Workflow
AI Product Requirements Workflow
Turn a fuzzy business need into requirements a team can build from — interrogate the need into concrete requirements, shape them as user stories, and write the PRD.
Build a CRM with AI
The full path to a CRM that fits your sales process — define the contacts, deals, and pipeline, model the data that ties them together, then build the roles, integrations, and pipeline UI, and ship.
Overview
A CRM is not a generic app — it's a specific data model with a sales process running through it: contacts and the accounts they belong to, deals moving through pipeline stages, the activities that push them forward, and the lifecycle from lead to customer. Build it like a blank SaaS and you get a database with forms; build it as a CRM and the contacts/accounts/deals/pipeline model is the spine everything hangs off. This project builds that spine deliberately. It pins what your sales process actually needs, cuts it to a first release, then models the CRM data (the step that makes or breaks it), designs the API around contacts and deals, builds the roles that decide who sees whose pipeline, wires the email and lead-source integrations a CRM lives on, designs the pipeline-and-contact UI, and ships. It is specifically a CRM — not a SaaS MVP with a different label, not an internal admin tool, not a two-sided marketplace — so every stage serves the customer relationship and the sales workflow. Each stage connects to a NewPrompt workflow you can run on its own; together they carry a CRM from a sales process to a platform your team works deals in. You own the process; the project keeps the CRM model at the center.
The journey
Each stage runs a NewPrompt workflow, with a supporting resource and tool. Work them in order — the output of each stage feeds the next.
See the execution map →Define & Scope
Clarify what you're building and for whom.
-
Define what your CRM must do
Pin the CRM to your actual sales process — the contacts and accounts you track, the deal stages your pipeline moves through, the activities that count — so the build serves how your team really sells, not a generic template.
Outcome Requirements grounded in your contacts, deals, and pipeline. -
Cut it to a first release
A full CRM is years of features; a first release is the core loop — capture a contact, open a deal, move it through the pipeline. Separate that from everything that can wait.
Outcome A first-release scope centered on the core sales loop.
Design
Design the right solution before building.
-
Model the CRM data
This is the step that makes it a CRM: model contacts, the accounts they belong to, deals and their pipeline stages, and the activity history that ties them together — the relationships a sales team lives in. Get this right and the rest is plumbing; get it wrong and it's a CRM in name only.
Outcome A contacts/accounts/deals/pipeline schema that fits the sales process. -
Design the API around contacts and deals
Design the endpoints the CRM is built on — contacts, accounts, deals, pipeline transitions, activities — as a contract before code, so the UI and integrations develop against a stable surface shaped to the CRM model.
Outcome An API contract for contacts, deals, and pipeline operations. -
Design the pipeline UI
Design the components a CRM is used through — the pipeline board, the contact and account views, the deal cards reps drag between stages — as a reusable system, so the interface reflects the sales process instead of a generic CRUD grid.
Outcome A component system for the pipeline board, contacts, and deals.
Build & Refine
Build, test, secure, and make it production-ready.
-
Build roles and record ownership
A CRM's access model is its own problem: reps see their own deals, managers see the team's, admins see everything, and record ownership decides who can touch whose pipeline. Design the roles and permissions before the data is exposed.
Outcome Roles and record-ownership rules for reps, managers, and admins. -
Integrate the sales stack
A CRM that doesn't connect to email, calendar, and lead sources is a data-entry chore nobody updates. Wire those integrations via webhooks and events — with the retries that keep a logged email or a captured lead from vanishing — so the CRM fills itself.
Outcome Email, calendar, and lead-source integrations wired reliably. -
Run a security review
A CRM holds customer data behind role-gated access and runs on integrations — review the auth, record-ownership, and input paths the way an attacker would, and back the findings with tests, before it's live.
Outcome The auth, record-ownership, customer-data, and integration paths reviewed for vulnerabilities before release.
Ship & Validate
Ship with confidence and validate results.
-
Ship the CRM
Cross from built to live — readiness checked, rollback planned, monitoring in place — and put the CRM in front of the team whose deals will now live in it.
Outcome The CRM shipped with a rollback path and monitoring.
Expected outcome
A CRM built on its real model — a contacts/accounts/deals/pipeline schema, an API and roles designed around it, the sales integrations a CRM runs on, a pipeline-and-contact UI, and the whole thing shipped — a platform your team works deals in, not a generic app with the word CRM on it.
Best for
- Building a CRM that fits a specific sales process, not a generic tool
- Modeling contacts, deals, and pipeline so they actually tie together
- Teams who outgrew a spreadsheet but do not want bloated SaaS
Not for
- Anyone happy with an off-the-shelf CRM
- A project with no sales or relationship data
FAQ
Why build a CRM instead of buying one?
When your process does not fit the off-the-shelf tools. This project models contacts, deals, and pipeline around how you actually sell, then builds it — worth it when the generic option fights you.
Is this a full app?
Yes, a real CRM application, not a mockup. But NewPrompt does not build it for you: it gives you the structured path and a prompt for each stage — data model, API, roles and record ownership, pipeline UI, security review, and shipping. You run those prompts in your own AI tools and own the build, validation, and deployment.
Does it handle permissions?
Yes — roles and record ownership are a dedicated stage, because a CRM without access control leaks the wrong deals to the wrong people.
How do I build a CRM with AI?
Run it stage by stage in your own AI tools. This blueprint gives you the ordered path and a prompt for each stage: pin your sales process, cut a first release, model the contacts/accounts/deals/pipeline schema, design the API, build roles and record ownership, wire the sales integrations, design the pipeline UI, and ship. You run each and own the CRM.
What should a CRM MVP include?
The core sales loop, nothing more: capture a contact, open a deal, and move it through your pipeline stages. This blueprint's second stage cuts a full CRM down to exactly that, separating the loop reps use daily from the reporting, automation, and extra integrations that can wait for a later release.
Does this blueprint migrate my CRM data automatically?
No. This blueprint structures the build; it does not move your old CRM's records for you. Its stages model the contacts/accounts/deals/pipeline schema and wire email and lead-source integrations, but importing legacy data is a migration you plan and run yourself against that new schema once it exists.
Workflows in this project
Workflow
AI MVP Planning Workflow
Cut a product idea down to the smallest first release that proves the core value — separate the real must-haves from everything that can wait, then define the MVP and its success signal.
Workflow
AI Database Design Workflow
Design a schema on its data, not a hunch — model the entities and relationships, set the constraints that protect integrity, plan indexes around real queries, then document the schema and migration.
Workflow
AI API Design Workflow
Design an API on its contract instead of discovering it endpoint by endpoint — model the resources, design the endpoints and payloads, pin the contract, then review it before code locks it in.
Workflow
AI Auth & Identity Workflow
Design access control before you build it, not after a breach — choose the authentication approach, model the roles and permissions, review the design for gaps, then document the identity model.
Workflow
AI Integration & Webhook Workflow
Connect systems so they don't break each other — map the integration boundaries, design the event and webhook contracts, plan retries and failure handling, then document the integration.
Workflow
AI UI & Component Design Workflow
Structure a UI so it stays consistent as it grows — inventory the screens, break them into reusable components, specify the component system and its rules, then review the structure for drift.
Workflow
AI Security Review Workflow
Review code for what an attacker would do, not just what tests catch — anchor the model as a security engineer, run a threat-focused review, then back the findings with auth and input tests.
Workflow
AI Deployment & Release Workflow
Cross the gap between 'tests pass' and 'safe in production' — assess release readiness, plan the deploy and its rollback, and set up the monitoring and launch checks before you ship, not after.
Resources used in this project
Resource
Product Requirements Assistant
Turn a rough feature idea into a structured requirement: problem statement, acceptance criteria, and what's explicitly out of scope.
Resource
Startup Advisor Role Prompt
An expert startup advisor role prompt — stage-aware, capital-efficiency-minded, and built to name the riskiest assumption in any plan instead of cheering it on.
Resource
Missing Index Analysis — Which Indexes, at What Cost
Map every predicate, join, and sort to the index that serves it — or doesn't. Composite order rules, covering decisions, and the write tax nobody mentions.
Resource
API Review Checklist Prompt
Architecture review for the public surface: abstractions that earn their place, dependency direction, seams, and the patterns the codebase already has.
Resource
RBAC Design Prompt
Design a role model that scales — roles derived from real permissions, the role-permission mapping, and the inheritance and edge cases before you hardcode 'isAdmin'.
Resource
Turn a JSON Schema into a Prompt
You have the schema — fields, types, requirements. The translation into a prompt the model actually follows: schema lines, realistic example, and validation rules.
Resource
Software Engineer Role Prompt
Make AI act as a software engineer — design, implementation, and testing trade-offs — instead of a generic assistant that writes whatever you ask.
Resource
Security Code Review Prompt
Twelve security checks — injection, auth, secrets, SSRF, privilege escalation — reviewed the way an attacker would read the code.
Resource
Production Readiness Review Prompt
SHIP or DO NOT SHIP: twelve checks on failure modes, observability, rollback, and load — the review that happens before the incident.
Resource
Schema Design & ERD Prompt — Entities, Relationships, and Keys
Turn product requirements and key entities into an ERD-ready schema spec: tables, fields, primary and foreign keys, relationships with cardinality, indexes, and constraints — with the modeling gaps named as open questions.
Resource
Design System Spec Prompt — Components, States, and Accessibility
Turn UI requirements and component needs into a design-system spec: a component inventory with states, variants, responsive behavior, accessibility requirements, microcopy rules, and developer handoff notes.
Tools used in this project
Tool
System Prompt Generator
Build structured system prompts from role, tone, constraints, and model target.
Tool
Role Prompt Generator
Generate expert role prompts — perspective, responsibilities, and decision criteria, not just "act as".
Tool
SQL Optimization Prompt
Build evidence-based SQL optimization prompts — goal, platform, and the evidence you have turn into a query tuning contract.
Tool
JSON Output Prompt Builder
Build prompts that return structured data — JSON first, with YAML, XML, and CSV modes — parseable every time.
Tool
Multi-Step Prompt Builder
Break a big goal into a sequential prompt workflow — each step with an objective, prompt, and expected output.
Tool
Markdown Output Builder
Build prompts that produce documents in a fixed structure — headings, sections, and tables.
Tool
Code Review Prompt Generator
Generate code review prompts for any scope — snippet, file, diff, or full pull request — with focused review rules.
Ways to Use This Project Path
Practical project ideas you can build from this base project path — each opens in the Project Advisor.
Recommended next project
Project
Build a Customer Support System with AI
The full path to a support operation, not just a bot — stand up the knowledge base, route the tickets, add the AI agent, integrate your stack, close the feedback loop, evaluate, and deploy.
Related projects
Project
Build an E-commerce Store with AI
The full path to a store you own end to end — model the catalog and orders, design the storefront and checkout, add customer accounts and payments, then secure it, test it, and ship.
Project
Build a SaaS MVP with AI
The full path from idea to a shipped SaaS MVP — define and scope the requirements, design the architecture, API, and data model, then build it reviewed, tested, secured, cost-controlled, and deployed.
Project
Build an API Backend with AI
The full path to a backend you can put clients on — define the requirements, design the architecture, API contract, data model, and access control, then build it reviewed, tested, secured, and shipped.