Job Change Intent Scorer

Your champions change jobs. Be the first call they take.

Three-agent swarm that detects when a past champion changes companies, researches the new context, scores re-engagement potential (RPS 1-10), and updates HubSpot with an actionable brief. Tracker uses web_search to find job change signals. Analyst scores across 4 criteria: relationship warmth, new company ICP fit, timing, buying power. Briefer drafts re-engagement brief + writes 6 custom HubSpot contact properties. We built this after a CS team lost three accounts in one quarter because the champion changed jobs and nobody noticed until the renewal call. The scorer monitors job change signals so teams can act before the relationship breaks.

Last updated March 5, 2026

Support ticket volume grows 15-20% year-over-year for most SaaS companies, but support headcount grows at half that rate. Finding patterns in ticket data — recurring issues, product areas driving volume, customer segments with disproportionate needs — requires analysis that ad-hoc queries cannot sustain. Automated pattern detection surfaces systemic issues.

Phase 1 — DetectioninputContact Data01Trackerweb_search DetectionChangefound?NoNoChangeYesPhase 2 — Intelligence02AnalystRPS 1–1003BrieferBrief + HubSpotoutputRPS + BriefTwo-Phase — Conditional on Job Change

Three Agents. Two Phases. Zero Missed Champions.

The Tracker

Step 1The Tracker

Tier 1 Reasoning

Detects job change signals via web_search — new employer, title, start date, public announcements. Confirms or rules out a change with a confidence score. No change detected? Pipeline terminates here. Zero Phase 2 cost.

The Analyst

Step 2The Analyst

Tier 1 Reasoning

What does The Analyst actually decide? Scores Re-engagement Potential (RPS 1–10) across 4 weighted criteria: relationship warmth (30%), new company ICP fit (25%), timing signal (25%), and new buying power (20%). Only runs when a job change is confirmed.

The Briefer

Step 3The Briefer

Tier 1 Reasoning

Without this step, upstream analysis sits idle. Drafts an actionable re-engagement brief and writes 6 custom HubSpot contact properties — new company, new title, RPS score, brief summary, change detected date, and last scored timestamp. Optional Slack alert for high-RPS contacts.When Anthropic releases a new model, the customer changes one value. Every blueprint uses a Config Loader node — one configuration point.

That's the full pipeline. Here's what it intentionally does NOT do — and why those boundaries exist.

What It Does NOT Do

×

Does not access LinkedIn API — uses web_search to surface publicly available job change signals (no LinkedIn OAuth required)

×

Does not send outreach emails — output is HubSpot property updates + optional Slack alert

×

Does not monitor contacts in real time — runs on-demand per contact

×

Does not create new HubSpot contacts — enriches existing records only

With those boundaries clear, here's everything that ships when you purchase.

The Complete Customer Success Bundle

9 files.

CHANGELOG.mdVersion history
LICENSE.mdLicense terms
README.mdSetup and configuration guide
dependency_matrix.mdThird-party service dependencies
error_handling_matrix.mdError handling reference
job_change_intent_scorer_v1.jsonn8n workflow (main pipeline)
system_prompts/analyst.txtAnalyst system prompt
system_prompts/briefer.txtBriefer system prompt
system_prompts/tracker.txtTracker system prompt

The technical specifications below are ITP-measured, not estimated.

Tested. Measured. Documented.

All values below are from Independent Test Protocol (ITP) testing — not estimates, not projections. Measured across 20 test contacts spanning confirmed job changes, no-change scenarios, and edge cases.

Workflow Nodes

20 specialized n8n nodes

Blueprint Quality Standard

BQS v2 — 12/12 PASS

Agent Roles

3 (Tracker, Analyst, Briefer)

Credentials Required

Anthropic API + HubSpot Private App + Slack Bot (optional)

Bundle Files

9 files

Cost Savings (No Change Path)

28% savings when no job change detected

Inspection & Test Plan

JCIS-01 through JCIS-06 — ALL PASS

n8n Versions Tested

Self-hosted

Cost per Contact (Full Pipeline)

$0.29 (full pipeline, ITP-measured)

Cost per Contact (No Change)

$0.21 (no change detected)

Tested on n8n v2.7.5, March 2026

Job Change Intent Scorer v1.0.0 — Technical Reference━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━Pipeline:     Webhook → Tracker (web_search) → Job Change Router → Analyst (RPS) → Briefer → HubSpot + SlackTopology:     Modular Agentic Swarm (3 agents, 2 phases)Phase 1:      Tracker — always runs (Detection)Phase 2:      Analyst + Briefer — conditional on confirmed job change (Intelligence)Node Count:   20LLM:          Claude Opus 4.6 (Tracker, Analyst, Briefer — Tier 1 Reasoning)Cost:         $0.29/contact (full pipeline) | $0.21/contact (no change)Savings:      28% cost reduction when no job change detectedITP:          18/20 PASS (90%)BQS:          12/12 PASSTool A:       HubSpot (contact source + write-back)Tool B:       Slack (alert delivery)

What You'll Need

⚠ Data Source Dependency

This blueprint uses Anthropic's managed web search tool to research contacts and companies. Search results depend on live web data and may vary.

Platform

n8n 2.11.2+

Est. Monthly API Cost

$5–15/month

Credentials Required

  • Anthropic API
  • HubSpot API
  • Slack Bot Token

Services

  • HubSpot CRM
  • Slack workspace

Setup Track

Quick Start

~15 min

All credentials live, n8n running

Full Setup

1–2 hrs

Needs API config + tables

From Scratch

2–4 hrs

No n8n, no credentials

Job Change Intent Scorer v1.0.0

$199

one-time purchase

What you get:

  • 20-node n8n workflow (.json) — you own it
  • 3 tested agent system prompts (ITP-validated)
  • 8 SDC inter-agent schemas
  • Error handling matrix (34 failure modes documented)
  • HubSpot custom field setup guide (6 fw_ properties)
  • Dependency matrix with ITP-measured costs
  • README setup guide (10 minutes)
  • All sales final after download

Frequently Asked Questions

What is RPS (Re-engagement Potential Score)?+

RPS is a 1–10 composite score across four weighted criteria: relationship warmth (30%), new company ICP fit (25%), timing signal (25%), and new buying power (20%). Higher scores mean higher likelihood of a successful re-engagement conversation. The Analyst agent evaluates each criterion independently with explicit reasoning.

How does the Tracker detect job changes without LinkedIn API?+

The Tracker uses web_search to find publicly available job change signals — press releases, company announcements, news articles, and public professional profiles. No LinkedIn OAuth, no scraping, no API access required. If no public evidence of a job change exists, the pipeline terminates after Phase 1.

What HubSpot custom properties does this write?+

Six custom contact properties with the fw_ prefix: fw_new_company, fw_new_title, fw_rps_score, fw_reengagement_brief, fw_change_detected_at, and fw_last_scored_at. The README includes step-by-step instructions for creating these properties in HubSpot.

What triggers Phase 2 vs. terminating after Phase 1?+

The Tracker returns a job_change_confirmed boolean. If true, Phase 2 activates: Analyst scores RPS, Briefer drafts the brief and writes to HubSpot. If false, the pipeline returns a no_change_detected response immediately — zero Phase 2 cost.

What credentials are required?+

Anthropic API key (required — used by all 3 agents). HubSpot Private App token (required — for writing custom contact properties). Slack Bot token (optional — for high-RPS alerts).

What does the re-engagement brief contain?+

Contact context (new company, new role, previous relationship), RPS breakdown by criterion, recommended talking points, timing recommendation, and suggested outreach channel. It is an intelligence document for your sales team — not an automated email.

What does this blueprint NOT do?+

It does not access LinkedIn API — uses web_search for publicly available signals only. It does not send outreach emails — output is HubSpot properties + optional Slack alert. It does not monitor contacts in real time — runs on-demand per contact.

How much does each contact analysis cost?+

Full pipeline (job change confirmed): approximately $0.29 per contact. No change detected: approximately $0.21 per contact. Web search adds approximately $0.03–$0.05 per contact, included in the above figures.

Is there a refund policy?+

All sales are final after download. Review the Blueprint Dependency Matrix and prerequisites before purchase. Questions?

Read the full guide →

Related Blueprints