Product-Market Fit (PMF) Engine

Vision: Vibn is not just a code generator; it is a "Business in a Box" platform. The PMF Engine bridges the gap between "Main Street" businesses (SMBs) and "Silicon Valley" SaaS by automating market research, lead generation, and Go-To-Market (GTM) strategy.

The Objective

When a user wants to build a product (e.g., "Software for Dentists"), the Vibn AI autonomously executes a complete End-to-End Discovery Pipeline. It guarantees the user receives:

Real Potential Customers: A qualified list of verified local businesses (with emails/phones) ready to be pitched.
Real Competitors: Identification of the proprietary SaaS incumbents currently dominating that specific niche.
Software Requirements (SRS): Database schemas and user flows extracted directly from proven open-source repositories in the same vertical.
An SEO Content Plan: Keyword gaps and blogging topics based on where competitors are overspending on Google Ads.
Website Positioning: Value propositions and wedge strategies designed explicitly to exploit competitor weaknesses.
Financials & Pricing: A calculated MRR model and disruptive pricing strategy based on local TAM and competitor costs.

1. Market Sizing & Lead Generation

Goal: Prove the market exists, identify customer pain points, and provide the founder their first 100 cold-outreach targets.

Mechanism: The AI maps the software idea to a specific Google Business Profile category (e.g., gcid:dentist).
Tooling: Uses two distinct DataForSEO Business Listings APIs:
1. search/live API: Used to fetch the exact Total Addressable Market (TAM) counts and extract the raw lead data (emails, addresses, phones). Crucially, this API is passed strict filters (e.g., ["address_info.country_code", "=", "CA"] and ["work_time.work_hours.current_status", "<>", "closed_forever"]) to guarantee accurate national counts and exclude dead businesses.
2. categories_aggregation/live API: Used to perform deep qualitative analysis. This endpoint aggregates thousands of Google Reviews to surface the Top Customer Pain Points (e.g., "receptionist", "price", "long wait") and break the market down into specific sub-niches (e.g., Cosmetic Dentistry vs. Pediatric Dentistry).
Output: A structured JSON of real-world businesses with extracted emails, alongside a summary of what patients/customers complain about most frequently in that market.
Data Co-op Model: Searches are charged via credits. Results are cached in BigQuery (vibn_market_data). Over time, Vibn builds a proprietary, zero-cost database of every SMB in North America.

2. Competitor Identification & Website Teardown

Goal: Understand what the market leaders are doing and how to beat them.

Mechanism: The AI identifies the top 3 proprietary SaaS competitors.
Tooling: Natively uses http_fetch and browser_navigate (headless browser) to scrape competitor URLs.
Output: Extracts their pricing model (or lack thereof), value propositions, feature sets, and website page hierarchy to inform the user's build plan.

3. SEO, Keywords & Ad Spend Analysis

Goal: Find the cheapest acquisition channels and keyword gaps.

Mechanism: The AI analyzes the competitors' domains.
Tooling: Uses DataForSEO Competitive Analysis / Keyword APIs (via the market_seo_analyze MCP tool).
Output: Estimated monthly Google Ads spend, top-performing paid keywords, and low-difficulty organic keyword gaps (e.g., "open source dental booking widget").

4. Open Source Baselining & Architecture Extraction

Goal: Never start from scratch if a foundation already exists, and ensure the domain data models are accurate.

Mechanism: The AI searches GitHub for actively maintained starter kits. It then explicitly reads the README and source code to reverse-engineer the "Software Requirements Specification" (SRS).
Tooling: Uses the github_search and github_file MCP tools.
Output: Extracts the exact database schemas (e.g., Camp Sessions, Parent Waivers, Cabin Assignments) and User Flows required to build a competitive product in this niche.

5. Automated Plan Generation

Goal: Turn all of this research into actionable engineering and marketing tasks.

Mechanism: The AI acts as the user's product manager, writing the business plan directly into the Vibn platform's Plan Tab.
Tooling: Uses plan_vision_set, plan_decision_log, and plan_task_add.
Example Output:
- Vision: "A $99/mo transparently priced patient engagement widget for dental clinics."
- Decision: "Targeting 'booking widget' SEO gap instead of 'practice management'."
- Tasks: Generated tickets for the AI to start scaffolding the Next.js landing page and database schema.

6. The Missing GTM & Operations Opportunities

To truly provide a "Business in a Box", the PMF Engine also synthesizes the following automatically:

Compliance & Regulatory Flagging: (e.g., Identifying HIPAA/PIPEDA requirements for health-tech or SOC2 for fintech) and automatically injecting those requirements into the Build Plan.
Financial Modeling & Pricing: Using the TAM count and competitor pricing to calculate exactly how many customers are needed to reach $10k MRR, and recommending a wedge pricing strategy.
Integration Ecosystems: Identifying the existing tech stack of the leads (e.g., WordPress) and suggesting native plugins/widgets as an acquisition wedge.
Customer Discovery & Sales Scripts: Generating tailored cold-email templates, starting with "Discovery Call" scripts for founders to validate the product before turning on hard-sales campaigns.
Brand Identity Differentiation: Analyzing competitor aesthetics and generating a contrarian Design System (e.g., warm/consumer-focused vs. sterile/corporate) to save to the Design tab.

7. AI Credit Cost Estimation (The "Bill of Materials")

Goal: Give the user complete transparency on what it will cost to execute the entire plan.

Mechanism: Before clicking "Build", the AI calculates the complexity of the generated plan (number of services, expected tool rounds, data enrichment API calls, and social media agent runs).
Output: Presents a "Bill of Materials" detailing exactly how many Vibn AI Credits are required to scaffold, enrich, and ship the MVP, allowing the user to top-up their account before proceeding.

6.4 KiB Raw Blame History