Topic

OpenAI.

OpenAI APIs back most of the AI work Remiam ships — GPT-4 Vision powers the Segment Analyzer's interior-photography labelling pipeline, GPT-4 handles content drafting and retrieval-augmented chat for Finding Mastery Bot, and the older GPT-3.5 era models powered the 2023 work when the bar for 'production-grade LLM' was set there. The studio uses the OpenAI Node SDK directly for tight integrations, and LangChain on top when retrieval and chunking get complex.

2 client works·1 product
Client work2
FINDING MASTERY · GPT-4 · LANGCHAIN2023PODCAST CORPUSN EPISODESEMBEDLANGCHAIN · OPENAIRETRIEVEEDITORBOTEDITORIAL CHATRESEARCH COLLAB · APPLIED AIPROJECT · CHATBOT15
Finding Mastery·2023·AI Chatbot · Research Collaboration · Editorial Tooling

Finding Mastery Bot

An AI chatbot built for Finding Mastery — the Michael Gervais podcast on the psychology of high performance — trained on their entire podcast back-catalogue so their internal editorial team could ask questions, surface guest insights, and write better content. Shipped in 2023 in the earliest days of production OpenAI, and the start of an ongoing research collaboration with Finding Mastery on applied AI.

Read case study →
SERPAPI · GPT-4 VISION · BATCH · USAEXPERIMENTALUSA · LOCATIONSLOCATION + SECTOR INPUTSCRAPEINTERIORSS3 · BATCHGPT-4 VISIONp-limit · BATCHLABELLABELS · LOCATION AWarm palette72%Pendant lighting61%Exposed brick48%Communal seating37%INDUSTRY COMPAREA · CAFEB · RETAILC · BANKTRENDS · GUIDANCEWEEKS OF FIELDWORK → MINUTESPROJECT · ANALYZER19
US Brand Strategy Firm · Confidential·2024·Experimental Product · AI Vision · Market Research

Segment Analyzer

An experimental AI product built for a US strategy client. Type a location and an industry sector — the tool scrapes that location, gathers interior photos, runs them through GPT-4 Vision to label features and surface percentage breakdowns, then lets you compare industries head-to-head on interior-design trends. Replaced weeks of in-person fieldwork with minutes of automated analysis.

Read case study →
Own products1