ATS sits alone in Greenhouse.
Judging candidate screening also takes assess qualifications, and that never shares a screen with Greenhouse.
Build a Candidate Screening Agent withGreenhouse and Ashby
People ops teams run hiring decisions on stale, scattered data: Ashby and Greenhouse each hold a piece, none hold the whole. Manual screening takes 20+ minutes per resume.
Candidate Screening runs on role data split across 2 tools.
The hiring decision pays for it.
The hiring decision pays for it.
Ashby holds what Greenhouse misses.
Assess qualifications lives in Ashby, cut off from ats, so candidate screening guesses at the link.
Ashby knows before you do.
Rank candidates lands in Ashby hours early. Too far from Greenhouse to change the hiring decision in time.
Under The Hood
Two sources, one query: candidate screening pulls Greenhouse and Ashby pre-wired. Already connected.
01
Read parse resumes from Greenhouse (applicant tracker)
ATS
02
Query assess qualifications from Ashby (applicant tracker)
Assessment Platforms
03
output
Agent-ready output
One worklist: Parse resumes, assess qualifications, rank candidates, identify red flags, recommend next steps. Ranked by priority, top risks flagged, a next step on each.
The Context Store
ATS from Ashby and Greenhouse, pre-joined before the agent runs.
Ashby and Greenhouse get reconciled up front for candidate screening: ATS, Assessment Platforms, Background Check Services, Communication Tools mapped to a single role view instead of 2 separate APIs.
Your agent queries one surface instead of three APIs. Faster responses, lower cost per query, and results that work because the relationships were built before you asked the question.
ROLE-LEVEL JOINSPEOPLE OPS SCHEMANO GLUE CODE
The Prompt
Copy. Paste.
a Candidate Screening Agent
Two steps. Your data, your results, under 60 seconds.
01install
Connect the Airbyte Agent MCP02copy and run
Help me turn Greenhouse and Ashby into a single hiring decision I can act on.
SETUP
The Agent MCP is connected to 2+ systems; query them directly, no API code.
WORKFLOW
list connectors -> link Greenhouse and Ashby -> pull ATS, Assessment Platforms, Background Check Services, Communication Tools -> join on the role key -> analyze. An unlinked tool returns a self-describing prompt; a one-time browser auth and retry.
TASK
Parse resumes, assess qualifications, rank candidates, identify red flags, recommend next steps, then give me a single worklist: sorted by what needs me first, each line with the why and the move.The Outcome
Parse resumes on demand: 2 hours of effort, ~60 seconds of agent.
10x
Faster
~10x. Candidate screening drops from a 2-hour chore to one query.
90%
Cheaper to run
90% less spend: no glue code; it runs on your existing 2-tool stack to parse resumes.
2 -> 1
Tools, one query
2 -> 1: candidate screening answers Greenhouse and Ashby in a single query.
Based on internal benchmarks comparing Context Store queries to sequential API calls across equivalent datasets.
01 · Output
Priority scoring
A 1-10 score on each role means the urgent ATS rises to the top of candidate screening on its own.
02 · Signal
Reality-check flags
When your applicant tracker and Greenhouse disagree on parse resumes, the gap is flagged. Not averaged into a guess.
03 · Context
Inline evidence
Assess qualifications from Ashby sits beside each item, letting you parse resumes without switching tabs.
04 · Action
Next action per item
Candidate Screening closes each role with a recommendation. Who to contact and what to send. Ready to run.
05 · Brief
Worklist-ready
The worklist arrives meeting-ready: ATS first, sources attached, Greenhouse and Ashby reconciled.
Keep going. More people ops agents from here
view All use casesGift Card Giveaway Agent
Your hiring decision is only as fresh as the slowest tab. Manual distribution wastes time. Yet the inputs sit split across Stripe + Shopify + Salesforce.
Recruiting Agents
People ops teams run hiring decisions on stale, scattered data: LinkedIn Ads / Salesforce / Greenhouse each hold a piece, none hold the whole. Top candidates are off market in 10 days.
IT helpdesk triage Agent
The data for your hiring decision already exists in Confluence + Notion. The problem is no one view joins it. VIP users require priority response.
Common questions
Didn't find your answer? Please don't hesitate to reach out.
Can Candidate Screening run on a schedule?
Yes, schedule it and the worklist arrives before the hiring decision starts, so parse resumes happens hands-free.
What Greenhouse data does Candidate Screening touch?
Just ATS, plus Assessment Platforms, Background Check Services, Communication Tools, via Greenhouse's scoped permissions. Candidate screening copies nothing outside your stack.
How fresh is the role data Candidate Screening uses?
Live, it reads Greenhouse at query time, so the worklist shows ATS as of now, not last night.
How do I build a candidate screening agent with Greenhouse and Ashby?
Link Greenhouse and Ashby in Airbyte's Agent MCP, paste the prompt above, and candidate screening reads all 2 sources at once to parse resumes.
Ashby and Greenhouse are connected. Point candidate screening at them.
47+ connectors including Greenhouse and Ashby are ready. Give candidate screening the access to parse resumes.
