Workable connector for AI agents

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

CALL ANY TOOL

66 tools for recruiting and HR in Workable: candidates, jobs, stages, ratings, offers, requisitions, events, employees, time off, and time tracking.

workable_candidate_activities_list

List candidate activities

List the activity stream of a candidate, such as comments, stage moves, ratings and emails. Returns an activities array with each activity's action, body, member, stage and created_at. Use workable_candidate_activities_list for one candidate's history. Use workable_job_activities_list for a whole job.

Parameters

Name

Type

Required

Description

candidate_id

string

Required

ID of the candidate. Get it from the id field of workable_candidates_list or workable_candidate_get. Example: "ce4da98".

actions

string

Optional

Only return these activity actions, comma-separated (for example comment,moved).

limit

integer

Optional

Number of activities to return per page. Workable defaults to 50. Example: 25.

max_id

string

Optional

Return activities with an ID less than or equal to this ID. Example: "2a9b4c".

since_id

string

Optional

Return activities with an ID greater than or equal to this ID. To fetch the next page, copy the since_id value from the paging.next URL of the previous response. Example: "2a9b4c".

updated_after

string

Optional

Only return activities updated at or after this date, ISO 8601. Example: "2024-01-01T00:00:00Z".

workable_candidate_comment_create

Create candidate comment

workable_candidate_copy

Copy candidate

workable_candidate_custom_attribute_update

Update candidate custom attribute

workable_candidate_disqualify

Candidate disqualify

workable_candidate_get

Get candidate

workable_candidate_rating_create

Create candidate rating

workable_candidate_rating_upsert

Upsert candidate rating

workable_candidate_relocate

Candidate relocate

workable_candidate_update

Update candidate

Update a candidate's profile fields such as name, email, phone, resume, education, experience, tags or social profiles. Returns the updated candidate. Fields you leave out keep their current values, but any list field you send (education, experience, tags, social profiles) replaces the existing list. Use workable_candidate_tags_update to change only tags. Use workable_candidate_move to change the stage.

Parameters

Name

Type

Required

Description

candidate_id

string

Required

ID of the candidate. Get it from the id field of workable_candidates_list or workable_candidate_get. Example: "ce4da98".

address

string

Optional

Candidate's postal address as a single string.

cover_letter

string

Optional

Candidate's cover letter as plain text.

education_entries

array

Optional

Education history. Each entry has a degree, school, field of study, and start and end dates (YYYY-MM-DD). On update this replaces all existing entries; an empty array deletes them. Example: [{"degree": "B.S.", "school": "University of Chicago", "field_of_study": "Economics", "start_date": "2004-09-01", "end_date": "2007-06-30"}].

string

Optional

Candidate's email address. Example: "jane.doe@example.com".

experience_entries

array

Optional

Work history. Each entry has a title, company, industry, summary, start and end dates (YYYY-MM-DD) and a current flag. On update this replaces all existing entries; an empty array deletes them. Example: [{"title": "Sales Director", "company": "Vox Mobile", "start_date": "2011-03-01", "end_date": "2014-03-30", "current": false}].

firstname

string

Optional

Candidate's first name. Example: "Jane".

headline

string

Optional

One-line professional headline for the candidate. Example: "Senior Backend Engineer".

image_source

string

Optional

Where the photo came from. Use "candidate" if you want image_url populated in later API responses.

image_url

string

Optional

Public URL of the candidate's photo. Workable downloads it. Set image_source to "candidate" so later responses return image_url.

lastname

string

Optional

Candidate's last name. Example: "Doe".

phone

string

Optional

Candidate's phone number. Example: "+1-555-010-0100".

resume

object

Optional

Resume file sent inline: an object with the file name and the file content encoded in base64. Use this or resume_url, not both. Example: {"name": "jane-doe.pdf", "data": "JVBERi0xLjQK..."}.

resume_url

string

Optional

Public URL of the candidate's resume (.pdf, .doc, .docx or .rtf). Workable downloads the file from this URL. Use this or resume, not both.

skills

array

Optional

Candidate's skills as a list of strings. Example: ["Go", "PostgreSQL"].

social_profiles

array

Optional

Social profiles. Each entry has a type (for example twitter or linkedin), a display name, a username and a url. On update this replaces all existing profiles. Example: [{"type": "linkedin", "name": "LinkedIn", "url": "https://www.linkedin.com/in/janedoe"}].

summary

string

Optional

Profile summary for the candidate, as free text.

tags

array

Optional

Tags to attach to the candidate. Example: ["referral", "senior"]. On update this replaces all existing tags; an empty array removes them.

texting_consent

string

Optional

Candidate's texting consent. One of forced or declined. One of: `forced`, `declined`.

workable_candidates_list

List candidates

workable_departments_list

List departments

workable_employee_documents_add

Add employee documents

workable_employee_fields_list

List employee fields

workable_employee_get

Get employee

workable_event_get

Get event

workable_events_list

List events

workable_job_get

Get job

workable_job_members_list

List job members

workable_job_recruiters_list

List job recruiters

workable_jobs_list

List jobs

workable_offer_reject

Reject offer

workable_recruiters_list

List recruiters

workable_requisition_create

Create requisition

Create a requisition for planned headcount. Requires Workable Hiring Plan. Returns the full requisition object, including its id, code and state. Use workable_requisition_create to open headcount. Use workable_requisition_update to change one. Get member IDs with workable_members_list.

Parameters

Name

Type

Required

Description

code

string

Required

Code for the new requisition. Sent to Workable as code.value. Example: "REQ-001".

hiring_manager_id

string

Required

Member ID of the hiring manager.

job_title

string

Required

Title of the job the requisition is for. Example: "Backend Engineer".

member_id

string

Required

ID of the Workable member creating the requisition. Workable records the action under this member and requires it for account-level tokens. Find member IDs with workable_members_list. Example: "13e0eb0e".

owner_id

string

Required

Member ID of the requisition owner.

plan_date

string

Required

Planned month for the hire, in YYYY-MM format. Example: "2024-06".

city

string

Optional

City of the location. Example: "Austin".

country_code

string

Optional

Two-letter ISO country code of the location. Example: "US".

department_id

string

Optional

Department ID, from workable_departments_list.

employment_type

string

Optional

Employment type: Full-time, Part-time, Contract, Temporary or Other. One of: `Full-time`, `Part-time`, `Contract`, `Temporary`, `Other`.

experience

string

Optional

Experience level: Not Applicable, Internship, Entry Level, Associate, Mid-senior Level, Director or Executive. One of: `Not Applicable`, `Internship`, `Entry Level`, `Associate`, `Mid-senior Level`, `Director`, `Executive`.

job_id

string

Optional

ID of an existing job to link the requisition to.

location_string

string

Optional

Location as a single display string. Example: "Austin, Texas, United States".

notes

string

Optional

Notes on the requisition.

reason

string

Optional

Reason for the requisition: new_hire, replacement or backfill. One of: `new_hire`, `replacement`, `backfill`.

requisition_attributes

array

Optional

Custom requisition attribute values. Each entry identifies the attribute and gives its value; get the attributes with workable_requisition_custom_attributes_list. Example from the Workable docs: [{"slug": "cost_center", "value": "Engineering"}].

salary_currency

string

Optional

Currency of the salary. Example: "USD".

salary_frequency

string

Optional

How often the salary is paid, for example year or month.

salary_from

string

Optional

Lower bound of the salary range. Example: "80000".

salary_to

string

Optional

Upper bound of the salary range. Example: "100000".

state_code

string

Optional

State or region of the location. Example: "TX".

workable_requisition_custom_attributes_list

List requisition custom attributes

workable_requisition_get

Get requisition

workable_requisition_update

Update requisition

Update fields on an existing requisition, such as owner, hiring manager, location, salary or plan date. Requires Workable Hiring Plan. Returns the full updated requisition object. Only the fields you send change. Use workable_requisition_get or workable_requisitions_list to find the requisition first.

Parameters

Name

Type

Required

Description

member_id

string

Required

ID of the Workable member editing the requisition. Workable records the action under this member and requires it for account-level tokens. Find member IDs with workable_members_list. Example: "13e0eb0e".

requisition_id

string

Required

ID of the requisition (the id field, not the code), from workable_requisitions_list.

city

string

Optional

City of the location. Example: "Austin".

country_code

string

Optional

Two-letter ISO country code of the location. Example: "US".

employment_type

string

Optional

Employment type: Full-time, Part-time, Contract, Temporary or Other. One of: `Full-time`, `Part-time`, `Contract`, `Temporary`, `Other`.

experience

string

Optional

hiring_manager_id

string

Optional

Member ID of the new hiring manager.

location_string

string

Optional

Location as a single display string. Example: "Austin, Texas, United States".

notes

string

Optional

Notes on the requisition.

owner_id

string

Optional

Member ID of the new owner.

plan_date

string

Optional

Planned month for the hire, in YYYY-MM format.

reason

string

Optional

Reason for the requisition: new_hire, replacement or backfill. One of: `new_hire`, `replacement`, `backfill`.

salary_currency

string

Optional

Currency of the salary. Example: "USD".

salary_frequency

string

Optional

How often the salary is paid, for example year or month.

salary_from

string

Optional

Lower bound of the salary range. Example: "80000".

salary_to

string

Optional

Upper bound of the salary range. Example: "100000".

state_code

string

Optional

State or region of the location. Example: "TX".

workable_stages_list

List stages

workable_time_entry_create

Create time entry

workable_timeoff_categories_list

List timeoff categories

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);

// Workable tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["workable"], toolNames: [
    "workable_candidates_list",
    "workable_candidate_move",
    "workable_offer_approve"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Move Jordan Lee to the Offer stage for the Account Executive job" }] });

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: ["workable"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Move Jordan Lee to the Offer stage for the Account Executive job" }],
  tools,
});

// Execute the tool call with the user's vaulted Workable access token
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: ["workable"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Move Jordan Lee to the Offer stage for the Account Executive job" }],
  tools,
});

// Tool call runs with the user's vaulted Workable access token
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: ["workable"] }, pageSize: 100,
});

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

await agent.run("Move Jordan Lee to the Offer stage for the Account Executive job");

Try these prompts

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

Candidates

Copy the prompt

Copied

List candidates in the Interview stage for the Account Executive job.

Copy the prompt

Copied

Move Jordan Lee to the Offer stage.

Copy the prompt

Copied

Disqualify Sam Lee from the Data Analyst job with a note.

Hiring team

Copy the prompt

Copied

Rate Priya Shah as a strong yes with a comment from today's interview.

Copy the prompt

Copied

Approve the pending offer for Maria Lopez.

Copy the prompt

Copied

Show interviews scheduled for this week.

Copy the prompt

Copied

What are Alex Rivera's time off balances?

Copy the prompt

Copied

Request 2 days of vacation for Dana Kim next Thursday and Friday.

Copy the prompt

Copied

List time off requests from this month.

SEE HOW AUTH WORKS

Each user connects their own Workable access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Workable

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

Workable

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

Workable

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

Workable

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.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Workable access token looks fine in a demo. In production every stage move and offer approval 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 token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Workable 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 Workable as the user or through a shared token?

As the user. Each user connects their own Workable access token once, and Scalekit sends it with every call. Stage moves, ratings, and approvals the agent records are attributed to that user in your audit trail, not a shared service account.

Where is the Workable access token stored?

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

Can I limit what the agent does in Workable?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the candidate and job read tools without workable_candidate_disqualify or workable_offer_approve. No Workable tool deletes data. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Workable 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.

Do some Workable tools need a user-level access token?

Yes. workable_offer_get, workable_offer_approve, and workable_offer_reject work only with a user-level access token, and so do the performance review template tools. The requisition tools also require the Workable Hiring Plan.