Your plan updates itself after every workout.
Kaizer recalculates the 1RM and adjusts weights and reps after every session your client logs — with real sets, RIR and NSCA tables. You always have the final say.
An adaptive workout app where each session updates the next routine.
The complete auto-progression loop — from the client closing a set to seeing the new weight in their next session.
The client trains and logs.
Everything is recorded from the client app — no spreadsheets, no WhatsApp screenshots.
- Sets, reps, weight and RIR per set
- Logged from the client app
- Data associated with the routine
Kaizer recalculates the 1RM.
As soon as the client closes the session, the engine crosses real performance with reference tables.
- Completed sets × reps × reported RIR
- NSCA-derived tables
- Estimate updated after the logged session
The next session adjusts itself.
The new weight and reps are already in the routine when the client opens the app again.
- Respects minimum increment and rep range
- Automatic or suggestion — you decide
- Every adjustment shows its reasoning
As a progressive overload app, the algorithm respects the minimum increment, rep range and progression mode (weight-driven, reps-driven or RIR-driven) you configured per exercise. Initial routine generation runs through an LLM that takes goals, preferences, limitations, equipment and experience as inputs. The coach retains full editorial control.
Monday's perfect program dies by Wednesday.
Performance changes between sessions, and re-planning every program by hand takes attention. Kaizer adjusts loads after each logged session, inside the limits you set, and you keep the final decision.
The next session adjusts itself, inside your guardrails.
You decide the control level.
The AI proposes or applies, depending on how you configure it per client. Every change carries visible reasoning: why the weight went up or down.
- Automatic or suggestionToggle on: it applies itself. Off: it queues as an editable proposal.
- Visible reasoningEach adjustment explains the data behind it. Nothing is a black box.
- Your rules, alwaysRespects rep range, minimum increment and progression mode per exercise.
What the AI does not do today.
We prefer to do one thing well. This is explicitly out of scope — and it's written here so there are no surprises.
Kaizer focuses on training and programming. The AI does not offer nutrition, macros, meal plans or medical diagnosis.
FAQ about Kaizer's AI.
On the adaptive AI, the coach's control and what happens with your data.
No. And that's not the idea. Progression applies specific adjustments based on client data within the limits you set. You can edit any week or switch it off globally or for one client. The coach-client relationship drives retention; AI helps the coach maintain quality at scale rather than removing them from the equation.
After each logged session, Kaizer uses sets, reps and RIR to update the estimated 1RM and adjust loads for upcoming sessions.
You can use adjustments as suggestions or allow them to apply automatically. In both cases, you keep the final decision and can edit the routine.
Kaizer uses the data available from each logged session to estimate the next adjustment. The trainer reviews whether the proposal fits the client's context.
Initial generation considers the limitations entered for the client. Kaizer does not provide medical diagnosis; the trainer reviews the routine and decides any exercise change.
No. AI automates part of programming, but results depend on the client's context, the program and the coach's follow-up.
Check the pricing page for current availability by plan.
Start by confirming they are actually stuck rather than having a bad week. In our own data, across 19,536 client-exercise pairs, 68% have their record in the most recent logged session and only 5.5% have gone more than 90 days without beating it, so a genuine plateau is rarer than it feels from the inside. When it is real, the current load usually sits almost 18% below the record. What works is to stop pushing load and move a different variable: drop intensity for a week, add volume at a higher RIR, or change the angle with an incline or dumbbell press and come back to the flat bar in three weeks. Kaizer flags when a lift's load has stopped moving, which is the part that normally gets noticed late.
There are two possibilities and it is worth separating them before changing anything. One is that the load really is light, and the fix is direct: 4 RIR on a set of 5 works out to about 77% of 1RM, when most strength blocks live between 80 and 87%. The other, more common in newer clients, is that they are underestimating effort — RIR estimation improves with practice, and beginners often say 4 when they had 1 or 2 left. The way to tell is to ask for one genuine set to failure on something safe, like a machine, and compare. Kaizer uses the logged RIR to set the next load, so if the reporting runs high, the suggestions will run high too.
In Kaizer it does not need recalculating: it updates after every session the client logs, from the sets, reps and RIR, using NSCA-derived tables. That is the difference from working off a 1RM test — a number measured in January governs March's loads even though the client has moved on. If you want to test anyway, a real test every 8 to 12 weeks is typical, and it is mainly useful for calibrating the estimate on the main lifts.
Explore other features.
Kaizer in your pocket.
Build routines, answer your clients and see how they are doing, from your phone. iOS and Android.
MetricsBusiness insights.
Retention, adherence, sessions and PRs — trended, with deltas vs the previous period.
ClientsClient management.
Every client in one panel: profile, notes, injuries, files and attention filters.
AssistantAI assistant.
Run Kaizer with words: the assistant searches, builds and edits for you.







