Skip to content

Si: AI agent for Greenhouse

Connect Greenhouse and ask Si about hiring: candidates, offers, offer acceptance rate, hires and average time to hire. DataxLand loads candidates, applications, jobs and offers; candidate names, emails and phone numbers are hashed on ingest. Si proposes how to read your hiring stages, you approve, then Si answers by job, department or period, in aggregate numbers only.

Free plan with no time limit · No card required · Sample workspace ready in minutes

Ask Si about Greenhouse

Example questions Si answers from the metrics below, once the source is connected and the model approved.

  • “How many candidates did each job get this month?”
  • “How does offer acceptance rate this quarter compare with last quarter?”
  • “What is average time to hire by department this year?”
  • “Show hires by month for the last six months.”
  • “How many offers did we make this month?”
  • “Why did average time to hire go up this quarter?”

Si answers with these metrics

MetricDefinitionUnit
ApplicantsNumber of candidates who applied in the period (by application date).Count
Job offers sentNumber of candidates sent a job offer in the period (by offer date).Count
Offer acceptance rateOffers accepted divided by offers sent in the period.= hr_offers_accepted / Job offers sentRatio (%)
New hiresNumber of employees with a start date in the period.Count
Average time to hire (days)Average number of days from application to offer date for hired candidates, by offer date.= hr_hire_days_total / hr_offers_acceptedNumber

How Si answers

A semantic layer, no free-form SQL

Si picks metrics, dimensions, filters and periods; DataxLand builds the query from versioned definitions; Si runs no SQL of its own when answering.

A confidence level on every number

Standard (pack metric), Approved (workspace metric checked before use), Unconfirmed (exploratory answer, clearly labelled).

One tool set everywhere

In the app, Slack, Telegram, Microsoft Teams or MCP, Si uses the same read-only tools and your permissions in the workspace.

Where to ask Si

In the app

Ask inside the workspace in the language you use; Si answers in the same language, with the metric source and confidence level.

Slack, Telegram and Teams

Link your account with a one-time code; ask in a private chat or a group bound to the workspace.

MCP

Create an expiring, revocable token (plans with MCP) so Claude, Cursor or your own agent call the same tools.

Get started

  1. 1

    Connect Greenhouse

    Choose Add source → Greenhouse and paste the account's Harvest API key (read access).

  2. 2

    Review Si's proposal

    Si proposes how to read candidates, jobs and offers and maps them to the pack's standard model; you fix the highlighted fields, answer the multiple-choice questions and approve the build.

  3. 3

    Ask Si

    Ask in the app, connect Slack or Telegram with a one-time code, or create an MCP token for Claude, Cursor or your own agent.

Frequently asked questions

Does Si change anything in Greenhouse?

No. Si only reads the workspace's approved metrics; there is no tool that writes to Greenhouse, and Si never runs SQL it wrote itself on your data when answering.

Does Si return personal data about candidates?

No. Personal data columns are hashed on ingest and masked before they reach Si; no dashboard, API or MCP returns the original values.

Can I use Si with Claude or Cursor?

Yes, through the DataxLand MCP server with a token that expires and can be revoked. MCP tokens come with the Small Business plan and above; on Starter you ask Si in the app, Slack and Telegram.

Dashboard templates that use this source

Connect Greenhouse →Use Si over MCP →

Ask Si about Greenhouse today

Free plan with no time limit · No card required · Sample workspace ready in minutes