rules are readable rather than folklore.

One "working with" window · bands as fixed multiples · modules, sources and spend set by an admin

Signal from where it already lives

Connectors drain on a schedule and write with provenance, so every row knows where it came from. You do no data entry; the corpus is the exhaust of work you were doing anyway.

Draining on a schedule: Gmail · Google Calendar · Outlook · Outlook Calendar · Slack · Granola · Mercury
Built, not yet run against live data: Zoom · Fathom · QuickBooks

Raw signal becomes a resolved person

This is where most relationship tools quietly fail. Identity lives in one durable identifier index, and a job's identity fields, the company, the title, the start date, are never rewritten once recorded; a role that ends is closed with an end date rather than edited away. Records fold together on a shared verified, non-role identifier wherever one exists, because a wrong merge is the one mistake a later pass cannot detect and undo.

And nothing reaches a shared surface ungated: every source runs through a declared, tested relevance gate before it can put a single row in front of you, and a build check fails on any attempt to write around it.

Durable identifier index · employment closed, not rewritten · uncertain merges held for a human

Resolved entities become judgement

One classifier turns recency and tie-existence into a single word, working, cooling, dormant, or network, and the graph, the directories, and the health scoring all read that one value rather than each keeping a private opinion about who counts as active.

On top of it sit company and contact intelligence, ratings, briefs and competitive battlecards. On the enrichment paths that write to a contact or company record, a fact without a source is dropped rather than quietly committed.

One tie-state classifier · provenance gate on the enrichment write paths · explainable scoring

Put it where the decision gets made

A daily briefing, one insights surface, the directories, the relationship graph, and a single triage queue where everything that needs you lands. One inbox, not one per source.

And Wita: chat over your own corpus. When an answer is grounded in your records it carries numbered citations that link back to the record, or to the company that owns it, and a citation that cannot be resolved to a real page renders flagged rather than being given a fabricated link. When it has no evidence to cite, it says so and labels the answer as general knowledge rather than dressing it up as a finding about your data.

Briefing · Insights · Relationship graph · Triage · Wita, with resolvable citations

A loop, or it's only a pipeline

Every triage decision is recorded. A source you keep dismissing as genuinely irrelevant stops filling your queue, but only once it has proven noisy across a run of decisions rather than one bad afternoon. Dismissing something because you had already handled it never counts against the source; it was relevant, you just dealt with it.

Reject a proposed merge and that rejection is recorded against the pair, so the same suggestion does not keep returning. It also learns upward: an approved recommendation that goes on to close raises how the next one like it is ranked.

Every triage decision recorded · a rejected merge does not return · approved outcomes reweight ranking