Skip to main content
Every tool answers with text for the model to read. Where there is more — a plan id, a run record, candidates — it is also in the result’s structuredContent. Refusals (“this needs a goal”) are ordinary answers, not errors: read them and call again.

Look around

orbbai_who_knows_them

One person in; the people around them, each with how strong the tie is and the evidence under it — who they worked alongside and for how long, who they interact with publicly, and where each of those people is now. One call: no plan, no approval, nothing to poll. It pins the person itself. A LinkedIn URL or public id is read directly; a full name is resolved on the open record, and the answer says how sure it was. Where a name really is several people, it lists them instead of guessing.
string
required
A LinkedIn profile URL, the public id after /in/, or a full name. A single word is read as a public id, never as a name — for somebody known only as “Dana”, send the full name.
string
Where they work. This is what pins a common name. Ignored when person is a URL or public id.
string
Their work email. Read only when company is not sent.
string
What the introduction is for, if the question says — "revenue", "engineering", "anyone senior". Ranks and filters the people around them by what each does now and did then. Without it, the answer is whoever they know best rather than whoever matters here.
string
Your own user’s LinkedIn URL. The answer then says which of these people your user has worked alongside themselves — a path that needs no introduction.
string
Your own user’s employer, by name or domain. Marks anybody already reachable from your side.
This reads a few people off the record and cannot rank them against a goal. “Every relationship, scored and ranked” is a research run.

orbbai_who_knows_someone_there

One company in; ways in out. Each is a named person who left that company and a named person still inside whose time there overlapped theirs, with how many months they were there together. The person who left is the one you can approach.
string
required
A domain (snowflake.com), a name, or a LinkedIn id company/<slug>. A name is a guess, and the answer says which company it read. A LinkedIn company URL is not read — send the company/<slug> id.
string
The part of the company that matters — "engineering", "sales", "security".
string
A city, state or country, when the question names one. Somebody whose record names no place is not excluded: “we do not know where they are” is not “they are somewhere else”.
string
Your own user’s LinkedIn URL.
string
Your own user’s employer.
For who is worth talking to at a company — rather than who can get you in — check orbbai_held first, then plan a company run.

Orient

orbbai_capabilities

What Orbb can and cannot answer. Called bare, a short overview and the questions it settles, with how much of each is public record and how much needs data only you hold.
enum
overview (the default), kinds (the kinds of research, their limits and depths), asking (what makes an introduction land), questions, or all — every part at once, and long.

orbbai_playbooks

A library of worked workflows: scoring accounts by who you can reach, finding the route into every open opportunity, spotting deals with no relationship behind them, prioritising outbound by warm access, finding a missing executive sponsor, picking an event invite list. Each says when it runs, the steps, the calls it makes, and what your own systems must supply — either to run once now with these tools, or as a build spec for your own automation.
string
What your user is trying to do, in their words — "prioritise outbound", "we keep losing deals we have no relationship into". Returns the two or three that fit. Omitted, the shortest overview.
string
One playbook, in full, with a worked example.

orbbai_held

What your account has already researched, by kind and date. An answer from research already done is immediate and free; researching the same subject again spends tokens to learn nothing new.
enum
Limit to one kind of research: person, people or company. Omitted, everything.
string
What you are looking for, in your user’s words.

Research

orbbai_people_resolve

Turns names into the handles orbbai_plan takes. Returns candidates and never picks: a common name comes back as several people, each with a headline and company.
string[]
required
1 to 25 names. Each is a full name or a LinkedIn URL. Add a company or title where you have one — "Dana Mor, Head of Data at Acme" resolves far more often.
string
What this is for, in your user’s words. Later calls in this conversation weigh answers against it.
Each entry in resolved has the name asked and its candidates — handle, name, headline, company, and held when Orbb already has research on them. settled is set when exactly one researchable profile matched.

orbbai_plan

What a research run would take: a price in Research Tokens, a time, and a planId. Nothing starts. What you give decides the kind of run, and every kind takes the goal in ask.
string
What your user wants, in their own words — a sentence, not a filter. Optional in the schema, but most plans are refused without it.
string[]
Up to 40 handles from orbbai_people_resolve. Plans a person run.
string
One company, by name or domain. Plans a company run: who inside it is worth going through. Answers with a run id for the shortlist rather than a planId.
string[]
Up to 20 roles — ["VP Data", "Head of Analytics"]. With country or cities, plans a search across the whole public index, with a column per condition and a yes, no or not-checked in every cell.
string
A country code or name. A search that says nowhere is refused.
string[]
Up to 20 cities.
string[]
Up to 50 domains or names, when a search is about particular companies.
enum
fast, standard or deep. Leave it out unless your user asked; Orbb chooses.
The answer carries planId (or run for a company), questions worth putting to your user, an optional outside block, and refused when the plan cannot run — with the one thing missing.

orbbai_run_start

Agrees to a plan and starts it. Spends Research Tokens against the account the server is signed in as — the plan carries the price. Takes the plan id and nothing else.
string
required
The planId from orbbai_plan, made under the same credential.
The structured result carries the run id, a link to it in the console, and reused: true when a run for the same subject was already working.

orbbai_run_status

Where a run is and what it has found so far. Runs take minutes; poll.
string
required
The run id from orbbai_run_start.

orbbai_run_stop

Stops a run and keeps what it found — the rows stay readable through orbbai_run_status. No refund for what was spent. Harmless on a run already finished.
string
required
The run to stop.

Use the results

orbbai_routes_from_research

Routes out of research already finished, ranked against your goal, with the reasoning and two warnings about how to read them. It reads only what your account has already researched, and researches nobody: on a subject nothing has been run on, it says so.
string[]
required
1 to 20 handles or companies already researched.
string
required
What your user is trying to achieve. Required here — without a goal there is nothing to rank against, so it refuses.

orbbai_table_narrow

A new table from one a run already built, keeping the rows that meet conditions written as sentences. The original is untouched. Each row is judged against the conditions, at a small cost per row, so send every condition in one call.
string
required
The table id a run gave you, in the text of its answer.
string[]
required
1 to 20 conditions, as plain sentences — "has changed job in the last year".
string
A name for the new table.

orbbai_ours_remember

Records who is on your own side — colleagues, advisors, investors, customers, former teammates. Every later answer takes them into account, and routes through them rank first. Adds and never removes.
string
required
Your user’s own word for the relationship — "design partner", "former colleague", "board member". The vocabulary is open on purpose.
object[]
required
1 to 100 people.