[All systems](https://mybb.ai/systems/) # Every family’s file *ready before the meeting.* One workspace for the whole agency, on top of its existing tools: every family’s file ready before the meeting, answers from policy terms with their source, and the follow-up drafted after it. Client An insurance and financial-planning agency Industry Insurance, pensions and savings Connects to The agency’s client system (read-only), email, calendar, call recordings, spreadsheets, insurers’ commission statements ## What we built - The family workspace - The knowledge and AI layer - The finance desk The system, drawn with sample data. We never show a client’s own screens. ## 01 Overview The agency’s advisers spend their best hours with families. The workspace sits on top of the tools they already use and files every lead, email, call and document to the right family, so the file and a brief are ready before each meeting. Answers cite the policy terms they came from, and the follow-up is drafted after the call. 01 ### The family workspace One file per household: its policies, conversations, tasks, proposals, claims and a brief. 02 ### The knowledge and AI layer Documents read and searched in Hebrew, every answer cited, every model call recorded. 03 ### The finance desk Cash flow, commission statements and their gaps, policy milestones and new-offer matching. ## 02 The challenge Preparing took longer than the meeting. Client data sat in the agency’s client system, with portfolios and cash flow in spreadsheets, mail in one place and the calendar in another. Preparing a meeting meant collecting all of it by hand. Answers were dug out of policy documents, each call was written up several times, and commission statements were checked line by line. ### What the client wanted to achieve #### Prepared before every meeting The family’s file and brief, ready without collecting anything by hand. #### Answers with their source Every answer cites its passage, or says it has none. #### Write each call once One summary becomes four follow-ups. #### The owner stays in control AI proposes and a person approves, with one switch to pause it. ### How it worked before - A family’s history across systems, spreadsheets and the inbox - Answers dug out of policy documents by hand - Each call written up several times ## 03 How we built it 1. 01 **Foundation and permissions** A Hebrew workspace, staff roles enforced on the server, every source kept as its original, and an approvals queue. 2. 02 **Knowledge and customer context** A read-only copy of the client system, Hebrew document reading, and search that cites its answers. 3. 03 **Intake and operations** Leads from forms, mailbox rules, call transcription, cases and tasks, the calendar and the family file. 4. 04 **Professional outputs** Exact calculations, comparisons, proposals, a claims workspace and Hebrew PDF reports. 5. 05 **Finance and the policy lifecycle** Cash flow imports, commission statements and their gaps, policy milestones and new-offer matching. 6. 06 **A controlled assistant** An assistant across the whole workspace, with a screen that pauses all AI work at once. **Five stages in about four weeks** Each stage ended with a walkthrough on a fresh copy. 1. 01 **Foundation** **2 days** 2. 02 **Knowledge** **3 days** 3. 03 **Intake and operations** **9 days** 4. 04 **Professional outputs** **11 days** 5. 05 **Finance** **4 days** ## 04 How it works **How a family is ready for its meeting** Whatever arrives is filed to a family, prepared for the meeting and followed up after approval. 1. Step 01 **Arrive** **Leads and mail** Kept exactly as they were received. **Calls and documents** Recordings transcribed, documents read. 2. Step 02 **File** **Matched, then confirmed** A shared phone number only suggests a family; a person confirms it. 3. Step 03 **Prepare** **The family file** Policies, calls, tasks and proposals in one place. **Cited answers** From the policy terms, with their source. 4. Step 04 **Follow up** **Four drafts** Written from one summary of the call. **Approved, then sent** Sent once, and only after approval. **WhatsApp** ### A summary for the family Ready to copy, never sent on its own. **Email** ### The meeting email Insurance, pension, finance and next steps; a topic that was not discussed says so. **Client system** ### An entry ready to file For the agency’s client system. **The team** ### A handover The decisions and the tasks that came out of the call. ### Who stays in control - Everything sent to a customer waits for approval, and goes once - Only a person can start an email to a customer - One switch holds all AI work while intake keeps running - No customer document ever carries a commission or cash flow figure - A phone number alone never identifies a person ## 05 The outcome Everything that arrives is filed to the right family. Before a meeting the file and the brief are ready, questions are answered with their source, and after the call one summary becomes four follow-ups that go out only once someone approves them. | Before | After | | --- | --- | | A family’s history across systems, spreadsheets and the inbox | One family file, with a brief before each meeting | | Answers dug out of policy documents by hand | Questions answered with the passage they came from | | Each call written up several times | One summary and four drafted follow-ups | | Commission statements checked by hand | Gaps and missing payments flagged | | Renewals and reviews remembered by people | Reminders per policy and per family | ## 06 Key figures **382 *of 382*** checks held in the final stage’s end-to-end walkthrough **8 *of 8*** test questions answered with the right source, or correctly declined **2,955** automated tests passing **Checks held at the end of each stage** Every stage closed with an end-to-end walkthrough on a fresh copy. Intake **166 of 166** Outputs **233 of 233** Finance **382 of 382** ## 07 Technology What the system runs on, for the technical reader. Cloud AWS Containers Managed PostgreSQL File storage and a CDN AI Claude and OpenAI, behind one gateway RAG with hybrid search Local multilingual embeddings Documents and speech OCR Hebrew speech-to-text Hebrew PDF reports Integrations The client system, read-only The mailbox Online forms The calendar Call and video recordings Insurers’ commission statements How we build TypeScript React PostgreSQL A background job queue A walkthrough at the end of every stage ## 08 What comes next Next, the assistant across the whole workspace, security and backups, then a first trial on the agency’s own records. ## 09 About ### About the client An insurance and financial-planning agency that looks after families’ insurance, pensions and savings. We name a client only with their permission. ### About MYBB MYBB builds systems around how a business already works. We diagnose it with MYBB ROIQ, build the system, launch it with the team and keep running and improving it. [All systems](https://mybb.ai/systems/) ## Questions about *our work.* **Can you build something like this for my business?** Each system here was built around one business. Answer the 10 questions, and within 48 hours your growth plan shows what we would build for yours. **Why don’t you name the clients?** We name a client only with their permission. Until then, each system is described by the kind of business it serves. **Are these the real screens?** They are redrawn with sample names and numbers. We never show a client’s own screens or data. **My business is in a different industry. Does that matter?** No. We start from how your business works, not from a template for its industry. **Will we have to replace the tools we use?** We start with what already works. The system may keep some of your tools, connect them, and add what’s missing. **Who decides what the AI does?** We agree with you where AI helps and where a person reviews, decides or approves. Those rules are part of the blueprint. **Who runs the system once it’s built?** We do, with your team. We keep running it and improving it as your business changes. **How is the price set?** By the scope, the connections and what the rollout needs. The price is in the blueprint, and nothing is built before you approve it. [Every meeting, prepared for you.](https://mybb.ai/start/) We build workspaces on top of the tools your agency already uses, so the preparation is done before you walk in. Tell us how your agency works. [Start with MYBB ROIQ](https://mybb.ai/start/) Prefer to talk first? Email [welcome@mybb.ai](mailto:welcome@mybb.ai) --- Source: [An insurance and financial-planning agency | Our work | MYBB](https://mybb.ai/systems/insurance-planning/)