Build Blueprint — Sample (CRM Add-on)
Cedar Point Insurance Group LLC — Renewal Pipeline Add-on for Their Existing CRM
SAMPLE — FICTIONAL CLIENT. Cedar Point Insurance Group does not exist. Every name, number, and quote in this document is invented so prospects in the CRM add-on wedge shape can see exactly what a paid Build Blueprint contains before buying one. A real Blueprint is built from the client's own intake answers, a workflow interview, and their actual tool/data access — the structure, depth, and fixed-price format below are the real thing.
| Prepared for | "Cedar Point Insurance Group LLC" — independent insurance agency, 14 producers + 3 service staff, ~6,200 active policies (fictional) |
| Prepared by | AI Build Concierge |
| Blueprint price | $995 flat — credited in full toward the Managed Build below if the client proceeds within 60 days |
| Delivery | 7 calendar days from paid intake |
| Verdict | BUILD — as an add-on, not a replacement. The CRM they already pay for stays the system of record. What is missing is a renewal pipeline layer on top of it: renewal dates turned into work, in the producers' own voice, with a manager view. Do not buy a new CRM. Details §2–§4. |
1. Problem map
The client came in asking for "a new CRM that actually works for insurance." The interview found that their current CRM holds the data fine — it is the work around renewals that is not happening, in cost order:
| # | Problem | What it costs them (client's own estimates, fictional) |
|---|---|---|
| P1 | Renewals are worked from memory and a monthly spreadsheet export. Policies lapse or renew un-shopped because nobody was reminded in time. The owner estimates 4–6% of the book is lost each year to avoidable non-renewal — at their fictional average commission, roughly $55k–$85k/yr. | Highest cost; the add-on exists for this |
| P2 | No cross-sell view. A client with an auto policy and no home policy (or a business with no umbrella) is invisible in the current setup. Producers find out by accident, usually after the client bought elsewhere. | Real revenue, currently uncounted |
| P3 | Referrals are thanked, not tracked. Referral sources get no systematic follow-up, so the agency cannot tell which 10 people send half its new business. | Fixed by one pipeline field + one report |
| P4 | The owner cannot see next quarter. "What renews in the next 90 days, what is it worth, and who owns each one" takes the service lead half a day to assemble. | Solved as a by-product of P1 |
What we are NOT solving in v1: carrier quoting or rating, claims handling, accounting / commission reconciliation, a client-facing portal, and replacing the CRM itself. Each is named in §4 as explicitly out of scope — that list is part of what the Blueprint fee buys. This Blueprint designs a workflow add-on only; it gives no insurance, coverage, or financial advice, and no automated message in v1 discusses coverage terms — see the escalation rules in §3.
2. Workflow audit — before / after
| Workflow step | Before (today) | After (with v1) |
|---|---|---|
| Renewal approaches (90 / 60 / 30 days out) | Monthly spreadsheet export, worked when someone remembers | Every policy auto-creates a renewal task in the CRM at 90 days out, assigned to its producer, with the policy's own dates and premium on the task |
| Client renewal contact | Ad hoc calls; no cadence, no record of what was said | A producer-approved touch sequence (email + a call task, not auto-dialled) at 60 / 30 / 10 days; every touch logged on the client record; a human reply stops the sequence instantly |
| Cross-sell opportunity | Found by accident | Nightly flag on the client record: lines held vs. common missing lines, shown as a producer worklist — a prompt for a human conversation, never an automated pitch |
| Referral received | Thank-you note, then forgotten | Referral source recorded on the new client in one field; monthly top-referrer report; thank-you + update messages drafted for the producer to send |
| Lapsed / lost policy | Discovered at the next spreadsheet export, weeks late | Same-day flag when a policy status changes; win-back task at 30 days with the reason recorded |
| Owner's 90-day view | Half a day of spreadsheet work | One dashboard: renewals due by week, value by producer, tasks overdue, cross-sell worklist size |
3. Context-engineering assets included
This is the part a generic builder skips, and the reason AI output sounds like this business instead of a template. The Managed Build includes building and handing over:
- Business context file — lines the agency writes and does not write, carrier appointments in general terms, service area, producer territories, the words the agency actually uses with clients.
- Voice pack — real (redacted) past renewal emails from two producers, distilled into a touch-sequence voice guide, so drafts read as the producer on a good day, not as a chatbot.
- Renewal touch library — the 60 / 30 / 10-day messages plus the lapsed win-back draft, each with a personal-lines and a commercial-lines variant, all producer-approved before anything sends.
- Objection + FAQ sheet — the 15 questions this agency actually gets ("why did my premium go up?" → the honest general answer and a route to the producer), so drafted replies answer or route correctly instead of inventing an explanation.
- Escalation rules — what the system must never handle alone: any coverage question, any claim, any premium dispute, any cancellation request, any complaint → straight to the producer of record with full context. Automation in v1 sends reminders and drafts; it never advises.
All context assets are the client's property, delivered as plain documents they can hand to any future builder.
4. Build spec (v1 — pinned)
In scope:
- Renewal pipeline layer inside the client's existing CRM: policy renewal dates → dated tasks at 90 / 60 / 30 days, assigned to the producer of record, with overdue escalation to the service lead.
- Renewal touch sequences of §2 (email from the producer's own mailbox + call tasks), with instant stop-on-reply and a full touch log on the client record.
- Cross-sell flagging: a nightly rules pass over lines held per client, producing a producer worklist only (no automated client pitch).
- Referral tracking: one source field, one intake prompt, and the monthly top-referrer report.
- Lapse flags + 30-day win-back tasks with a required reason code.
- Owner dashboard: next-90-days renewals by week and producer, task overdue list, cross-sell worklist count.
- Training: two recorded walkthroughs (producers, service lead) + a one-page runbook.
Out of scope (explicit): new CRM purchase or migration, carrier quoting/rating integrations, claims workflows, commission accounting, client portal, marketing campaigns to prospects (this is a renewal add-on for existing clients only), and any automated communication about coverage, price, or claims. Quoting any of these later is a separate Blueprint or a change order — never a mid-build addition.
Acceptance test: v1 is accepted when (a) a test policy set at 90 / 60 / 30 days creates the right tasks for the right producers, (b) a test renewal sequence sends its first touch, logs it, and stops the moment a test reply arrives, (c) the dashboard's next-90-days renewal count and value match a hand count from the same policy export. The QA bot runs this checklist against this spec before handoff; it fails loudly, it does not pass silently.
5. Recommended stack
| Layer | Choice | Why |
|---|---|---|
| CRM (system of record) | The client's existing CRM — unchanged | The data and the team's habits already live there; migration is the costliest, riskiest way to buy a reminder system |
| Add-on automation | Make (n8n if the client later wants self-hosting) | Reads policy dates and status from the CRM, creates tasks, sends from producers' own mailboxes, writes the log back — configuration, not a platform |
| Messaging | Producers' existing email accounts; call tasks inside the CRM | Renewal mail must come from the producer the client knows, not a system address |
| Cross-sell rules | A maintained rules table (lines held → lines to flag), reviewed quarterly | Deliberately boring: rules the owner can read and change, not a model making coverage judgements |
| Dashboard | The CRM's native reporting + the add-on's renewal view | No BI tool to learn |
Custom code in v1: none. Everything above is configuration + automation + the context assets of §3, on accounts the client already owns. If the book doubles, §8 names the trigger where a deeper policy-system integration starts paying for itself.
6. Timeline
| Phase | Duration | Owner |
|---|---|---|
| Blueprint (this document) | 7 days from paid intake | AI Build Concierge |
| Client decision window | Up to 60 days — the $995 credit holds | Client |
| Managed Build: renewal layer + task wiring | Weeks 1–2 | Concierge + builder bench |
| Voice pack + touch library, producer approval round | Week 3 | Client (one ~45-min review per producer group) |
| Cross-sell rules + dashboard + acceptance test | Week 4 | Concierge QA |
| Training + handover | Week 5 | Both |
| Total, decision → live | ~5 weeks |
7. Fixed price
| Item | Price | Terms |
|---|---|---|
| Build Blueprint (this document) | $995 | Paid at intake. Credited in full toward the Managed Build |
| Managed Build v1 (spec §4, complete) | $11,500 fixed | 50% ($5,750) to start, 50% on acceptance test passed. 2 revision rounds included. Kill fee: if the client stops the build mid-flight, work-to-date is invoiced at the milestone reached and everything built is handed over — no hostage code |
| Care Retainer (optional, from go-live) | $950/mo | Automation monitoring, touch-library tuning, quarterly cross-sell rules review, monthly renewal report. Tool costs (automation tier) pass through at cost — estimated $30–$60/mo at this volume |
| Client's real first-year picture | $11,500 + ~$11,400 retainer + ~$540 tools ≈ $23,440 | Against the owner's own estimate of $55k–$85k/yr in avoidable non-renewal commissions, retaining even a third of the at-risk book covers it; that estimate is the owner's, not measured data — see §8 |
All prices inside the Concierge's published pricing (Blueprint $995 flat · Managed Build $3,500–$15,000 · Retainer $500–$1,500/mo). Fixed means fixed: if the build takes longer than §6, that is our cost, not the client's — scope changes go through a written change order priced before work starts. Proceeding costs $4,755 net new money at signing (first milestone $5,750 − $995 Blueprint credit).
8. Risks — stated, not buried
| Risk | Honest read | Mitigation in this plan |
|---|---|---|
| Renewal mail sounds robotic and cheapens a relationship business | The #1 real risk — clients chose this agency for humans | Voice pack from producers' real mail (§3); every sequence producer-approved before it sends; any reply stops automation instantly; calls stay human tasks, never auto-dialled |
| Policy data in the CRM is messier than the export suggests | Renewal dates are the whole system; bad dates = wrong tasks | Week 1 includes a date-integrity pass on a sample of the book; if more than ~5% of sampled dates are wrong, the build pauses and the honest recommendation is a data cleanup first — said in advance, here |
| The P1 payoff is smaller than the owner's estimate | Possible — the $55k–$85k figure is the owner's estimate, not measured data | The Retainer's monthly report measures actual retained renewals against the prior year; if retention does not move after two renewal cycles, the honest recommendation is to cut the retainer, and this Blueprint says so in advance |
| An automated message strays into coverage advice | A compliance and trust hazard, not a copy problem | Escalation rules (§3) are technical, not editorial: sequences contain reminders and meeting offers only; coverage words route to the producer; QA tests this before handoff |
| Scope creep toward "replace the CRM / add quoting" | The original ask, and the classic margin/reputation killer | §4's out-of-scope list is contractual; new ideas get their own Blueprint |
9. Next-step offer
- Proceed to Managed Build at the fixed $11,500 — the $995 Blueprint fee is credited, so starting costs $4,755 net new money (first milestone $5,750 − $995 credit). Signature on the MSA + SOW starts the clock.
- Or take this Blueprint anywhere. It is the client's property — spec, stack, and context assets are complete enough for any competent builder to execute. We'd rather earn the build than trap it.
- Or don't build. If the interview numbers were optimistic, the correct move may be a $0 version: the 90 / 60 / 30-day task cadence of §2 run manually from the existing monthly export for one quarter to measure P1 before spending anything. This Blueprint's audit tables are structured so the client can do exactly that.
Contracts (mutual NDA, MSA, SOW with IP assignment to the client) are provided before any payment beyond the Blueprint. The client owns the code, the data, and every context asset from day one.