Rafael M. EhlersRafael M. Ehlers

I solve complex customer problems and turn what I learn into better software.

I've spent 25 years in tech across software development, technical support, and product. I led a distributed support team, handled the issues that reached the end of the escalation path, wrote documentation and code, tested fixes, and brought what customers were struggling with back into the product.

Today I also build AI products and publish independent research on language agents, memory, and long-term interaction.

I'm open to work where customer understanding, technical depth, and product judgment belong together.

Selected work

Ink-on-bone engraving of a branching quiz flow being rebuilt by an indigo chat thread.

Case study

Rebuilding the Quiz editor used by thousands of Shopify brands as AI-native

How I diagnosed the problem with my own first-use recording and an NPS survey, then led a ground-up redesign of every surface: the canvas, components, live preview, and an AI assistant that edits by chat.

Read

Ink-on-bone engraving of a magnifying glass and balance scale over a page of text — instruments of critical reading.

Featured project

Jiddu — Critical Reading

Eight lenses in one for reading critically: fallacy detection, fact-checking, neutrality, paper explanation, AI-slop detection, adversarial review, live speech, and conversational context. Jiddu runs in the browser, as a Chrome extension, over a REST API, and through a hosted MCP server.

See the project

Ink-on-bone engraving: six small framed plates, each with a distinct emblem, connected in sequence by a single indigo thread — six papers bound into one research program.

Conceptual AI research

Six papers on language agents, memory, and individuation

Independent conceptual work on what language agents inherit across model successions, whether scale alone yields a persistent self, how perspective forms, and why stable deference may need a self-model first.

Read the papers