Graph quickstart
Get your talent data onto the Graph, then ask your first question. Two ways in — a live integration, or your own files.
- Create a Workerbee account (Console).
Access is invite-only — no self-serve signup.
“Ask your Workerbee contact for an invite, or email support@workerbee.ai.”
- Choose your path
Ingest using integrations
Connect a live ATS, HRIS, or LMS and let Workerbee sync data automatically — see Integrations.
Ingest your own files
Bring data you already have. Three ways to do it, all landing in the same place:
- Get an upload link from your AI assistant or agent. Connect through either an LLM connector (Claude, ChatGPT, Gemini — see LLM Connectors) or an agent/MCP client (Claude Code, Cursor, or another MCP-compatible tool — see MCP Server). Ask it to create an upload session — you’ll get a link back. Open it in a browser and upload. Either path calls the same tool underneath, so pick whichever surface you’re already working in.
- Upload inside the Console. A direct upload screen in the Intelligence Console — no assistant required.
- Build a custom workflow. Use the Workerbee REST API and SDK to upload and ingest files from your own automation — no assistant or Console involved, just your own code.
- Let the Graph structure your data.
This isn’t indexing for retrieval — it’s where Workerbee actually earns its keep. Resumes, HRIS records, and system events get mapped onto a shared taxonomy of skills, roles, and evidence, not chunked into a vector store for an LLM to guess at on every question. That structuring is done once, up front, so every answer after this one is faster, cheaper, and backed by real evidence — instead of a fresh, expensive re-read of raw documents per query.
Poll the upload-session status until it reads
PROCESSED, then query. - Ask your first question.
Try any of these on your connected AI assistant. Each one looks like a simple question, but answering it requires comparing what a role actually requires against what every person in your workforce has actually demonstrated — across roles, departments, and job titles that were never written to match each other. That comparison is what the Graph is for; a keyword search over resumes can’t do it.
“Before we approve headcount, could our current internal workforce already cover our open roles?”A capability inventory rolled up from real evidence across every open role, not a headcount spreadsheet — so you know what you’re actually short on.Works at org scale — the Graph holds your whole workforce, not the ten people that fit in a prompt.Click to copy“What’s the one company-wide standard we’re evaluating this role against?”The Success Profile behind the role — the same one every candidate and every recruiter is held to, with its provenance.Grounded, not retrieved — one versioned standard, applied the same way to everyone.Click to copy“Rank every applicant for this role against the same standard, and show your work.”A full-pool ranking with capability-level evidence per candidate — never a black-box score.One framework, every decision — the same standard behind hiring, mobility, and workforce planning.Click to copy“What does the “Cloud Automation Engineer” standard actually require at our company, and where else does it apply?”One company-specific Success Profile for the occupation, reusable by every job posting mapped to it — plus whether any similarly-titled role should be mapped to it too, instead of drifting into its own standard.One framework, every decision — every job mapped to the occupation reads the same standard.Click to copy“Hiring managers say what this role needs has changed — what would that change in the Success Profile, and should we accept it?”A proposed update showing exactly what the new input would change. Nothing enters the standard until someone approves it, and the change is recorded with who, when, and why.Everything is logged — every change to the standard is reviewed and recorded, never silently absorbed.Click to copySee these worked through end to end, organized by who’s asking, in Examples.