Job Applications Pipeline

Automate job applications across multiple postings on any job portal. This cookbook creates an agent that logs into a job portal, searches for relevant positions based on your resume, extracts job listings, and applies to each one with AI-generated responses tailored to the role.

What you’ll build

An agent that:

Parses your resume PDF to extract structured information
Logs into a job portal using saved credentials
Searches for relevant jobs based on your resume
Extracts a list of matching job postings
For each job: extracts details, generates tailored answers, and submits the application

Prerequisites

Skyvern Cloud API key: Get one at app.skyvern.com/settings → API Keys

Install the SDK:

pip install skyvern

npm install @skyvern/client

Set your API key:

export SKYVERN_API_KEY="your-api-key"

Sample Job Portal

We’ll use Job Stash, a fake job board website created for agent automation testing. Change job_portal_url to use your job portal’s URL.

Field	Value
URL	https://job-stash.vercel.app
Login email	demo@manicule.dev
Login password	helloworld

Step 1: Store credentials

Before defining the agent, store the login email and password Skyvern will use. This makes sure your passwords are never stored in the shareable agent definition and never sent to LLMs.

Cloud UI
API / SDK

Open Credentials

Go to Credentials in the sidebar. Choose Password after clicking on + Add.

Creating a password credential on Skyvern

Create a credential

Click Create Credential. Set the name to Job Stash, add login page URL, and enter the username (demo@manicule.dev) and password (helloworld). Click Save.

Fill username and password to add a credential to Skyvern

Copy the credential ID

Copy the credential ID (here: cred_504284876895871734). You’ll use this when configuring the agent.

import os
import asyncio
from skyvern import Skyvern

async def main():
    client = Skyvern(api_key=os.getenv("SKYVERN_API_KEY"))

    credential = await client.create_credential(
        name="Job Portal",
        credential_type="password",
        credential={
            "username": "demo@manicule.dev",
            "password": "helloworld"
        }
    )

    print(f"Credential ID: {credential.credential_id}")
    # Save this ID for your workflow: cred_xxx

asyncio.run(main())

import { SkyvernClient } from "@skyvern/client";

const client = new SkyvernClient({
  apiKey: process.env.SKYVERN_API_KEY,
});

const credential = await client.createCredential({
  name: "Job Portal",
  credential_type: "password",
  credential: {
    username: "demo@manicule.dev",
    password: "helloworld",
  },
});

console.log(`Credential ID: ${credential.credential_id}`);

curl -X POST "https://api.skyvern.com/v1/credentials" \
  -H "x-api-key: $SKYVERN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Job Portal",
    "credential_type": "password",
    "credential": {
      "username": "demo@manicule.dev",
      "password": "helloworld"
    }
  }'

Step 2: Create a new agent

Cloud UI
API / SDK

Create the agent

Go to Agents → Create Agent. Name it “Search and Apply for Jobs Workflow”.

Create a new agent from Skyvern Dashboard

An agent definition is a JSON or YAML file that describes your entire agent: its metadata, parameters, and blocks. Create a file called job-application-workflow.yaml (or .json) with the following template:

{
  "title": "Search and Apply for Jobs Workflow",
  "description": "Search for jobs on any portal, extract listings, generate tailored answers with AI, and submit applications automatically.",
  "proxy_location": "RESIDENTIAL",
  "workflow_definition": {
    "version": 1,
    "parameters": [],
    "blocks": []
  }
}

title: Search and Apply for Jobs Workflow
description: "Search for jobs on any portal, extract listings, generate tailored answers with AI, and submit applications automatically."
proxy_location: RESIDENTIAL
workflow_definition:
  version: 1
  parameters: []    # <-- filled in below
  blocks: []        # <-- filled in Step 3

We’ll populate parameters and blocks in the sections that follow.

Set parameters

Parameters are the inputs your agent accepts. Defining them upfront lets you reuse the same agent against different job portals.

Cloud UI
API / SDK

On the Start node, add the following parameters:

Parameter	Type	Notes
`resume`	File URL	URL to your resume PDF
`credentials`	Credential ID	Select the credential you created in Step 1
`job_portal_url`	String	Job portal login URL

Setting input parameters in an agent in Skyvern

Replace the empty parameters array with the following:

"parameters": [
  { "key": "resume", "parameter_type": "workflow", "workflow_parameter_type": "file_url" },
  {
    "key": "credentials",
    "parameter_type": "workflow",
    "workflow_parameter_type": "credential_id",
    "default_value": "your-credential-id"
  },
  {
    "key": "job_portal_url",
    "description": "URL of the job portal",
    "parameter_type": "workflow",
    "workflow_parameter_type": "string"
  }
]

parameters:
  - key: resume
    parameter_type: workflow
    workflow_parameter_type: file_url
  - key: credentials
    parameter_type: workflow
    workflow_parameter_type: credential_id
    default_value: your-credential-id     # <-- replace this
  - key: job_portal_url
    description: URL of the job portal
    parameter_type: workflow
    workflow_parameter_type: string

Step 3: Add agent blocks

The agent chains together several blocks to automate the full job application process:

PDF Parser block: Extracts structured data from your resume
Login block: Authenticates to the job portal using stored credentials
Navigation block: Searches for relevant jobs based on your resume
Extraction block: Extracts a list of job postings from search results
For loop (Go to URL + Extraction + Action + Extraction + Text Prompt + Navigation): Iterates over each job to extract details, generates tailored answers using an LLM, and submits the application.

In the Cloud UI, click the + button after the Start node to add blocks sequentially. For SDK users, add each block to the blocks array in your agent definition file.

PDF Parser block

The pdf_parser block extracts structured information from your resume PDF. Skyvern uses AI to identify your name, contact info, work experience, education, and skills.

Cloud UI
API / SDK

Add a PDF Parser block. Set File URL to the resume parameter.

{
  "block_type": "pdf_parser",
  "label": "parsed_resume",
  "file_url": "{{ resume }}"
}

- block_type: pdf_parser
  label: parsed_resume
  file_url: "{{ resume }}"

The parsed data is accessible as parsed_resume_output in subsequent blocks. The login block authenticates using stored credentials. Skyvern injects the username/password directly into form fields without exposing them to the LLM.

Cloud UI
API / SDK

Add a Login block. Configure it as follows:

URL: set to the job_portal_url parameter
Credential: Select the credentials parameter
Goal: “Log in using the provided credentials. Handle any cookie consent popups. COMPLETE when on the account dashboard or orders page.”

{
  "block_type": "login",
  "label": "login_to_portal",
  "url": "{{ job_portal_url }}",
  "title": "login_to_portal",
  "parameter_keys": ["credentials"],
  "navigation_goal": "Log in using the provided credentials.\nHandle any cookie consent popups.\nCOMPLETE when on the account dashboard or orders page.",
  "max_retries": 0,
  "engine": "skyvern-1.0"
}

- block_type: login
  label: login_to_portal
  url: "{{ job_portal_url }}"
  title: login_to_portal
  parameter_keys:
    - credentials
  navigation_goal: |
    Log in using the provided credentials.
    Handle any cookie consent popups.
    COMPLETE when on the account dashboard or orders page.
  max_retries: 0
  engine: skyvern-1.0

Search for jobs block

Navigate to the job search and find relevant positions based on the parsed resume.

Cloud UI
API / SDK

Add a Navigation block. Configure it as follows:

URL: Leave empty (continues from the current page after login)
Goal: “Search for a relevant job based on the parsed resume.” The block will automatically reference the parsed_resume_output from the previous step.

{
  "block_type": "navigation",
  "label": "search_for_job",
  "url": "",
  "title": "search_for_job",
  "engine": "skyvern-1.0",
  "navigation_goal": "Search for a relevant job based on the parsed resume: {{parsed_resume_output}}",
  "max_retries": 0
}

- block_type: navigation
  label: search_for_job
  url: ""
  title: search_for_job
  engine: skyvern-1.0
  navigation_goal: "Search for a relevant job based on the parsed resume: {{parsed_resume_output}}"
  max_retries: 0

Extract jobs list block

Extract job postings from the search results. The data_schema tells Skyvern exactly what structure to return.

Cloud UI
API / SDK

Add an Extraction block. Configure it as follows:

Goal: “Extract all visible job profiles: job page url, title, employer, location, and type (full time, part time, etc)”
Data Schema: Paste the following JSON schema:

{
  "jobs": {
    "type": "array",
    "items": {
      "type": "object",
      "properties": {
        "job_page_url": { "type": "string", "description": "Link to the apply page for the job" },
        "title": { "type": "string", "description": "Title of the role offered" },
        "employer": { "type": "string", "description": "Name of the company posting the job profile" },
        "location": { "type": "string", "description": "Where is the job role based. City and country," },
        "type": { "type": "string", "description": "Type for employment: full-time. part-time, contractual, internship etc." }
      },
      "required": ["job_page_url", "title", "employer", "location"]
    }
  }
}

{
  "block_type": "extraction",
  "label": "jobs_list_extraction",
  "url": "",
  "title": "jobs_list_extraction",
  "data_extraction_goal": "Extract all visible job profiles: job page url, title, employer, location, and type (full time, part time, etc)",
  "data_schema": {
    "jobs": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "job_page_url": {
            "type": "string",
            "description": "Link to the apply page for the job"
          },
          "title": {
            "type": "string",
            "description": "Title of the role offered"
          },
          "employer": {
            "type": "string",
            "description": "Name of the company posting the job profile"
          },
          "location": {
            "type": "string",
            "description": "Where is the job role based. City and country,"
          },
          "type": {
            "type": "string",
            "description": "Type for employment: full-time. part-time, contractual, internship etc."
          }
        },
        "required": ["job_page_url", "title", "employer", "location"]
      }
    }
  },
  "max_retries": 0,
  "engine": "skyvern-1.0"
}

- block_type: extraction
  label: jobs_list_extraction
  url: ""
  title: jobs_list_extraction
  data_extraction_goal: "Extract all visible job profiles: job page url, title, employer, location, and type (full time, part time, etc)"
  data_schema:
    jobs:
      type: array
      items:
        type: object
        properties:
          job_page_url:
            type: string
            description: Link to the apply page for the job
          title:
            type: string
            description: Title of the role offered
          employer:
            type: string
            description: Name of the company posting the job profile
          location:
            type: string
            description: Where is the job role based. City and country,
          type:
            type: string
            description: "Type for employment: full-time. part-time, contractual, internship etc."
        required:
          - job_page_url
          - title
          - employer
          - location
  max_retries: 0
  engine: skyvern-1.0

The output is accessible as jobs_list_extraction_output.jobs in subsequent blocks.

Apply to jobs loop

Iterate over each job posting and complete the application. This loop contains multiple blocks that work together:

goto_url: Navigate to the job page
extraction: Extract detailed job information
action: Click the Apply button
extraction: Extract application form questions
text_prompt: Generate tailored answers using AI
navigation: Fill out and submit the application

Cloud UI
API / SDK

Add a For Loop block. Set the Loop Variable to jobs_list_extraction_output.jobs. Enable Continue on Failure and Next Loop on Failure.Inside the loop, add the following blocks in order:

Go to URL block

Add a Go to URL block. Set URL to the current_value.job_page_url variable.

Extract job details

Add an Extraction block. Set Goal to: “Extract every detail about the job role present on the page.”

Click Apply

Add an Action block. Set Goal to: “Find Apply button and click it. COMPLETE when the job application is visible on the screen.”

Extract form questions

Add an Extraction block. Set Goal to: “Extract every question in the job application form as a list.”

Generate answers

Add a Text Prompt block. Set the Prompt to reference the parsed resume, job details, and extracted questions so the AI generates tailored answers for each field.

Fill and submit

Add a Navigation block. Set Goal to: “Fill out all of the form fields using the generated answers, including optional fields. COMPLETE when the application form has been successfully submitted.”

{
  "block_type": "for_loop",
  "label": "for_each_job",
  "loop_variable_reference": "{{jobs_list_extraction_output.jobs}}",
  "continue_on_failure": true,
  "next_loop_on_failure": true,
  "complete_if_empty": true,
  "loop_blocks": [
    {
      "block_type": "goto_url",
      "label": "go_to_each_job",
      "url": "{{ current_value.job_page_url }}"
    },
    {
      "block_type": "extraction",
      "label": "extract_job_detail",
      "url": "",
      "title": "extract_job_detail",
      "data_extraction_goal": "Extract every detail about the job role present on the page",
      "max_retries": 0,
      "engine": "skyvern-1.0"
    },
    {
      "block_type": "action",
      "label": "click_apply",
      "url": "",
      "title": "click_apply",
      "navigation_goal": "Find Apply button and click it.\n\nCOMPLETE when the job application is visible on the screen",
      "max_retries": 0,
      "engine": "skyvern-1.0"
    },
    {
      "block_type": "extraction",
      "label": "extract_questions",
      "url": "",
      "title": "extract_questions",
      "data_extraction_goal": "Extract every question in the job application form as a list",
      "max_retries": 0,
      "engine": "skyvern-1.0"
    },
    {
      "block_type": "text_prompt",
      "label": "answer_form_questions",
      "prompt": "Given:\nresume: {{resume}}\nparsed resume: {{parsed_resume_output}}\ninformation about the job profile: {{extract_job_detail_output}}\napplication form questions: {{extract_questions_output}}\n\nYou are applying for {{ current_value.title }} at {{ current_value.employer }}.\n\nWrite thoughtful and impressive answers to each question using the information from resume and parsed resume output."
    },
    {
      "block_type": "navigation",
      "label": "apply_to_job",
      "url": "",
      "title": "apply_to_job",
      "engine": "skyvern-1.0",
      "navigation_goal": "Given:\n{{answer_form_questions_output}}\n\nFill out all of the form fields, including the optional fields.\n\nIf you dont know the answer to an optional question, leave it blank. If you dont know the answer to a required question such as referral name put N/A or something equivalent.\n\nCOMPLETE when the application form has been successfully submitted.\n\nMore context:\nresume: {{resume}}\nperson_information: {{parsed_resume_output}}",
      "max_retries": 0
    }
  ]
}

- block_type: for_loop
  label: for_each_job
  loop_variable_reference: "{{jobs_list_extraction_output.jobs}}"
  continue_on_failure: true
  next_loop_on_failure: true
  complete_if_empty: true
  loop_blocks:
    - block_type: goto_url
      label: go_to_each_job
      url: "{{ current_value.job_page_url }}"

    - block_type: extraction
      label: extract_job_detail
      url: ""
      title: extract_job_detail
      data_extraction_goal: Extract every detail about the job role present on the page
      max_retries: 0
      engine: skyvern-1.0

    - block_type: action
      label: click_apply
      url: ""
      title: click_apply
      navigation_goal: |
        Find Apply button and click it.

        COMPLETE when the job application is visible on the screen
      max_retries: 0
      engine: skyvern-1.0

    - block_type: extraction
      label: extract_questions
      url: ""
      title: extract_questions
      data_extraction_goal: Extract every question in the job application form as a list
      max_retries: 0
      engine: skyvern-1.0

    - block_type: text_prompt
      label: answer_form_questions
      prompt: |
        Given:
        resume: {{resume}}
        parsed resume: {{parsed_resume_output}}
        information about the job profile: {{extract_job_detail_output}}
        application form questions: {{extract_questions_output}}

        You are applying for {{ current_value.title }} at {{ current_value.employer }}.

        Write thoughtful and impressive answers to each question using the information from resume and parsed resume output.

    - block_type: navigation
      label: apply_to_job
      url: ""
      title: apply_to_job
      engine: skyvern-1.0
      navigation_goal: |
        Given:
        {{answer_form_questions_output}}

        Fill out all of the form fields, including the optional fields.

        If you dont know the answer to an optional question, leave it blank. If you dont know the answer to a required question such as referral name put N/A or something equivalent.

        COMPLETE when the application form has been successfully submitted.

        More context:
        resume: {{resume}}
        person_information: {{parsed_resume_output}}
      max_retries: 0

Key pattern: continue_on_failure: true ensures that if one application fails, the agent continues to the next job. Inside the loop, current_value gives you the current job being processed.

Complete agent definition

Cloud UI
API / SDK

Here’s a summary of the complete agent you’ve built in the visual editor:

Create the agent

Go to Agents → Create Agent. Name it “Search and Apply for Jobs Workflow.” On the Start node, set Proxy Location to Residential and add the parameters: resume, credentials, and job_portal_url.

Block 1: PDF Parser

Add a PDF Parser block. Set File URL to the resume parameter.

Block 2: Login

Add a Login block. Set URL to the job_portal_url parameter. Select the credentials parameter. Set the goal: “Log in using the provided credentials. Handle any cookie consent popups. COMPLETE when on the account dashboard or orders page.”

Block 3: Navigation (search for jobs)

Add a Navigation block. Leave URL empty. Set the goal: “Search for a relevant job based on the parsed resume.”

Block 4: Extraction (job listings)

Add an Extraction block. Set the goal: “Extract all visible job profiles: job page url, title, employer, location, and type.” Paste the jobs JSON schema into Data Schema.

Block 5: For Loop (apply to each job)

Add a For Loop block. Set Loop Variable to jobs_list_extraction_output.jobs. Enable Continue on Failure and Next Loop on Failure. Inside the loop, add six blocks in order: Go to URL (job page), Extraction (job details), Action (click Apply), Extraction (form questions), Text Prompt (generate answers), Navigation (fill and submit the form).

Save this complete definition to job-application-workflow.yaml (or .json) before running.

{
  "title": "Search and Apply for Jobs Workflow",
  "description": "Search for jobs on any portal, extract listings, generate tailored answers with AI, and submit applications automatically.",
  "proxy_location": "RESIDENTIAL",
  "workflow_definition": {
    "version": 1,
    "parameters": [
      { "key": "resume", "parameter_type": "workflow", "workflow_parameter_type": "file_url" },
      { "key": "credentials", "parameter_type": "workflow", "workflow_parameter_type": "credential_id", "default_value": "your-credential-id" },
      { "key": "job_portal_url", "description": "URL of the job portal", "parameter_type": "workflow", "workflow_parameter_type": "string" }
    ],
    "blocks": [
      {
        "block_type": "pdf_parser",
        "label": "parsed_resume",
        "file_url": "{{ resume }}"
      },
      {
        "block_type": "login",
        "label": "login_to_portal",
        "url": "{{ job_portal_url }}",
        "title": "login_to_portal",
        "parameter_keys": ["credentials"],
        "navigation_goal": "Log in using the provided credentials.\nHandle any cookie consent popups.\nCOMPLETE when on the account dashboard or orders page.",
        "max_retries": 0,
        "engine": "skyvern-1.0"
      },
      {
        "block_type": "navigation",
        "label": "search_for_job",
        "url": "",
        "title": "search_for_job",
        "engine": "skyvern-1.0",
        "navigation_goal": "Search for a relevant job based on the parsed resume: {{parsed_resume_output}}",
        "max_retries": 0
      },
      {
        "block_type": "extraction",
        "label": "jobs_list_extraction",
        "url": "",
        "title": "jobs_list_extraction",
        "data_extraction_goal": "Extract all visible job profiles: job page url, title, employer, location, and type (full time, part time, etc)",
        "data_schema": {
          "jobs": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "job_page_url": { "type": "string", "description": "Link to the apply page for the job" },
                "title": { "type": "string", "description": "Title of the role offered" },
                "employer": { "type": "string", "description": "Name of the company posting the job profile" },
                "location": { "type": "string", "description": "Where is the job role based. City and country," },
                "type": { "type": "string", "description": "Type for employment: full-time. part-time, contractual, internship etc." }
              },
              "required": ["job_page_url", "title", "employer", "location"]
            }
          }
        },
        "max_retries": 0,
        "engine": "skyvern-1.0"
      },
      {
        "block_type": "for_loop",
        "label": "for_each_job",
        "loop_variable_reference": "{{jobs_list_extraction_output.jobs}}",
        "continue_on_failure": true,
        "next_loop_on_failure": true,
        "complete_if_empty": true,
        "loop_blocks": [
          {
            "block_type": "goto_url",
            "label": "go_to_each_job",
            "url": "{{ current_value.job_page_url }}"
          },
          {
            "block_type": "extraction",
            "label": "extract_job_detail",
            "url": "",
            "title": "extract_job_detail",
            "data_extraction_goal": "Extract every detail about the job role present on the page",
            "max_retries": 0,
            "engine": "skyvern-1.0"
          },
          {
            "block_type": "action",
            "label": "click_apply",
            "url": "",
            "title": "click_apply",
            "navigation_goal": "Find Apply button and click it.\n\nCOMPLETE when the job application is visible on the screen",
            "max_retries": 0,
            "engine": "skyvern-1.0"
          },
          {
            "block_type": "extraction",
            "label": "extract_questions",
            "url": "",
            "title": "extract_questions",
            "data_extraction_goal": "Extract every question in the job application form as a list",
            "max_retries": 0,
            "engine": "skyvern-1.0"
          },
          {
            "block_type": "text_prompt",
            "label": "answer_form_questions",
            "prompt": "Given:\nresume: {{resume}}\nparsed resume: {{parsed_resume_output}}\ninformation about the job profile: {{extract_job_detail_output}}\napplication form questions: {{extract_questions_output}}\n\nYou are applying for {{ current_value.title }} at {{ current_value.employer }}.\n\nWrite thoughtful and impressive answers to each question using the information from resume and parsed resume output."
          },
          {
            "block_type": "navigation",
            "label": "apply_to_job",
            "url": "",
            "title": "apply_to_job",
            "engine": "skyvern-1.0",
            "navigation_goal": "Given:\n{{answer_form_questions_output}}\n\nFill out all of the form fields, including the optional fields.\n\nIf you dont know the answer to an optional question, leave it blank. If you dont know the answer to a required question such as referral name put N/A or something equivalent.\n\nCOMPLETE when the application form has been successfully submitted.\n\nMore context:\nresume: {{resume}}\nperson_information: {{parsed_resume_output}}",
            "max_retries": 0
          }
        ]
      }
    ]
  }
}

title: Search and Apply for Jobs Workflow
description: "Search for jobs on any portal, extract listings, generate tailored answers with AI, and submit applications automatically."
proxy_location: RESIDENTIAL
workflow_definition:
  version: 1
  parameters:
    - key: resume
      parameter_type: workflow
      workflow_parameter_type: file_url
    - key: credentials
      parameter_type: workflow
      workflow_parameter_type: credential_id
      default_value: your-credential-id # <-- replace this
    - key: job_portal_url
      description: URL of the job portal
      parameter_type: workflow
      workflow_parameter_type: string

  blocks:
    - block_type: pdf_parser
      label: parsed_resume
      file_url: "{{ resume }}"

    - block_type: login
      label: login_to_portal
      url: "{{ job_portal_url }}"
      title: login_to_portal
      parameter_keys:
        - credentials
      navigation_goal: |
        Log in using the provided credentials.
        Handle any cookie consent popups.
        COMPLETE when on the account dashboard or orders page.
      max_retries: 0
      engine: skyvern-1.0

    - block_type: navigation
      label: search_for_job
      url: ""
      title: search_for_job
      engine: skyvern-1.0
      navigation_goal: "Search for a relevant job based on the parsed resume: {{parsed_resume_output}}"
      max_retries: 0

    - block_type: extraction
      label: jobs_list_extraction
      url: ""
      title: jobs_list_extraction
      data_extraction_goal: "Extract all visible job profiles: job page url, title, employer, location, and type (full time, part time, etc)"
      data_schema:
        jobs:
          type: array
          items:
            type: object
            properties:
              job_page_url:
                type: string
                description: Link to the apply page for the job
              title:
                type: string
                description: Title of the role offered
              employer:
                type: string
                description: Name of the company posting the job profile
              location:
                type: string
                description: Where is the job role based. City and country,
              type:
                type: string
                description: "Type for employment: full-time. part-time, contractual, internship etc."
            required:
              - job_page_url
              - title
              - employer
              - location
      max_retries: 0
      engine: skyvern-1.0

    - block_type: for_loop
      label: for_each_job
      loop_variable_reference: "{{jobs_list_extraction_output.jobs}}"
      continue_on_failure: true
      next_loop_on_failure: true
      complete_if_empty: true
      loop_blocks:
        - block_type: goto_url
          label: go_to_each_job
          url: "{{ current_value.job_page_url }}"

        - block_type: extraction
          label: extract_job_detail
          url: ""
          title: extract_job_detail
          data_extraction_goal: Extract every detail about the job role present on the page
          max_retries: 0
          engine: skyvern-1.0

        - block_type: action
          label: click_apply
          url: ""
          title: click_apply
          navigation_goal: |
            Find Apply button and click it.

            COMPLETE when the job application is visible on the screen
          max_retries: 0
          engine: skyvern-1.0

        - block_type: extraction
          label: extract_questions
          url: ""
          title: extract_questions
          data_extraction_goal: Extract every question in the job application form as a list
          max_retries: 0
          engine: skyvern-1.0

        - block_type: text_prompt
          label: answer_form_questions
          prompt: |
            Given:
            resume: {{resume}}
            parsed resume: {{parsed_resume_output}}
            information about the job profile: {{extract_job_detail_output}}
            application form questions: {{extract_questions_output}}

            You are applying for {{ current_value.title }} at {{ current_value.employer }}.

            Write thoughtful and impressive answers to each question using the information from resume and parsed resume output.

        - block_type: navigation
          label: apply_to_job
          url: ""
          title: apply_to_job
          engine: skyvern-1.0
          navigation_goal: |
            Given:
            {{answer_form_questions_output}}

            Fill out all of the form fields, including the optional fields.

            If you dont know the answer to an optional question, leave it blank. If you dont know the answer to a required question such as referral name put N/A or something equivalent.

            COMPLETE when the application form has been successfully submitted.

            More context:
            resume: {{resume}}
            person_information: {{parsed_resume_output}}
          max_retries: 0

Step 4: Run and monitor

Create the agent from your definition file and execute it.

Cloud UI
API / SDK

Run the agent

Click Run in the agent editor. Fill in the parameters:

resume: URL to your resume PDF
job_portal_url: https://job-stash.vercel.app
credentials: Select the Job Stash credential

Monitor the run

Watch the run in real time. Each block shows its status as it executes. The for loop will iterate over each job posting, and you can see the AI filling out application forms in the browser recording.

import os
import asyncio
from skyvern import Skyvern

async def main():
    client = Skyvern(api_key=os.getenv("SKYVERN_API_KEY"))

    # Create workflow from YAML file
    workflow = await client.create_workflow(
        yaml_definition=open("job-application-workflow.yaml").read()
    )
    print(f"Created workflow: {workflow.workflow_permanent_id}")

    # Run the workflow
    run = await client.run_workflow(
        workflow_id=workflow.workflow_permanent_id,
        parameters={
            "resume": "https://your-resume-url.com/resume.pdf",  # <-- replace this
            "job_portal_url": "https://job-stash.vercel.app"
        }
    )
    print(f"Started run: {run.run_id}")

    # Poll for completion
    while True:
        result = await client.get_run(run.run_id)
        if result.status in ["completed", "failed", "terminated"]:
            break
        print(f"Status: {result.status}")
        await asyncio.sleep(10)

    print(f"Final status: {result.status}")
    if result.status == "completed":
        print("Job applications submitted successfully")

asyncio.run(main())

import { SkyvernClient } from "@skyvern/client";
import * as fs from "fs";

async function main() {
  const client = new SkyvernClient({
    apiKey: process.env.SKYVERN_API_KEY,
  });

  // Create workflow from YAML file
  const workflow = await client.createWorkflow({
    body: {
      yaml_definition: fs.readFileSync("job-application-workflow.yaml", "utf-8"),
    },
  });
  console.log(`Created workflow: ${workflow.workflow_permanent_id}`);

  // Run the workflow
  const run = await client.runWorkflow({
    body: {
      workflow_id: workflow.workflow_permanent_id,
      parameters: {
        resume: "https://your-resume-url.com/resume.pdf", // <-- replace this
        job_portal_url: "https://job-stash.vercel.app",
      },
    },
  });
  console.log(`Started run: ${run.run_id}`);

  // Poll for completion
  while (true) {
    const result = await client.getRun(run.run_id);
    if (["completed", "failed", "terminated"].includes(result.status)) {
      console.log(`Final status: ${result.status}`);
      if (result.status === "completed") {
        console.log("Job applications submitted successfully");
      }
      break;
    }
    console.log(`Status: ${result.status}`);
    await new Promise((r) => setTimeout(r, 10000));
  }
}

main();

# Create workflow
WORKFLOW=$(curl -s -X POST "https://api.skyvern.com/v1/workflows" \
  -H "x-api-key: $SKYVERN_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"yaml_definition\": $(cat job-application-workflow.yaml | jq -Rs .)}")

WORKFLOW_ID=$(echo "$WORKFLOW" | jq -r '.workflow_permanent_id')
echo "Created workflow: $WORKFLOW_ID"

# Run workflow (replace resume URL with your own)
RUN=$(curl -s -X POST "https://api.skyvern.com/v1/run/workflows" \
  -H "x-api-key: $SKYVERN_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"workflow_id\": \"$WORKFLOW_ID\",
    \"parameters\": {
      \"resume\": \"https://your-resume-url.com/resume.pdf\",
      \"job_portal_url\": \"https://job-stash.vercel.app\"
    }
  }")

RUN_ID=$(echo "$RUN" | jq -r '.run_id')
echo "Started run: $RUN_ID"

# Poll for completion
while true; do
  RESULT=$(curl -s "https://api.skyvern.com/v1/runs/$RUN_ID" \
    -H "x-api-key: $SKYVERN_API_KEY")
  STATUS=$(echo "$RESULT" | jq -r '.status')
  echo "Status: $STATUS"

  if [[ "$STATUS" == "completed" || "$STATUS" == "failed" || "$STATUS" == "terminated" ]]; then
    echo "Workflow finished with status: $STATUS"
    break
  fi
  sleep 10
done

Resources

Agent Blocks Reference

Complete parameter reference for all block types

Credential Management

Securely store and use login credentials

File Operations

Upload and parse files in agents

Error Handling

Handle failures and retries in production

​What you’ll build

​Prerequisites

​Sample Job Portal

​Step 1: Store credentials

​Step 2: Create a new agent

​Set parameters

​Step 3: Add agent blocks

​PDF Parser block

​Login block

​Search for jobs block

​Extract jobs list block

​Apply to jobs loop

​Complete agent definition

​Step 4: Run and monitor

​Resources