Yes, you would have to use the workaround that Hadley suggests:
From the red triangle at the top of the Fit Least Squares report
1. Save Columns > Prediction Formula
2. Save Columns > Indiv Confidence Limit Formula
Then
3. Graph > Profiler
4. Put all 3 saved columns into Y, Prediction Formula, and click OK
This will give the mean and upper and lower prediction limits as separate Y-axes on the profiler.
It would probably be possible to "hack" the saved StdErr Pred Formula column to use that generate confidence intervals on the profiler using this approach.