CRM. Analytics dashboards. Automated data pipelines. Lead attribution. AI-powered insights. The conventional SaaS stack runs about $2,000 a month, plus implementation costs. We built it for $47.
We call it Lighthouse.
The challenge
At Coastalview Advisory, we needed to centralize eight data streams into a single platform: website analytics, LinkedIn performance across three accounts, ad spend, lead attribution, pipeline status, assessment funnels, qualitative intelligence, and AI-powered marketing analysis.
We also needed a CRM. Enterprise CRM pricing did not match how an advisory firm actually sells. The work is high-value and relationship-driven, not high-volume. Salesforce at $300 a month felt like renting a warehouse for a jewelry case. The conventional answer would have been HubSpot, Salesforce, Sprout Social, a dashboard tool, and Zapier glued together. We chose a different path.
What we built
Lighthouse is a marketing analytics platform with an integrated CRM, built on a small set of accessible tools. Google Sheets is the central database. Make automations pull data daily from GA4, our assessment events, and form submissions. A companion app on Vercel provides nine modules for manual entry: lead tracking, LinkedIn analytics, ad spend imports, pipeline kanban, profile statistics, a UTM builder, qualitative notes, and AI insights. Looker Studio renders the executive dashboards. The Claude API powers the AI analysis with full access to our operational data.
Total monthly cost: $47. Twenty-nine for Make. Eighteen for the Claude API. Everything else is free.
The CRM that should not exist
The CRM lives directly inside Lighthouse. Same data layer. Same interface. Every lead is tracked from source to close. The pipeline kanban provides drag-and-drop stage management. Source attribution connects each lead back to the campaign that generated it.
This is arguably better architecture than the conventional approach. In a typical setup, analytics data lives in one platform, leads in another, pipeline in a third. Connecting them requires middleware. In Lighthouse, there is no integration because there is no separation.
The AI advantage SaaS cannot match
Every SaaS platform in the MarTech stack is racing to bolt on AI features. Salesforce has Einstein. HubSpot has assistants. Almost universally, the experience is mediocre compared to going directly to a frontier model.
Because CVA owns its data layer, we connected Lighthouse directly to Claude. Every piece of marketing data feeds into our project workspace with full operational context. When we ask for analysis, strategic recommendations, or pattern recognition, the AI has real business data. Not a generic chatbot embedded in a dashboard. Our actual AI working with our actual data.
When you own the data, you choose the AI. When you rent the platform, the vendor chooses it for you.
What this means for content operations
If you run a content operation, an in-house team, an independent agency, a media company, a production studio, consider how many platforms you are renting for workflows you could own. The CRM your pipeline does not justify but your business needs the discipline of. The production tracker bent into shape because you bought Asana for general project management and spent months customizing it for content workflows it was never designed for. The client approval workflow duct-taped across email, Slack, and a shared folder because no single tool does it the way your business actually works.
Every one of those can now be built as a custom tool, designed around exactly how your operation works. No engineering team. No vendor evaluation. No six-month implementation.
We have entered a post-SaaS era for small and mid-size content companies. Building custom tools that meet your exact needs, for a fraction of the cost, in a fraction of the time, is about to be the new normal.