Multi-brand SEO & content platform
A multi-tenant platform that pulls search and analytics data for each brand, drafts articles, scores them, sends them for review and publishes to WordPress, Shopify, Webflow or a hosted blog.
- 1The problem
Each brand had its own sites, analytics and publishing tools, so content work was slow, inconsistent and hard to measure. One shared system had to serve every brand without any brand ever seeing another’s data.
- 2Our contribution
Designed and built by Kumar Sahil, who wrote the large majority of the code.
- 3What we built
A Next.js and PostgreSQL platform with background workers: keyword → draft → score → review → publish. An automated gate rejects any draft that scores under 70 or breaks a compliance rule and sends it back for rework before a person sees it. Fifteen job queues run on supervised workers, with publishers for WordPress, Shopify, Webflow and a hosted blog, and a separate NLP service for analysis.
- 4The result
In production. Results shared on request.
Other systems we’ve built
Reply Classifier Cascade
A cost-ordered classifier for English and Dutch cold-email replies that decides which replies become CRM deals, built so a false “hot deal” needs several layers to agree.Read the case studyLLM Gateway
A provider-neutral LLM gateway: code asks for a job, the gateway routes it through a chain of models with safe failover, a deadline per call, and the cost of every call written to a ledger.Read the case studyLLM Eval Gauntlet
Invariant-checked evaluation suites for tool-calling agents that run in CI and fail the build when an agent invents a number, leaks its prompt or obeys an injection.Read the case studyFind the workflow worth automating first.
Tell us about one process that costs your team hours every week. We will tell you honestly whether AI or automation is the right fix, and what a first build would take.