메뉴
Trigger and interpret underwriting on an application — parse bank statements, read risk flags, produce a readiness score, and recommend the next action.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Mandatory compliance gate before any outbound (email, SMS, blast). Verifies consent, opt-out status, CASL footer, send window, and daily cap.
Queue a cold outreach campaign to a segmented lead list via the cold_outreach_campaigns endpoint, with CASL compliance enforced before any send.
Generates the structured daily call sheet for Ezra — 6 prioritized categories, specific opening lines for each call, and a clear action order.
Surfaces overdue follow-ups, prioritizes the call list, and recommends specific outreach actions for each stuck deal or contact.
Domain literacy for MCA and alternative business funding. Reference glossary and clarifying-question guide for when operators use ambiguous terms.
Uses historical lender feedback data to recommend the best lenders for a specific deal profile and surfaces typical terms and decline patterns.
| name | underwriting-flow |
| description | Trigger and interpret underwriting on an application — parse bank statements, read risk flags, produce a readiness score, and recommend the next action. |
| triggers | ["run underwriting","parse these statements","what's the readiness on this deal","underwrite this","run the UW","pull the underwriting","what does underwriting say"] |
| tier | stable |
| disable_model_invocation | false |
| argument_hint | Which application ID should I run underwriting on? |
| requires | ["env:SUNBIZ_SUPABASE_URL","env:SUNBIZ_SUPABASE_ANON_KEY"] |
Where these endpoints live: All
/api/...URLs below are routes on the OASIS Command Center dashboard (repo:CC90210/oasis-command-center, deployed at https://agent-dashboard-sigma-eight.vercel.app). They are NOT served by this repo's localscripts/api_server.py(which only exposes/health,/status,/sms/send,/webhook/jotform). Solara's bridge makes authenticatedfetchcalls into the dashboard's API surface, and the dashboard then writes to Supabase / queues threads / dispatches the 8 daemons in this repo.
Run or retrieve underwriting on a specific application. Interpret the structured output into a plain-English recommendation for Ezra.
If bank statements have been uploaded and the application is in pending_uw or ready_for_uw status:
POST /api/applications/[id]/underwriting/run
This kicks off the underwriting agent. Response includes a job_id and estimated completion time (typically 60–120 seconds).
If underwriting was already run: skip to Step 2 — don't re-trigger unless Ezra asks for a re-run.
GET /api/applications/[id]/underwriting/latest
Response shape:
{
"readiness_score": 72,
"paper_grade": "B",
"revenue_monthly_avg": 38500,
"nsf_count": 3,
"position_count": 2,
"leverage_pct": 31,
"risk_flags": [
{ "level": "warning", "code": "nsf_elevated", "detail": "3 NSFs in 90 days" },
{ "level": "info", "code": "multi_position", "detail": "2 existing positions" }
],
"recommended_advance": 45000,
"recommended_factor_rate": 1.38,
"recommended_term_days": 120,
"notes": "B-paper candidate. Good revenue, manageable leverage. NSFs are the primary risk."
}
Translate the JSON into a plain-English summary:
Underwriting Summary — [Applicant Name]
READINESS SCORE: 72/100 — B-Paper
Revenue: $38,500/mo avg (sufficient)
Existing positions: 2 (moderate)
Leverage: 31% (within B-paper threshold)
NSFs: 3 in 90 days (elevated — flagged)
RECOMMENDED OFFER
Advance: $45,000
Factor rate: 1.38x
Term: 120 days (daily payment: ~$519)
RISK FLAGS
- NSFs (warning): 3 in 90 days. Some lenders auto-decline at 5+.
- Multi-position (info): 2 existing. Include in shop-out notes.
RECOMMENDATION: Ready to shop. Lead with B-paper funders.
Restrict to lenders with NSF tolerance ≥ 3.
| Readiness Score | Recommendation |
|---|---|
| 80–100 | Shop immediately — A-paper, wide lender pool |
| 60–79 | Shop with caveats — B-paper, filter lender set |
| 40–59 | Conditional — address risk flags before shopping |
| < 40 | Do not shop — escalate to Ezra for restructure plan |
For scores below 60, surface the specific flags and ask Ezra whether to proceed, defer, or seek additional docs.
After review, update status appropriately:
status = ready_to_shopstatus = needs_review, add note with flag summaryrisk_flags — a 72 score with a high_risk flag is not the same as a clean 72.paper_grade is D, escalate to skills/operator-handoff/SKILL.md before taking any action.