Jason Ki|AI Studio
Back to work
Live
AI agentsDataBISaaS

Clearfraim

The AI team a 10-person company can't afford.

AI-native data integration and BI for small teams. Connects Shopify, Meta Ads, Stripe, Notion, and Sheets — agents answer business questions with source attribution.

Visit clearfraim
The problem

A 10-person company can't afford a data team — but it still needs answers from its data every day. The sources are scattered (Shopify, Stripe, Meta, Notion, Sheets), the questions are specific, and a generic LLM has no idea what "top SKU last quarter" means in your business. The gap is the canonical layer underneath, not the model on top.

The approach

Start with the data layer. Every connector lands in the same canonical schema, owned per-tenant, never trained on. Put a RAG agent on top that always cites its sources and is allowed to refuse. Wrap it in an eval harness that catches drift before customers see it. The model is the thin part; the stitch underneath is the moat.

Inside the build
  • 01Shopify, Stripe, Meta Ads, Notion, and Sheets in one canonical schema
  • 02Source-attribution on every answer — refuses when it doesn't know
  • 03Eval harness gates every prompt or model change before deploy
  • 04Multi-tenant, per-tenant data isolation, no model training on customer data
  • 05Drift watcher reruns the eval set hourly and pages on regression
Patterns inside this app

Clearfraim runs on 6of the studio’s patterns.

These are the standardized agents and automations nested inside this product. The same pieces show up — with the same contract — across every app the studio builds.

  • Source Connector

    Shopify, Stripe, Meta Ads, Notion, Sheets

    Pull anything in. Normalize. Keep current.

  • Router

    Routes business questions to the right answerer

    Classify the inbound. Send it to the right place.

  • RAG Answerer

    Answers business questions from connected sources

    Answer from your data. Cite the source. Refuse when unsure.

  • Trace Logger

    Source-attribution trail for every BI answer

    Every decision an agent makes is auditable.

  • Drift Watcher

    Watches RAG faithfulness + answer latency

    Catch the moment an agent stops performing.

  • Eval Runner

    Gates RAG answerer + router deploys

    Every agent ships with a test set it has to pass.

See every pattern
Want one in your stack?

Bring the question.

The Automation Studio mode builds patterns like the ones above into your product, then keeps them tuned.

See the modes Chat with Sage
Other work

The rest of
the body of work.

One flagship live, more in build. Every product runs the same standardized stitch underneath.

Browse the work