Step 2: Connect Bright Data Requests

Trigger the Bright Data dataset, poll for completion, and retrieve results based on the snapshot status.

1. Open Submit Bright Data Request and set URL to https://api.brightdata.com/datasets/v3/trigger with Method POST and Specify Body set to json.
2. Set JSON Body to =[ { "country": "{{ $json['Country (2 letters)'] }}", "domain": "indeed.com", "keyword_search": "{{ $json.Keyword }}", "location": "{{ $json['Job Location'] }}", "date_posted": "Last 24 hours", "posted_by": "" } ].
3. In Submit Bright Data Request, set query parameters: dataset_id to [YOUR_ID], include_errors to true, type to discover_new, discover_by to keyword, and uncompressed_webhook to true.
4. Add a header in Submit Bright Data Request: Authorization = Bearer [CONFIGURE_YOUR_TOKEN].
5. Configure Pause for Snapshot Poll with Unit minutes and Amount 1.
6. Set Check Snapshot Progress URL to =https://api.brightdata.com/datasets/v3/progress/{{ $('Submit Bright Data Request').item.json.snapshot_id }} and add the same Authorization header.
7. In Snapshot Status Branch, set the condition to Left Value ={{ $json.status }} equals Right Value running.
8. Configure Retrieve Snapshot Results with URL =https://api.brightdata.com/datasets/v3/snapshot/{{ $('Submit Bright Data Request').item.json.snapshot_id }}, set query format to json, and add the same Authorization header.

Step 3: Set Up Processing and AI Evaluation

Split incoming job fields and evaluate fit using an LLM.

1. In Split Job Fields, set Field to Split Out to company_name, job_title, description_text.
2. Open LLM Fit Evaluation and set Prompt Type to define.
3. Set Text in LLM Fit Evaluation to =Read the following job post: Company Name {{ $json.company_name }}, job Title: {{ $json.job_title }}, And job description {{ $json.description_text }}, and tell me if you think I'm a good fit. Answer only YES or NO. I'm looking for roles in Pfizer.
4. Ensure OpenAI Chat Engine is connected to LLM Fit Evaluation as the language model and set Model to gpt-4o-mini.
5. Credential Required: Connect your openAiApi credentials in OpenAI Chat Engine (LLM credentials are added to the parent node, not LLM Fit Evaluation).

Step 4: Configure Output to Google Sheets

Write job records to the sheet and update the fit decision.

1. Open Append Job Records Sheet and set Operation to append.
2. Select the target document in Document ID as [YOUR_ID] and Sheet Name as gid=0 (input).
3. Credential Required: Connect your googleSheetsOAuth2Api credentials in Append Job Records Sheet.
4. Open Update Fit Column and set Operation to update with Matching Columns set to company_name.
5. In Update Fit Column set column mappings: AM I a Fit? = ={{ $json.text }} and company_name = ={{ $('Split Job Fields').item.json.company_name }}.
6. Credential Required: Connect your googleSheetsOAuth2Api credentials in Update Fit Column.

Step 5: Test and Activate Your Workflow

Validate the end-to-end flow and then enable the workflow for production use.

1. Click Execute Workflow and submit the form from Form Intake Trigger with sample values.
2. Confirm that Submit Bright Data Request returns a snapshot_id and that Snapshot Status Branch loops through Pause for Snapshot Poll while status is running.
3. Verify that Retrieve Snapshot Results returns job data and Append Job Records Sheet appends rows to the spreadsheet.
4. Check that LLM Fit Evaluation produces YES or NO and Update Fit Column updates the AM I a Fit? column.
5. When everything works as expected, toggle the workflow Active to run it in production.