Statistics for surveys

We generate surveys where we ask our customers about the quality of service provided. Responses are likert scale commonly (strongly agree, agree etc). Demographic data is gathered (or already exists in data bases).

In the past we analyzed this through regression and descrptive analysis. I was wondering if any could suggest approaches that might be interesting beyond that.

I know this is a vague question - I am hoping some have done similar surveys and might have suggestions.:yup: