Tracking tradeoff from agentic MCP migration plan (onboarding flow).
Context: After extracting the user's resume, the agent proposes a detected role list saved to ~/.jobsync/profile/roles.json. User then confirms, adds custom roles, and marks excluded roles.
Open questions:
- How aggressive should the agent be? Suggest top 3 roles vs top 10?
- Weight by recency of experience (e.g., most recent job > projects from 3 years ago)?
- Handle career-switchers: someone with backend experience targeting AI roles
- Should custom roles be validated against a known role taxonomy or accepted verbatim?
Downstream impact: union of detected + custom minus excluded drives every scrape_jobs_workflow run — miscalibration means irrelevant jobs in Airtable.
Tracking tradeoff from agentic MCP migration plan (onboarding flow).
Context: After extracting the user's resume, the agent proposes a
detectedrole list saved to~/.jobsync/profile/roles.json. User then confirms, addscustomroles, and marksexcludedroles.Open questions:
Downstream impact: union of detected + custom minus excluded drives every
scrape_jobs_workflowrun — miscalibration means irrelevant jobs in Airtable.