I worked ~20 years ago doing this exact job at Royal Mail in UK

I did the same job back in the mid-90's at the facility discussed in the article when it first opened. The piece rate was probably higher, though the measure we cared about was keystrokes per hour so I don't know if I ever saw a real statistic for this. The work-load almost certainly has changed with technological improvement. Back then, my recollection is that we'd see more machine type than handwritten addresses, but only slightly. Also we were only filling in the gaps depending on how well the original OCR worked. Sometimes we'd have to key in the important portions of the whole address (house number, part of a street name, postal code)... sometimes just the postal code, and sometimes only a portion of the postal code. Some of these data entry modes were faster than others; the extended "zip code" data entry only required two numeric keystrokes whereas the full data entry mode require…

I worked on the LM side of this team ~8 years ago, and it sounds like they learned some lessons since you had to deal with them! The ML team was still in house and working on all sorts of projects, and there was a sizeable software team working on the software around this. One of my most valuable lessons working there as a green engineer - you can figure out more in an hour sitting down with the end user then months of meetings before then.

What does the data entry look like for this job? The article says, "Our keyers key about a thousand images an hour, so they're spending about 2 seconds on an image". Are keyers typing whole addresses in that quickly?