Six AI-QA workflows. The Maturity Model. A free readiness self-assessment.
The Institute is what Gloxx knows, written down. A documented methodology for testing AI-feature software — the workflows we run, the rubric we score by, and the readiness audit we deliver as a stand-alone product. The retainer is the same methodology, run on your code every week. Read it free; run the assessment in five minutes; book the audit when you want a written verdict.
Thirty questions across the six workflows the Institute audits against. You'll get your AI-QA maturity level (Ad-hoc → Continuous), your weakest workflow flagged, and the next-level gap described in concrete artifacts. Five minutes. The same rubric the paid readiness audit anchors to.
The Institute's workflows
Eval-suite design, golden-set curation, and baseline tracking. The discipline that turns "did you try it?" into "did the suite pass and did the baseline hold?"
Read the workflow → 02 · WorkflowPre-deploy gate specification, threshold enforcement, and the documented override policy. The procedure that decides what's allowed to ship.
Read the workflow → 03 · WorkflowProduction sampling, online evals, and the paging integration. The procedure that catches model degradation before users do.
Read the workflow → 04 · WorkflowTagged incident postmortems and the named-failure-mode catalog. The procedure that turns last quarter's pain into next quarter's eval coverage.
Read the workflow → 05 · WorkflowIn-product user reports, the triage queue, and the time-to-coverage SLO. The procedure that closes the loop from production failure to eval suite.
Read the workflow → 06 · WorkflowWritten refuse list, system-prompt enforcement, refusal-correctness evals, and the dated compliance review. The procedure that names what the AI must never do.
Read the workflow →Publication cadence
The Institute publishes weekly. Tools drop monthly. Reports are quarterly. Workflow documentation deepens on a rolling basis.
The Institute is the public methodology. The Gloxx Retainer is where a senior QA lead runs it on your code, every week, with accountability on the call when something breaks.
Book a 30-minute call →