Ashby connector for AI agents

Tools your recruiting agent reaches for on Ashby, scoped per user.

CALL ANY TOOL

98 tools for recruiting in Ashby: search candidates and applications, change stages, schedule interviews, submit feedback, manage jobs and postings, and start offers.

ashby_application_create

Create application

Create an application that considers an existing Ashby candidate for a job, optionally choosing the interview plan, starting stage, source and credited user. Returns the created application record including its id and current interview stage. Use after ashby_candidate_create to put a candidate into a job's pipeline. Use ashby_application_transfer to move an existing application to another job. Requires the candidatesWrite permission on the Ashby API key.

Parameters

Name

Type

Required

Description

candidate_id

string

Required

The id of the candidate to consider for a job. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

job_id

string

Required

The id of the job to consider the candidate for. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

application_history

array

Optional

Optional history events to create the application with. Each event needs the stage id, a stage number (0 for the first; the highest number is the current stage) and the time the application entered that stage; an archive reason id is needed when the stage is of type Archived. Example: [{"stageId": "e9ed20fd-d45f-4aad-8a00-a19bfba0083e", "stageNumber": 0, "enteredStageAt": "2024-01-15T10:30:00Z"}].

created_at

string

Optional

An ISO date string to set the application's createdAt timestamp. Defaults to the time the call was made when not provided. Example: 2022-08-12T20:29:56.964Z.

credited_to_user_id

string

Optional

The id of the user the application will be credited to. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

interview_plan_id

string

Optional

The id of the interview plan to place the application in. If none is provided, the default interview plan is used. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

interview_stage_id

string

Optional

The interview stage to place the application in. Use a stage id from ashby_interview_stages_list, or the value FirstPreInterviewScreen for the first pre-interview screen stage. Defaults to the first Lead stage. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

source_id

string

Optional

The source to set on the application being created. Example: e9ed20fd-d45f-4aad-8a00-a19bfba0083e.

ashby_application_feedback_list

List application feedback

ashby_application_feedback_submit

Submit application feedback

ashby_application_get

Get application

ashby_application_hiring_team_member_add

Add application hiring team member

ashby_application_hiring_team_member_remove

Remove application hiring team member

ashby_application_update

Update application

ashby_applications_list

List applications

ashby_candidate_note_create

Create candidate note

ashby_candidate_notes_list

List candidate notes

ashby_candidates_list

List candidates

ashby_candidates_search

Search candidates

ashby_custom_field_value_set

Set custom field value

ashby_department_get

Get department

ashby_departments_list

List departments

ashby_interview_briefing_get

Get interview briefing

ashby_interview_events_list

List interview events

ashby_interview_schedule_cancel

Cancel interview schedule

ashby_interview_stages_list

List interview stages

ashby_interviewer_pool_get

Get interviewer pool

ashby_job_boards_list

List job boards

ashby_job_create

Create job

ashby_job_posting_get

Get job posting

ashby_job_update

Update job

ashby_locations_list

List locations

ashby_offer_process_start

Start offer process

ashby_opening_create

Create opening

ashby_opening_get

Get opening

ashby_openings_search

Search openings

ashby_projects_list

List projects

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Ashby tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ashby"], toolNames: [
    "ashby_candidates_search",
    "ashby_application_stage_change",
    "ashby_interview_schedule_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Move Maya Chen to the onsite stage and schedule her technical interview for Thursday" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ashby"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Move Maya Chen to the onsite stage and schedule her technical interview for Thursday" }],
  tools,
});

// Execute the tool call with the user's vaulted Ashby API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ashby"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Move Maya Chen to the onsite stage and schedule her technical interview for Thursday" }],
  tools,
});

// Tool call runs with the user's vaulted Ashby API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ashby"] }, pageSize: 100,
});

const agent = new Agent({
  name: "recruiting_agent",
  model: "gemini-2.5-pro",
  instruction: "Ashby tools scoped to this user",
  tools,
});

await agent.run("Move Maya Chen to the onsite stage and schedule her technical interview for Thursday");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Ashby tool. Click to copy, paste into your agent, done.

Candidates

Copy the prompt

Copied

Find the candidate with email maya.chen@example.com.

Copy the prompt

Copied

Add a note to Maya Chen's profile about her salary expectations.

Copy the prompt

Copied

Add Maya Chen to the Q4 backend sourcing project.

Pipeline

Copy the prompt

Copied

Move Maya Chen's application to the onsite stage.

Copy the prompt

Copied

Schedule a 45-minute technical interview for Maya Chen on Thursday.

Copy the prompt

Copied

Show the feedback submitted on Maya Chen's application.

Jobs and offers

Copy the prompt

Copied

Create a Product Designer job in the London office.

Copy the prompt

Copied

Unpublish the Senior Backend Engineer posting.

Copy the prompt

Copied

Start the offer process for Maya Chen.

SEE HOW AUTH WORKS

Each user connects their own Ashby API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Ashby

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Ashby

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Ashby

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Ashby

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other recruiting and HR connectors.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Ashby API key looks fine in a demo. In production every stage change and offer looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Ashby today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Ashby as the user or through a shared key?

As the user. Each user connects their own Ashby API key once, and Scalekit sends it with every call. Audit logs attribute every stage change, note, and offer to that user, not a shared service account.

Where is the Ashby API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Ashby?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the search and list tools without ashby_offer_create or ashby_interview_schedule_cancel. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Ashby access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent submit interview feedback in Ashby?

Yes. ashby_application_feedback_submit submits a feedback form for an application, and ashby_application_feedback_request_create asks an Ashby user to submit theirs. ashby_application_feedback_list returns the feedback already submitted.