Eidetic

Robin Miklinski · independent AI and software product engineering · London

I turn difficult briefs into software that holds up in use.

Eidetic is my independent AI and software product engineering practice. The work draws on fifteen years across defence, retail, collaboration software and global SaaS, spanning hands-on engineering, quality leadership and applied AI.

Discuss a project → See the work →
  1. Understand how the work gets done today
  2. Find the parts that could be simpler
  3. Remove what isn’t earning its place
  4. Build the smallest complete system
01 / Ledger

Selected work and the decisions behind it.

None of it began as portfolio work. Each item solved a problem or recorded a decision that mattered at the time.

Public work links to source. Private work is marked clearly.

Year Context / System The decision or constraint Evidence
2026 eidetic-studio Anything I haven’t checked against the manual is marked as unchecked, so I don’t lose an evening to a menu path that doesn’t exist. Public repo →
2026 yr2l-emails It writes the reply and leaves it in drafts. Someone reads it before it goes. Public repo →
2026 ai-complaint-resolution Drafts FCA complaint responses. The QA report is published with the code: 180 test cases, plus cost guards in CI. Public repo →
2019–2026 Reward Gateway, now part of Edenred Led quality engineering across the business and owned quality and release assurance for its first customer-facing AI product. Built the evaluation approach from scratch and gave the launch panel a defensible basis for its decision. Employment history
2025 eidetic-sample-tools Builds device-ready exports for Octatrack MKII, Digitakt and TR-8S while leaving the source library unchanged. Public repo →
2025 Agent infrastructure (Mac mini) A linter that enforces my writing rules, records why each one exists and denies risky operations by default. Not public
2024 BrowserStack, London Spoke on AI in test automation. London, November 2024. Talk
2021 cypress-slack-reporter Cypress results straight into Slack and CircleCI. I extended and maintained it for Reward Gateway’s CI workflow. Public repo →
2019 ZAPClient OWASP ZAP security client in the CI pipeline. Automated vulnerability scanning. Public repo →
2018 Tooling budget Restructured a six-figure annual tooling budget by moving the capability in house. Coverage increased without increasing annual cost. Not public
2016 Black Friday peak trading Designed the Black Friday load-testing programme at five-figure concurrency and built the team that ran it. The platform went through peak trading without a performance incident. Not public
2015 OWASP ZAP in CI (Huddle) Moved security scanning into the TeamCity pipeline, so a scan ran on every build instead of once before a release. Not public
2010–14 Secure intelligence data systems Worked on data processing, quality and release assurance for a secure intelligence client, where traceability and controlled change were part of the engineering standard. Not public
02 / The story

I owned release assurance for Reward Gateway’s first AI product.

I owned quality and release assurance for Reward Gateway’s first customer-facing AI product. The product had already been built, but there was no test infrastructure and no defensible basis for a launch decision.

I built security and evaluation from scratch. Exact-output checks were unsuitable because the model answered differently on each run. The suite tested whether responses stayed within the system’s boundaries and did the job asked of them, across repeated runs.

The evidence exposed material gaps before launch. I separated what we could prove from what remained unknown and took both to the launch panel. They accepted the residual risk and approved the release.

The suite became the release gate for later AI work. I also introduced follow-up question rate as a product signal because a second question usually meant the first answer had not done its job.

03 / Workbench

Public repositories, and the decisions that shaped each one.

ai-complaint-resolution Python

Complete AI product with published QA report

Multilingual response drafting for FCA-regulated complaints. The system drafts a response; a person approves it before anything is sent. The 180-case QA report is published with the code.

Applied AI View Repository →
producer-release-os TypeScript

Local-first planning tool for music producers

A local-first planning tool for music releases. React 18, entirely in the browser, with no backend. Built around a small component library, with the scope kept deliberately narrow: no accounts, no payments.

Interfaces View Repository →
eidetic-sample-tools Python

Sample library curation for hardware samplers

Builds device-ready exports for Octatrack MKII, Digitakt and TR-8S while leaving the source library unchanged.

Services View Repository →
eidetic-studio Markdown

My studio, in git

Wiring, the MIDI clock chain, a log of what broke and what fixed it, and why the setup is the way it is. Anything I haven’t checked against the manual is marked as unchecked, so I don’t lose an evening to a menu path that doesn’t exist.

Direction View Repository →
cypress-slack-reporter TypeScript

CI reporter for Cypress test results

Puts Cypress run results straight into Slack and CircleCI, so a red build shows up where the team already is. I extended and maintained it for Reward Gateway’s CI workflow.

Platform View Repository →
ZAPClient Python

OWASP ZAP security scanning in CI

Automated security scanning wrapped for continuous integration. Committed in 2019.

Platform / Security View Repository →
04 / Measurement

The numbers need to survive scrutiny.

I document how each metric is calculated, what it excludes and when the definition changes. That gives a team a reliable basis for release decisions and for judging whether a change worked.

05 / Capability index

  1. 01 Interfaces

    • workflows
    • integrations
    • design systems
    • React 18
    • design tokens
    Evidence: producer-release-os →

  2. 02 Services

    • audio processing
    • APIs
    • metadata cleaning
    • background tasks
    Evidence: MP3-Service → · yr2l-emails →

  3. 03 Applied AI

    • retrieval
    • classification
    • agents
    • evals
    • guardrails
    • red-teaming
    • prompt injection
    Evidence: ai-complaint-resolution →

  4. 04 Platform

    • architecture
    • reliability
    • performance
    • CI/CD
    • security scanning
    Evidence: cypress-slack-reporter → · ZAPClient →

  5. 05 Direction

    • technical strategy
    • feasibility
    • decision records
    • risk governance
    Evidence: eidetic-studio →
06 / About

Robin Miklinski

Background

For fifteen years I’ve built systems across defence, retail, collaboration software and global SaaS. I read Internet Engineering at Exeter and began in defence data systems, where defining what a system was allowed to do came before asking it to do anything.

I still write code in Python, JavaScript, TypeScript and C#. The work also spans the architecture around it, the evidence used to judge it, and the guardrails that determine when a system must stop and ask.

Outside work

I produce electronic music and DJ as Eidetic. The studio is documented in much the same way as the software: notes made as I go, decisions kept in git, and nothing recorded as fact until I’ve checked it against the manual.

07 / Contact

Tell me where the work is getting stuck.