Agentic Index
Ashby vs Greenhouse (2026)
Both vendors last verified
Ashby builds its own agents into the recruiting platform, while Greenhouse keeps its built in AI to notes, matching and screening and lets outside assistants act on its data through MCP. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Both are applicant tracking systems for growing and large companies, and both connect Claude, ChatGPT and Glean to hiring data. Ashby combines tracking, a sourcing CRM, scheduling and analytics in one product. Its Assistant advances applications, adds notes and emails candidates once a user confirms each step. Since September, custom agents can also run on a schedule and post results to Slack or email. Shopify, Notion and Ramp hire on Ashby, and Juniper Square made 300 hires with five recruiters. Greenhouse is built around structured hiring, with interview kits and scorecards for every role, and says more than 7,500 companies use it, DoorDash and HubSpot among them. Its MCP server lets an assistant update candidates and move applications, then stops for a person before a reject, a hire or a merge. Both hold SOC 2 Type 2 and run on AWS with no choice of region. Ashby's Foundations plan costs $400 a month for up to 100 employees, and Greenhouse quotes every tier. Choose Ashby for agents that work inside the product. Choose Greenhouse for structured hiring with governed outside access.
On the Agentic Index MCP platform ranking, neither Ashby nor Greenhouse clears the bar, which asks for all three interoperability capabilities documented in full. Neither documents model flexibility and routing in full. 142 of the 554 platforms it grades clear it. See the MCP platform ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Ashby and Greenhouse are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,165 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Ashby if
- You want one product for tracking, a sourcing CRM, scheduling and analytics rather than separate tools.
- Recruiters should ask an assistant to advance applications, add notes and email candidates, confirming each action before it runs.
- A recurring report, such as a weekly pipeline review, should run on a schedule and land in Slack or email.
- You are under 100 employees and want a published price, $400 a month on Foundations.
- Developers will build on a public API and connect AI tools through an MCP server available on every plan.
Choose Greenhouse if
- Your hiring method rests on interview kits and scorecards that put the same questions to every candidate.
- Recruiters already work in Claude, ChatGPT or Copilot Studio and should update Greenhouse from there, with rejections and hires held for confirmation.
- You want AI voice screens in 11 languages that never advance or reject a candidate on their own.
- Your stack is wide, and you want a marketplace of 520 partner integrations to draw from.
- Your compliance team asks for ISO 27001, ISO 27701 and ISO 42001 certificates as well as SOC reports.
| Feature | A Ashby |
G Greenhouse |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
AshbyIntegrations & Tool Calling Ashby offers a marketplace of more than 250 integrations spanning sourcing, assessment, video interview, job board and post hire tools. Google Workspace and Microsoft 365 connect for sending email and scheduling, with read and write access to calendars, and Ashby does not write or delete messages in users' inboxes. Workday and Juro integrations start and track workflows in those systems on the upper plans, Enterprise can share Ashby data to Snowflake and S3, and the Assistant's tools for emailing candidates and posting to Slack act through these connected systems. Sourceashbyhq.com/pricingread 2026-11-03 |
||
|
GreenhouseIntegrations & Tool Calling The integrations marketplace Greenhouse runs at integrations.greenhouse.com lists 520 integrations in four named classes, from HRIS and onboarding and job distribution to productivity and collaboration and candidate experience. It has Alliance Partner and Preferred Partner tiers and localization across more than thirty languages. These partner integrations act outward, in systems Greenhouse does not own. Job distribution publishes job posts to external boards, and HRIS and onboarding integrations push hires into the customer's HR system. E-signature, scheduled take-home tests and CLEAR ID verification each run in a third party service and return a result into the record. SMTP relay with self service custom SMTP sends through the customer's own mail infrastructure. Multi brand job boards and featured internal job posts extend the same publishing path. Sourceintegrations.greenhouse.com and greenhouse.com/pricingread 2026-09-08 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
AshbyWorkflow Orchestration The Ashby Assistant chains its tools inside one conversation, finding records, opening their details, then changing an application's stage, adding a note, emailing a candidate or filling a form, and it reports when every action is complete. Custom agents carry instructions, inputs, sources and allowed actions, and a scheduled agent repeats its read only work on a set cadence. Only one agent can be added to a request at a time, so each request is one agent working through several steps, with no workflow engine and no way to combine agents. Sourcedocs.ashbyhq.com/ashby-agentsread 2026-11-03 |
||
|
GreenhouseWorkflow Orchestration A workflow engine the customer configures runs hiring across several participants. Structured stages come with interview kits, scheduling automation weighs interviewer limits, preferences and working hours, and job and offer approval chains, bulk offers and candidate self scheduling round it out, with auto reject and auto advance adding unattended branching on Plus and above. No agent runs this sequence end to end. The Job Setup Assistant and Candidate Insights Assistant, promised for Q3 2026, are still listed as upcoming, and the sourcing piece of the Orchestrated Hiring Ecosystem launched on October 15, 2026 is in closed beta. Sourcegreenhouse.com/greenhouse-latest-featuresread 2026-11-03 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
AshbyTriggers & Channel Coverage Any custom agent can run on a recurring schedule and deliver its results to Slack channels, Slack users or email addresses without anyone starting it. Scheduled runs are read only, and the feature is in open public beta on all plans. People also call the Assistant and custom agents by @mention in Ashby's chat or from Slack, and fixed features such as AI application review and reply tracking respond to new applications and candidate replies. Agents cannot yet be started by an event. Sourceashbyhq.com/product-updates/scheduled-agentsread 2026-11-03 |
||
|
GreenhouseTriggers & Channel Coverage Event and scheduled triggers live in the workflow layer. Auto-reject and auto-advance rules act on an application without a person touching it, stage transitions fire on pipeline movement, and scheduling automation rules run off interview state. Scheduled take-home tests and candidate interview reminders fire on a schedule, not on a click. Channels run from email automation with SMTP relay and texting to a candidate portal at MyGreenhouse with self scheduling and scheduling links. They also include internal and multi brand job boards, e-signature and configurable candidate surveys, and Greenhouse Voice AI adds a voice channel for two way structured screening interviews at the top of the funnel. None of the AI capabilities starts on an event. A user or a connected outside assistant invokes Notetaker, the Analytics Chart Agent and MCP, so the rules that fire on events are classic ATS workflow automation. Auto-reject, auto-advance, email automation and texting are on Plus and above. Sourcegreenhouse.com/pricing and /greenhouse-latest-featuresread 2026-09-08 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
AshbyKnowledge Grounding & RAG The Assistant and custom agents search, filter and open the customer's own recruiting records, including candidates, applications, jobs, interview plans, feedback forms, interview transcripts, openings, notes, emails and texts, and every answer cites the underlying Ashby record. AI Talent Rediscovery matches those stored records against job criteria. The records persist in the customer's Ashby instance and reach far beyond what fits in a single conversation. SourceAshby Knowledge Base Ashby Agents (docs.ashbyhq.com/ashby-agents) and Ashby AI page (ashbyhq.com/ai)read 2026-09-08 |
||
|
GreenhouseKnowledge Grounding & RAG The customer's whole hiring estate lives in Greenhouse as the system of record, from candidates, prospects and applications to jobs, interview kits, scorecards, feedback, offers and activity history. That corpus persists between runs, scales across a hiring organization far past any context window and stays queryable. Greenhouse MCP and the Greenhouse in Claude plugin let approved assistants query it for daily briefs, pipeline reviews and debrief preparation, Chart Builder turns plain questions into charts over the reporting data, and Notetaker writes AI notes back onto scorecard questions. The announced Candidate Insights Assistant, designed to give answers linked to sources, is still listed as upcoming. Sourcegreenhouse.com/greenhouse-latest-featuresread 2026-11-03 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
AshbyMemory & State Persistence Previous Assistant conversations are kept under Recents and are searchable, and follow up questions within a conversation carry context. No memory that agents read across conversations is described. Custom agent instructions are settings the customer writes, and the candidate database is Ashby's own record of the hiring pipeline. SourceAshby Knowledge Base Ashby Agents (docs.ashbyhq.com/ashby-agents) and Ashby Assistant release 2026-05-07read 2026-09-08 |
||
|
GreenhouseMemory & State Persistence Greenhouse names no agent memory layer, no state its AI keeps across sessions and no retained preferences. Candidates and applications, scorecards and notes, offers and activity history persist in Greenhouse as the application's own data model, and deleting them deletes the hiring record itself. Notetaker transcribes an interview, the Chart Agent answers a question and MCP serves a query, and Greenhouse does not say that any of them retains anything between invocations. The Pro tier's data configuration controls cover session time-outs, restricted files and application limits, with no retention or deletion control over agent memory. Sourcegreenhouse.com/greenhouse-latest-features, /security and /pricingread 2026-09-08 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
AshbyHuman Oversight & Guardrails Every Ashby Assistant and custom agent action is held for the user's confirmation before it runs, with approve, reject and refine options in the chat, and email and note drafts are reviewed before they are sent or saved. Custom agents declare which actions they may take, scheduled agents run read only and take write actions only in a follow up the author starts, and admins opt in to each AI feature and can disable agents. Approval chains of several steps also route offers, jobs and openings, approvable from Slack, email and mobile. Sourceashbyhq.com/product-updates/ashby-assistantread 2026-11-03 |
||
|
GreenhouseHuman Oversight & Guardrails Greenhouse's MCP server holds five high stakes actions, rejecting or hiring an applicant, merging or anonymizing candidates and bulk revoking user permissions, and returns a plain language summary that a person must confirm before the action runs. Site Admins choose which data categories outside AI tools may read or write, every delete endpoint is blocked, and each tool acts under the user's own permissions. Greenhouse says its own AI never advances or rejects a candidate, and Voice AI scores can be overridden, though rule based auto advance and auto reject run without a confirmation step. Sourcesupport.greenhouse.io/hc/en-us/articles/53944054829083-greenhouse-mcp-security-faqread 2026-11-03 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
AshbySecurity, Identity & Governance SOC 2 Type II is audited annually, with 2024, 2025 and 2026 reports and a SOC 1 Type II on the trust center, available through a standard access request. Single sign on works through SAML or OIDC with the customer's identity provider, included on Plus and Enterprise and $100 a month on Foundations, and SCIM directory sync and custom permission roles come on Plus, which allows three roles, and Enterprise, which has no limit. Enterprise adds an organization wide audit log of about 150 event types. Agent actions run as the user under the permissions already set on each record, and a shared scheduled agent always runs with its author's permissions. Sourceashbyhq.com/resources/securityread 2026-11-03 |
||
|
GreenhouseSecurity, Identity & Governance Annual third party audits cover SOC 1 Type 2 and SOC 2 Type 2, and Greenhouse holds ISO 27001:2022, ISO 27701:2019 and ISO 42001:2023 certificates. It cites GDPR, CCPA and CPRA and the EU-U.S. DPF with its UK and Swiss extensions, and its trust center describes PCI DSS compliance through a self assessment. Single sign on comes with every tier, alongside SCIM provisioning, granular permissions and permissions approvals, and the audit log is Pro only. MCP access is set by Site Admins per data category and runs under each user's own role. Sourcegreenhouse.com/securityread 2026-11-03 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
AshbyObservability & Auditability After an Assistant action runs, each action expands to show its details in the conversation, every response cites the source records, and conversations are kept and searchable under Recents, so a user can see what the agent did and on what basis. Since October 2026 Enterprise customers get an organization wide audit log of about 150 event types, filtered by date, category and actor and retrievable through the API, with each entry naming the person or API key responsible. Ashby does not say that agent runs or prompts are among the logged events, so the record of agent work still lives in each user's chat. Sourcedocs.ashbyhq.com/ashby-agentsread 2026-11-03 |
||
|
GreenhouseObservability & Auditability An audit log ships on Pro, with an Audit Log API, and gives a retrievable record of user and system activity. Greenhouse's MCP documentation covers audit logging of MCP activity for customers who have the audit log, but Greenhouse does not say the log captures the prompts, inputs or reasoning behind an AI action, and customers without it have no such record. Reports, dashboards, AI report filters and the BI Connector measure hiring operations, not agent behavior. Sourcegreenhouse.com/securityread 2026-11-03 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
AshbyDeployment & Data Residency Ashby is hosted on Amazon Web Services, and its privacy policy says personal data is transferred to and processed in the United States. No region list, customer environment option or way to choose a location is published. Ashby holds Data Privacy Framework certification for those transfers, and the trust center's answer on where Ashby is hosted is available only through an access request. SourceAshby Security Overview 2024-12-20, Privacy Policy 2025-09-24, Trust Center (trust.ashbyhq.com); ashbyhq.com/resources/privacyread 2026-09-08 |
||
|
GreenhouseDeployment & Data Residency Greenhouse runs on Amazon Web Services and describes no region list, regional hosting choice, VPC, on premises install or customer tenant, so a customer cannot select where its data sits. Cross border transfers rely on the EU-U.S. Data Privacy Framework and its UK and Swiss extensions, which are legal transfer mechanisms rather than a choice of location. Sourcegreenhouse.com/securityread 2026-11-03 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
AshbyPrebuilt Agents, Templates & Packs Custom agents are written by the customer, generated from a plain language description or built by hand. A start from template option was announced with the release, though the agent creation wizard in the help center does not show it. The use case library holds prompts, and the named AI features, Application Review, Talent Rediscovery, Candidate Assistant and Notetaker, are switched on one at a time inside the product, two of them as paid add-ons. Ashby names no whole prebuilt agents. Sourceashbyhq.com/product-updates/ashby-assistantread 2026-11-03 |
||
|
GreenhousePrebuilt Agents, Templates & Packs Several separately named AI capabilities ship. Notetaker records and transcribes interviews and maps notes onto scorecard questions, Real Talent adds matching, fraud and spam detection and CLEAR identity checks, Chart Builder is in open beta, and Greenhouse MCP serves Site Admins. Greenhouse Voice AI, from the May 2026 Ezra AI Labs acquisition, is sold on its own with or without the ATS. Inside the ATS the capabilities come bundled by tier rather than as a set the customer picks from, there is no catalog of agents or templates to clone, and the Job Setup Assistant and Candidate Insights Assistant are still upcoming. Sourcegreenhouse.com/pricingread 2026-11-03 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
AshbyModel Flexibility & Routing Ashby says it uses third party AI models and names OpenAI, under a DPA, and customers and admins get no choice of model. The full subprocessor list and the trust center's answer on where the AI model is hosted are available only on request, so whether a second LLM provider is used is not published. Assembly AI and Recall AI handle transcription for the Notetaker add-on. SourceAshby AI page FAQ (ashbyhq.com/ai) and Trust Center subprocessor updatesread 2026-09-08 |
||
|
GreenhouseModel Flexibility & Routing Greenhouse runs off the shelf generative models alongside its own proprietary models, and its trust center lists Anthropic and OpenAI as subprocessors. Greenhouse chooses which model serves each feature, and customers get no model picker, admin setting or way to bring their own model. Choosing Claude, ChatGPT or another assistant to connect through MCP picks the outside tool that calls Greenhouse, not the models inside Greenhouse's own AI. Sourcetrust.greenhouse.comread 2026-11-03 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
AshbyAPIs, SDKs & MCP Extensibility Ashby's own platform can be called from outside through a public developer API at developers.ashbyhq.com, with versioned releases and endpoints added through 2026, and API access is listed on every plan. Customers generate and regenerate their own access keys, Enterprise adds an Offer Approval API and an audit log endpoint, and the Ashby MCP server, in beta on all plans, connects Claude, ChatGPT, Cursor, Glean and Gemini CLI to Ashby data. Sourceashbyhq.com/pricingread 2026-11-03 |
||
|
GreenhouseAPIs, SDKs & MCP Extensibility The Harvest API, now on version 3 with reference documentation at harvestdocs.greenhouse.io, lets customers and partners read and update candidates, applications, jobs and scorecards, and the older v1 and v2 versions were set for removal on August 31, 2026. Job Board, Onboarding, Ingestion, Assessment and Audit Log APIs sit alongside it, with a Business Intelligence Connector and a developer sandbox on Pro. Greenhouse MCP, built on Harvest v3 with OAuth sign in, lets approved tools such as Claude, ChatGPT, Microsoft Copilot Studio, Glean, Amazon Q and Grok read and write Greenhouse data under the user's permissions, and the Greenhouse in Claude plugin, in open beta since October 22, 2026, adds hiring skills on top. Sourcegreenhouse.com/apiread 2026-11-03 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
AshbyTesting, Debugging & Optimization Customers get no harness, test cases, quality gate or optimization loop for the Assistant or custom agents. Agent management in the help center covers creating, editing and disabling agents and a step that generates a draft, and the sandbox instance on the pricing table is a separate environment for testing configuration outside production. Ashby runs FairNow bias audits and lists Braintrust, an AI observability and evaluation service, as a subprocessor, both part of its own model evaluation and engineering work. Sourcedocs.ashbyhq.com/ashby-agentsread 2026-11-03 |
||
|
GreenhouseTesting, Debugging & Optimization A developer sandbox with sandbox sync ships on the Pro tier, so a customer can try configuration and integration changes before they reach production. Greenhouse says all Voice AI scoring can be calibrated and will improve over time, and that the customer sets the criteria for what makes a candidate great. On Talent Matching, recruiters choose which criteria to prioritize and the relative weight of each factor. Greenhouse names no holdout set, scored test cases or comparable results. A bias audit statement covers Talent Matching. Warden AI runs disparate impact analysis and demographic variable testing across ten protected classes on its own proprietary dataset, and the results go to a single public Greenhouse dashboard. The audit tests the product in general, not the customer's deployed instance on the customer's data. It is aligned to NYC LL-144, Colorado SB205 and California FEHA, which are legal mandates. Reports, dashboards, AI report filters and the BI Connector measure hiring operations, not agent behavior. Sourcegreenhouse.com/pricing, /bias-audit-statement and /greenhouse-latest-featuresread 2026-09-08 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
AshbyBrowser & Computer Use The agents act through Ashby's own tools, and no browser, desktop or computer control is described. The sourcing Chrome extension is for recruiters, who use it to add candidates from a web page into Ashby. SourceAshby AI page (ashbyhq.com/ai), pricing feature table, Knowledge Base Ashby Agentsread 2026-09-08 |
||
|
GreenhouseBrowser & Computer Use The Prospecting Chrome plugin ships on all three tiers as part of Sourcing and CRM, alongside prospect creation and prospect pools. With it, the recruiter finds the profile and opens the page, and the plugin captures what is on it into Greenhouse. The plugin does not navigate, click or fill on its own. Greenhouse names no hosted or local browser, desktop session, or remote or local computer control. Sourcegreenhouse.com/pricingread 2026-09-08 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | A Ashby |
G Greenhouse |
|---|---|---|
|
Entry price Lowest public entry point |
From $400/mo | Quote only |
|
Pricing confidence How public the numbers are |
Public, partial | Contact only |
|
Billing Primary billing axis |
Hybrid. The plan price is set by company size band, not by recruiter seats, and SMS, sourcing email lookups and AI Credits carry stated allowances with paid extras beyond them. | A custom quote shaped by the plan, hiring volume and organizational complexity. The unit hiring volume is counted in is not defined. |
|
Variable cost Workload / overage exposure |
Low variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
No free tier
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Sales call |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Greenhouse
-
· Integrations
Recruiters and hiring managers can now check pipelines, prepare for debriefs and draft scorecards inside Claude with Greenhouse in Claude, a plugin built on Greenhouse MCP.
Source -
· MCP / tool calling / API
Greenhouse expanded access to its Model Context Protocol (MCP) beyond Site Admins, enabling Job Admins, coordinators, and hiring managers to run AI workflows against platform data.
Source
Neither vendor offers a choice of where data is hosted. Ashby does not say its audit log records agent runs, and Greenhouse logs MCP activity only for customers on its audit log. Ashby publishes no price for Plus or Enterprise, keeps custom and scheduled agents in open beta and has not said how many AI Credits they will use at general availability. Greenhouse publishes no price for any tier or for Voice AI, and two assistants it promised for Q3 2026 have not launched. Ask Ashby for a Plus quote and the credit cost of its agents. Ask Greenhouse for a quote by tier and a launch date for its Job Setup and Candidate Insights assistants.
More comparisons with Ashby or Greenhouse
Other matchups in enterprise operations agents
Not the pairing you were after? These compare a different set of enterprise operations agents on the same 14 capabilities.