How to use: (1) Contact source picks where candidates come from; (2) Language + Variant radios pick which prompt variant renders; (3) Click a row to populate the detail pane; (4) Generate Drafts makes real Claude API calls — each draft streams into its row. Approve/Skip now persist a
ConversationTurn to disk (feeds Prompt Versions metrics + the optimizer dev-set); Send Approved is currently disabled pending LinkedIn scrutiny recovery.
Contact source
Sourcing run
후보자
📄 직무 설명(JD)
[연락처 로드]에서 소싱된 후보자를 선택하세요.
후보자 상세
일괄 작업
메시지 초안
~/.hr_agent/scheduled_sends.sqlite) backed by /api/scheduled-sends. Approved drafts enqueue here; the worker dispatches one at a time via Run tick now. Channel is chosen automatically (LinkedIn when cookies are present, Email when SMTP env vars are set).
계정 연결
확인 중…
대기 중 · 0
| 후보 | 채널 | 예정 시각 | |
|---|---|---|---|
| 불러오는 중… | |||
Recent (last 24h)
| 후보 | 결과 | 시간 | |
|---|---|---|---|
| 불러오는 중… | |||
How to use: (1) Click a node to see its full prompt text on the right; (2) Fork from selected opens a modal pre-filled with the parent's instructions — edit the change_note + text, save, a new variant appears as a child in the tree; (3) Green dot = a variant that's measurably outperforming the default (≥15% lower edit_distance + n≥3 sends). A Suggestion card surfaces when a winner qualifies — one-click Promote. (4) [demo data] toggle in the header swaps
data/sessions/ for the pre-seeded data/sessions/_demo/ fixture — useful when showing the feature with realistic metrics before real HR traffic lands.
프롬프트 대시보드
POST /api/linkedin/poll-replies. New replies land as ConversationTurn(role="candidate") and the session state flips to REPLIED_PENDING_HR.Composing the next-turn draft is Phase C (multi-turn state machine) — not wired yet. For now, HR reads the reply here and replies manually in LinkedIn Recruiter / LinkedIn web.
Active · 0
변형별 평균 편집 거리 (실 데이터)
낮을수록 HR가 초안을 더 신뢰함 — 편집을 덜 함.
변형별 응답률 (샘플)
후보자 깔때기 — 30일 (샘플)
How to use: (1) Pick a run on the left — rows show run_id, timestamp, and qualified/total candidate count. (2) The right pane expands with full run metadata (JD preview, filter, cutoff thresholds). (3) Click a candidate — ✓ means qualified, ✗ means
below_cutoff (Module 1 filtered them out). (4) Candidate detail on the far right shows everything Module 1 knows; sources are clickable. (5) To trigger a new run, click + New run above the runs list — the same modal as on the Batch Dashboard, with a streaming progress log in Korean.