What a research-to-production handover should contain
At some point a result stops being yours and becomes a system somebody else has to run. That moment is usually informal: a meeting, a repository link, a promise to answer questions. The people receiving it inherit everything the prototype assumed and nothing about why.
Production readiness can be written down
Google engineers turned this into a checklist. The ML Test Score is a rubric of 28 tests, drawn from running production machine learning systems for years, that scores how ready a system is to go live and how much technical debt it carries. You do not need to adopt it wholesale. It is useful as proof that readiness is a finite list of concrete checks, not a feeling.
concrete tests in Google's ML Test Score rubric for production readiness and technical debt reduction.
A handover does not need 28 items. It needs a small set of things that are specific enough to act on.
The essentials
| The receiving team needs | In practice |
|---|---|
| What it is for | The decision or product this supports, and the failure that would matter most |
| What it assumes | Input ranges, data freshness, the conditions it was validated on, where it degrades |
| How to rebuild it | One command from a clean checkout, with versions pinned |
| How to know it is healthy | The few signals that matter, and the thresholds that should page someone |
| What to do when it is not | A first-response runbook a person who did not build it can follow at 2 a.m. |
| Who to ask | Named owners for the method, the data and the infrastructure, and how long support lasts |
Test the handover
The only reliable check is to have the receiving team do something with it before the original team steps away: rebuild it, change a parameter, respond to a simulated incident. Every place they get stuck is a line missing from the document.
- Receiving team rebuilds the artefact from a clean checkout, without help.
- They change one parameter and explain what should happen before running it.
- They respond to a simulated failure using only the runbook.
- They list every question they had to ask. That list is the next version of the document.
Handovers fail quietly. The system keeps running until the first change nobody understands. A small amount of structure up front is much cheaper than rediscovering the assumptions later.
Sources