Every set finished close to failure counts toward its muscle, against a weekly range.
Five checks come first, then the weight moves one step of the weights you use.
Your best set per lift over six weeks, turned into an estimated 1RM.
A block that runs long, or fatigue well above your recent average.
Where your first program comes from.
Import a CSV export from your current app and Povver reads your newest 12 weeks. If you trained a steady split in the last six weeks and keep those training days, the program is built around them, with the lifts you already do. Starting weights and reps come from your last few sessions, and a weight comes from your own lifts only for a lift you have trained enough to trust.
If you pick different days, or your log shows no steady split, you get a starter plan where your own lifts take a slot. With no import it is a plain starter plan. Either way you look through the whole program before you make an account.
One workout in, one decision out.
Two steps of plain arithmetic work out your numbers. A language model then reads the pattern for each muscle group and proposes changes. A set of checks can throw those out before anything reaches your templates.
Finished working sets per muscle group, with the weight, reps and reps in reserve. Warm-ups, sets you did not finish and sets stopped four or more reps short are left out.
What the plan asked for against what you did, plus the direction your strength is going on that lift.
A language model reads the pattern for each muscle group and proposes one change, with a confidence score.
Rules that throw out a change built on too little evidence, and limits on how far one session can move anything.
With Auto-Pilot on, accepted changes go straight into your templates. With it off, they wait for you to say yes. You can also write your own plan, and then the automatic engine steps aside.
Hard sets per muscle, per week.
Volume is counted in hard sets per week for each of ten muscle groups. A hard set is a working set you finished with three reps in reserve or fewer. A set with no RIR logged counts as hard. It counts in full for the muscle the exercise is built for, and as half a set for each muscle that helps. Warm-ups, unfinished sets and sets stopped four or more reps short do not count.
Enough, productive, too much.
Each muscle group has a range, in sets per week. MEV is the least that still makes it grow. The MAV band is where most of your progress happens. MRV is the ceiling, where fatigue builds faster than you can recover from it. Together these are called volume landmarks.
Every muscle group starts from the same range: 4 sets, 10 to 18, 29. If you write your own plan, its weekly target sets the top of the band. The floor and ceiling stay where they are, unless your target sits outside them.
Under the floor, the model is told to add sets before it adds weight. No exercise gets added that would take a muscle over the ceiling. On a strength goal, 5 sets is enough, and no sets get added past it. A muscle that sits under its floor for eight weeks gets more work, without you having to spot it.
Reps in reserve, logged on every working set.
Reps in reserve is how many more you could have done. Weight and reps on their own cannot tell a hard set from an easy one. That is why it is logged for every set, and why it decides whether you progress.
Effort can step up through the session, as here. The targets are your template's, and they stay the same when the weight goes up. With none set, the target is one rep in reserve.
12, 10, 10 with effort going up is what tiredness looks like. Povver reads the whole session together, so a normal drop-off never turns into a higher target for the later sets.
RIR is your own estimate, and the more consistently you log it, the better Povver reads your sets. With none logged, a set counts as hard, and the weight goes up after two sessions in a row at the top of the range instead of one.
A strength number you never test for.
Estimated 1RM turns any set into one number, so 5 reps at 100 kg and 9 at 85 kg can be compared. No single session is taken as a result. Povver takes your best set from each of the last six weeks. Up 2% or more over the window is climbing, down 2% or more is declining, and anything between is maintaining. So is a lift whose last three weeks sit within 4% of the latest, or one whose weeks scatter too much to show a direction. The Strength card on the Intelligence tab looks back eight weeks, so the two can disagree about a lift, and each one tells you which window it used.
Load goes up when it is earned.
Reps go up first. Most lifts use double progression. Each session a set hits its rep target, that target rises by one to three reps, more when you had reps to spare. The weight goes up once you reach the top of the range at the target effort.
A weight increase has to pass all of these. Fail one and the weight stays.
One session that meets the rest of these is enough. With no RIR logged on the last set, it takes two in a row.
Each planned set logged, each one at its own rep target once reps in reserve are counted.
At most one rep harder than planned. Easier than planned is fine: it means the weight is light.
On the last set, counting reps in reserve past the target. 10 reps at RIR 3 with a target of 1 counts as 12.
If two or more increases on this lift have failed or been undone in the last four weeks, Povver waits.
Every set done at 120 kg, last set at the top of the rep range with the target effort. The step is sized from the reps you had left: one step of your weights, or up to 10% (5% on small lifts) when that is larger. It is rounded to the steps you load that lift in. The rep target drops to what the new weight predicts you can do. No progression in a deload week, on a lift that reads as declining, or into a muscle that reads as tired, whatever the numbers say.
What overrides the plan.
An automatic deload halves your working sets, takes about a fifth off the bar and asks for three reps in reserve. Your own plan can ask for a lighter cut, anywhere from 30% to 60% of the sets. Either way it is a planned easy week. Deload week: when to take one has the research behind it.
This week's work divided by your average over the last few weeks sets your fatigue status. A big jump moves you toward a deload, unless your average is so low that the ratio means nothing.
A session you cut short still counts toward volume. It cannot earn a heavier weight, though: the session that does has every working set done. A set more than one rep short of the bottom of the range, counting reps in reserve, takes the weight down a step next time.
A moderate or severe injury blocks recommendations that would load that area, and a severe one adds a deload. After three pain-free sessions it drops back to watching, and you can close it yourself whenever you like.
Once your training block has run past its planned length, progressions pause and a deload is suggested until the block resets.
How Povver is built.
A muscle that is not getting enough work gets more sets before it gets more weight. The research supports this order for growth, and how best to balance it for other goals is still being worked out.
Weight moves up when the numbers say you have earned it, and not a week before. If you like to push harder, write your own plan.
Povver works from the sets you log. Form checks stay with a coach or a training partner who can see you lift.
Strength is read from your lifts, not from a score, and calories are not tracked. Bodyweight comes from your profile once a week: if it is dropping, the coach is told that a dip of up to about 3% on a lift is the diet, not a stall, before it suggests a deload.
Tell Povver and it backs your training off around it. A diagnosis is a physio's job.
Strength training is the whole job. Timed and distance work can be logged and prescribed in a template.
If you turn one down, Povver remembers. Turn down a swap and the lift stays where it is.
