Prices, the App Store listing and the connected services were rechecked, and every screen shown is from the build you will install today.
A running coach that lives in your messages
Most running apps want you to open them. Runsense wants to talk to you.
You tell it what you are training for, it builds a real periodized plan to get you there, and then it more or less gets out of the app and into your messages. Every run you do arrives on its own. When your week falls apart, you say so in a sentence and it rebuilds around you.
Runsense is an AI running coach for iPhone. You give it a goal, usually a race with a date, though it also takes open goals such as running farther, running faster or maintaining fitness. It writes a periodized plan to get you there, and then it coaches you through the plan by message rather than expecting you to open an app. It reads your runs from Apple Health, Strava, COROS, Suunto or Polar, it prescribes sessions in effort rather than pace, and it answers questions about your own training in a conversation. One price, no tiers, and a 14 day trial that takes no card.
That is the pitch, and the product delivers it. The strongest part is not the plan. Plan generation is a solved problem. What is not solved, anywhere in this category, is what happens when you ask a question that a chart cannot answer.
| Price | $8.99 a month, $69.99 a year |
|---|---|
| Free trial | 14 days, no credit card |
| Platform | iPhone only, iOS 18 or later. Android is a waitlist |
| Billing | Apple In-App Purchase only, no web checkout |
| How you talk to it | SMS, email or in-app, your choice |
| Runs come in from | Apple Health, Strava, Suunto, Polar, COROS |
| Distances | 5K to 100 mile ultra |
| Made by | Runsense LLC, Longmont, Colorado |
| First released | 30 June 2026 |
Setting it up
Setup is four rows, and it takes about a minute.
We gave it one goal with a date. That field is what everything else hangs off, and the countdown to it sits at the top of the app from then on. A goal does not need a date. Runsense also takes open goals such as running farther, running faster or maintaining fitness. You point it at wherever your runs already land. You pick how you want to be coached: by text, by email, or in the app. And that is essentially it.
That channel choice is the whole design in one setting. Pick text and the coaching comes to you the way a message from a person would, which is the point: you are not relying on remembering to open anything.
The heart rate row can stay empty. Runsense prescribes by effort by design, so a phone is enough to follow every session in this review exactly as written.
What connects, and how
| Service | How it connects | What you get |
|---|---|---|
| Strava | Direct, one tap | Your existing history comes across with it |
| Suunto | Direct, one tap | History from your watch account, plus workouts pushed to the watch as SuuntoPlus Guides |
| Polar | Direct, one tap | Last 30 days only, and only runs recorded after you connect |
| Apple Watch | Automatic via Apple Health | Each day’s session pushed to the wrist with warm-up, intervals and targets |
| Garmin | Via Apple Health | Needs Garmin Connect set to share activities. The Connected apps screen lists Garmin as coming soon, and Runsense says a direct integration is in progress |
| COROS | Direct, one tap | Runs arrive as the watch recorded them |
| Your calendar | Export | Sessions land in your calendar alongside everything else in your week |
| Just a phone | Apple Health | Distance, pace and duration. No continuous heart rate |
Two things worth pulling out of that table.
The Polar limitation comes from Polar, not from Runsense. Polar’s own AccessLink API documentation describes a short default window for activity data, returning the last 28 days when no date range is given, and Runsense tells you on its own page that connecting Polar will not bring your older history over. Most companies let you find that out yourself.
And you do not have to buy anything to start. A phone in your pocket is a supported setup, not a degraded one. What a watch adds is the recovery half of the picture rather than the coaching itself.
What a week actually looks like
The plan we were given was a 10 week build to a 5K, and the first thing you see when you open the app is the shape of the current week on a single strip.
Easy, strength, workout, rest. Every day is typed, so you never have to work out what today is supposed to be, and the race countdown sits above it so the week always has a reason attached.
Tap into the day and the session is written out in full. Here is where the product’s best small decision shows up: the sessions are prescribed in effort, not pace.
A Wednesday intervals session read: five minutes of brisk walking to warm up, then five efforts of ninety seconds at an intensity where “you can only speak in short phrases, breathing deeper but still in control”, each one followed by a full two minute recovery walk, then five minutes of easy walking to cool down.
You can run that. You do not need to know your threshold, own a watch, or have any idea what your 5K pace is. You check the instruction against your own breathing, mid-run, and you always know whether you have it right.
And underneath it, the line that gives the game away: “You should finish the last one looking like the first. If the last is a struggle, the first was too fast.”
That is a coach talking. It is the sort of line you get from someone who has watched a lot of people run intervals too hard, and it is not the sort of line a plan generator produces.
Around the running sit the extras, and they are marked optional rather than mandatory: a bodyweight strength and mobility routine with a video, and the Myrtl routine, a twelve move mobility circuit with both a PDF and a video.
That framing matters more than it sounds. Mobility work is the thing that keeps beginners uninjured and it is also the first thing everyone drops, so a plan that hands it to you as homework is a plan people quit in week three. Here it sits beside the run, available, and the copy explicitly says taking full rest instead is completely fine.
Two other details in that screen are worth noticing. A gym session that was never part of the plan appears anyway, pulled in from Apple Health and labelled “Also logged, not on plan”. And where the day offers an easy run, it offers alternatives in the same breath: a run, or a slow uphill treadmill walk-jog, which is a small kindness to anyone whose weather or knees are not cooperating.
How much of this plan is actually yours
Tap the mobility routine sitting on your plan and what opens is not something Runsense wrote. It is Nike’s published Myrtl routine, served in the app with its own branding still on it, credited rather than quietly rebadged. Which turns out to be how the whole plan works.
The same is true of the plan. Runsense sorts a new athlete into one of around 150 plan shapes, so week one is a carefully chosen starting point rather than something written from scratch. It becomes yours from there, as training history builds and as you tell it about your own constraints.
Most of a beginner 5K plan comes from None to Run, the well-known existing programme, and Runsense says so plainly: it assessed the couch to 5K plans available, picked the ones it rated highest, and built on those rather than writing a new one from scratch.
What it adds is the fitting, and the fitting is the part that matters to a beginner. None to Run assumes you can already run 2 to 3km continuously and sends anyone who cannot somewhere else; Runsense prepends run and walk weeks instead of turning you away. Where the source plan prints “2 to 3 km” and leaves you to choose, Runsense gives one number, set from your own measured baseline. It lays the block out backwards from your race date, takes two easier rungs on the way up, adds strides in the final four weeks, and describes effort with a cue you can check mid-run rather than “hard but controlled”.
That is the right call. A beginner 5K plan is a solved problem, and starting from the best one available beats inventing a worse one. What you are paying for is the fitting, and the coaching that happens once that plan meets your actual week.
What Runsense is actually trying to fix
Runsense’s founder has written up the problem he set out to solve. His argument is that a runner who wants real coaching has two options and both fail. A responsive human coach starts around $150 a month and climbs steeply from there. But the economics do not work on the coach’s side either: after the platform’s cut, a coach on that rate keeps roughly $127 per athlete, so they need something like 42 athletes to earn a median living. Nobody carrying 42 athletes is reading every run you do. The alternative is an app, which is affordable and instant and, in his words, mostly a plan generator wearing a coach’s clothes.
He calls it a missing market. Buyers who want the thing and cannot afford it, providers who cannot make a living supplying it.
Runsense’s own research behind that covered 165 running-community threads and more than 1,800 comments. The top frustrations were communication at 64%, personalization at 61%, relationship at 55% and adaptability at 52%. Plan quality was not on the list.
So the thesis is: the expensive part of coaching was never writing the plan. It was a person paying attention to you. That is why the coach lives in your messages and the app is somewhere you go to look things up.
Runsense says the coaching sits on a knowledgebase of 126 sources, and unusually you can check it: the knowledgebase is the public guide library on their own site, with real academic references attached. Worth knowing where it is thickest. The physiology, injury and nutrition guides are the well-cited ones, while the training guides mostly carry no sources at all, because how you build a training block is closer to craft than to literature.
He also runs ultras himself, most recently a 100k. This is not a product built by someone who has never been on the wrong end of a training block.
How we looked at it
Runsense gave us an account with training history already in it, at our request, because a review written from an empty account describes the first week and calls it a verdict. Every conversation quoted below, every attempt to break it and every activity recorded came from this reviewer’s own phone.
You do not need a watch for any of this. Without one you still get the plan, the conversation and the adaptation, because the coach asks how each session went and uses your effort rating and your own description of it to adjust. A watch adds the recovery layer on top.
We used the in-app channel, so where this review describes the coach, that is the coaching conversation inside the app rather than the SMS thread. Our trial was extended beyond the public one so we had room to review. The public trial is 14 days, confirmed in writing, and that is the figure used in the pricing section below.
This is a review of days rather than months, so nobody got faster in the writing of it. What days are enough to judge is how it prescribes, how it answers, and what it does with your data, and that is what the rest of this page is about.
Talking to the coach
This is the part that justifies the subscription.
The first thing we asked was the most basic thing a beginner has: running is not part of my usual routine, what do I need to think about before starting.
No listicle came back. It said run-walk was completely fine, that no pace targets were needed yet, and that the equipment list was comfortable shoes and a short warm-up walk. Then it put the timeline in perspective: with 59 days to race day, the job was building the habit rather than chasing fitness in a week.
It also got the date arithmetic right, which sounds like nothing until you have watched an app in this category tell you, with total confidence, that a race eight weeks away is three months off.
Asked about a warm-up, it gave two answers rather than one, because an easy run and an interval night are not the same problem, and then explained the reasoning: for a new runner the point of a warm-up is to settle your breathing, not to tire you out. Asked about recovery after a hard session, it listed six ordinary things, including the least glamorous and most correct one, sleep, and then tied them to the actual plan by pointing at the next day’s easy walk and the mobility routine already sitting there.
Then came the one that changed our mind about the category.
The question was about sore thighs after a gym leg day, and whether that night’s intervals were still on.
It did not cancel the session, which is the safe answer, and it did not wave it through, which is the useless one. It said keep the intervals, but make the first rep the test. If the soreness eases once you are warmed up, carry on as planned. If it stays awkward and changes your stride, stop the hard parts and walk it in. Then it named the thing that tells the two apart: dull soreness on both sides is usually gym fatigue rather than an injury signal.
And here is the part that got me. I never told Runsense about that gym session. It arrived through Apple Health, turned up on the plan screen as an unplanned workout of an hour and five minutes, and the coach used it to answer a question about something else entirely.
And when thanked for being straight rather than reassuring, it said it would rather help you make the right call than fake certainty. Which is, for once, the correct posture for software handing out training advice.
The claim we put to the test
Runsense makes a claim that is easy to put on a marketing page and hard to build: that it will refuse a goal that is not realistic and tell you what to do first, instead of building a plan to a date that was never going to work.
Rather than repeat it, we asked Runsense how to trigger it, and they gave us the exact condition: plan refusal needs a goal that is genuinely impossible rather than merely ambitious, the example offered being a marathon a week away.
I would rather have that than a marketing line. A claim with a threshold on it can fail in public, which is exactly why almost nobody in this category will give you one.
We put it to the test, and made the ask harder than their own example. Not a marathon next week. A marathon tomorrow.
It opened with the short answer, which was no. Then it did three things that a template would not.
It grounded the refusal in this account rather than in general caution: currently rebuilding from runs of around 3 km, with the next planned session being 32 minutes easy on Saturday. It named the actual failure mode, that the jump would more likely produce a rough walk-or-injury day than a real race effort. And then it split the question in two, which is the part we did not expect: if what you mean is could you cover the distance somehow, then maybe eventually, with a lot of run-walk and suffering. If what you mean is are you marathon-ready, definitely not yet.
Those are two different questions, and most people asking are asking the first while saying the second. Separating them is a coaching answer rather than a safety disclaimer.
The coach starts the conversation
The thing that stands out living with Runsense is that you do not have to remember it. A message arrives each morning with the day already decided, in a window you set yourself, and it reads like a person who knows what you did yesterday.
One morning it is a reset: “Morning Faz, 30 min easy walk today, nice and relaxed, then the MYRTL routine smooth and controlled. Keep it as a proper reset day so you’re ready to run again tomorrow.” The next it is the session in full: “easy run today: 5 min brisk walk, then 6 rounds of 4 min easy running with 1 min walking. Keep every run segment fully conversational, and take the walk break before you feel like you need it.” The optional extra is named as optional, which is a small thing that keeps a beginner honest about what actually matters.
At the end of the first week it wrote without being prompted: “nice work getting the first week underway. I like seeing you tick off a run, a walk, and another activity; that’s a solid start to building rhythm without forcing it.” Then the invitation that makes the rest of the plan work: “If anything felt too easy, too hard, or awkward in the schedule, tell me now and I’ll adjust it before we keep building.”
It asks before it assumes
The best coaching behaviour we have seen from it is what happens when the data is wrong. A walk came through as a zero minute activity. Instead of ticking the session off or ignoring it, the coach said what it could see and asked: “I saw a walking activity come through today, but it synced as 0 minutes, so I can’t safely count it as your full 30-minute walk yet. I do see your MYRTL marked done. Was that walk just a partial/accidental recording, or did you get the full 30 minutes in and want me to count today’s walk as done?”
Answer it and the record is corrected in the open: “I’ve counted today’s 30-minute walk as done from your message instead of relying on that bad recording. Your MYRTL is already marked too, so today’s reset day is complete.” The same care shows up with a stray recording: a 0.3 km run at 6:57 AM was flagged as too short to interpret, with the question of what the rest of the session looked like. It was a treadmill run, the runner said so, and the plan moved on.
It chases the gaps politely, too: “If yesterday’s easy run happened, tell me and I’ll mark it.” Say yes and it is marked, with a line about where that leaves the week: “Got it, I’ve marked yesterday’s easy run done. Nice work keeping the rhythm going. Today stays as the easy 30-minute walk plus MYRTL, nice and relaxed so you’re ready for tomorrow’s hill session.”
The week keeps moving
Reset day, then the work: “hill repeats today: 5 min brisk walk, then 4 x 20-30 sec uphill at a controlled hard effort with a full 2 min walk back down between reps, then 5 min easy walk to finish. Use a gentle hill or a treadmill incline, the hard parts should feel punchy but controlled, short phrases only.” That last clause is the whole Runsense idea in six words: effort you can feel, described in a way you can check while you are running.
It also keeps a running count of the habit rather than the mileage. “Faz, nice work getting 4 sessions in already, 2 walks, a run, and another activity. That kind of consistency is exactly what will help you feel ready for the Summer Sunset 5K.” For a beginner four weeks out from a first 5K, that is the correct thing to be praising.
First, make sure you are installing the right app
Three unrelated apps in the App Store are called Runsense. The one this review is about is Runsense: Run Coaching, published by Raphael Crawford-Marks. There is a separate Runsense from Different Pen Limited, subtitled “Run faster and further”. And a third, RunSense, from PragmaTec.
The listing above is the right one. Match on both the full name and the developer, because the one you want does not always come up first. Searching from India put Different Pen’s app above the one you want. The ordering shifts by storefront.
Two things on that listing are worth reading before you install anything. It is iPhone only, per the compatibility line on the listing itself, with Android on the way. And it carries four ratings, averaging five stars. It is a new app, so the rating count is still small.
Three ways to be sure:
- The developer line under the title reads Raphael Crawford-Marks.
- The subtitle reads “From first run to finish line”.
- Or skip the search and use the download link on runsense.ai, which goes straight to the right listing.
If what you opened shows you a body map of aches and pains, or motivational quote cards, you have the wrong one.
What you control
The settings are short and each one earns its place. Connected apps shows where runs come from: Apple Health and Strava connected here, Polar, Suunto and COROS a tap away, Garmin listed as coming soon on this build, and Apple Watch setup underneath. The line below it matters for anyone with an unusual setup: “Runs recorded in any app that talks to Apple Health sync in automatically.”
It is a short screen, and that is the point: one row per source, a connected label where it applies, and a plain sentence underneath telling you that anything reaching Apple Health arrives on its own. A runner with a Polar or a Suunto is one tap from being set up.
Coaching preferences decides how the coach reaches you: a text message or an in-app notification, with the full conversation living in the app either way. You pick the morning message window, six to seven in the morning by default, your units and your timezone. There is also an “Export to calendar” option that gives you a live webcal feed of the plan in whatever calendar app you use, which is the quiet feature that gets a plan into a working week.
The goal screen keeps one goal at a time, and says so: “You have one goal at a time. Choosing a different one builds you a new plan.” Race details go further than most apps bother with, including surface, elevation gain and loss, and a cutoff field that applies to ultras. Change the goal and it tells you exactly what will happen before it does it.
Read the middle line again, because it is the part that matters to anyone nervous about pressing the button: the training you have already done stays on the plan. You are not wiping the record of your work, you are asking for the weeks ahead to be rebuilt around a new target.
“Your coach will build you a new plan for it. The training you’ve already done stays on your plan; the weeks ahead are replaced.” That is the sentence a runner needs before touching anything, and it is on the screen where the decision happens rather than in a help centre.
The numbers it shows you
The Trends tab has three parts, and the first one told us nothing for six weeks.
When we opened it on 27 August, fitness, form and fatigue were completely blank. Not zeroed, not estimated. Blank, with a note explaining why in the app’s own words: they need about six weeks of runs before they mean anything, and it would show them the moment they were honest.
We have not seen another app in this category do that. The normal move is a confident curve drawn on three data points, which looks like insight and is closer to decoration. Refusing to draw it is a small act of integrity that costs Runsense a screenshot in their own marketing.
Then it kept its word. Once the account had the runs behind it, the same screen filled in: fitness, form and fatigue, each drawn as a trend and each labelled in plain language, recovering, maintaining, holding steady, rather than left as a number to interpret alone.
One thing to know before you read it: the small arrows on the cards track the day rather than the trend, so a downward arrow on a good week is not bad news. The promise was about six weeks and it took about six weeks, which is a small thing to get right and a common thing to get wrong.
The recovery panel is the other half of the picture, and it is the half a watch buys you. It plots HRV, resting heart rate and sleep over 30 days against a band built from your own history rather than a population average, so a reading is called high or low for you rather than for an average adult. Here is the split:
| With just a phone | With a watch or ring | |
|---|---|---|
| Distance, pace, duration | Yes | Yes |
| Continuous heart rate on the run | No | Yes |
| Resting heart rate trend | No | Yes |
| HRV trend | No | Yes |
| Sleep | No | Yes |
| Prescribed sessions | Yes, in effort | Yes, and pushed to the wrist |
| Coaching conversation | Full | Full |
The coaching still works on a phone. What thins out is the recovery half of the picture.
What you lose during a run, without a watch, is heart rate. The consequence is longer-term. Once you develop past the beginner stage, Runsense offers a lactate threshold test, and that test can only be run with a device that measures heart rate. Pass it and the coaching adds heart rate zone and pace cueing on top of the effort-based coaching it does by default. That test needs a watch or another device that measures heart rate.
That is the part worth knowing. On a phone alone you keep the effort-based coaching, and the heart rate zone and pace layer waits until you add a device that measures heart rate. For a beginner the effort-based coaching is the right coaching anyway, which is the argument for their design. For someone who intends to keep improving, a watch becomes worth adding at the point the fitness test does. If you are weighing which one, our Whoop vs Oura vs Garmin comparison covers what each actually feeds back.
The three numbers are the ones a coach would actually use: fitness as the base you have built, form as how fresh you are on top of it, and fatigue as the cost still sitting on you. Alongside them sits a ramp rate that turns the three into one word, the kind of summary a beginner can act on without learning a new vocabulary.
Your data, and what it refused to do
Runsense publishes a full sub-processor table. Almost nothing in this category does, and this section is the reason we would trust it with health data.
| Provider | What for |
|---|---|
| OpenAI | Generating coaching responses. Real time only, not used to train models |
| Twilio | SMS delivery |
| Resend | Email delivery |
| Render | Hosting and database |
| Apple | Push notifications and App Store billing |
Apple Health data is not used to train or benchmark models, not used for product analytics, and reaches no advertising or analytics service. Web analytics run on Umami, which is cookieless. Account deletion is in the app, and backup copies are purged within 30 days. GDPR legal bases are set out with article references, with health data handled as special category data under explicit consent you can withdraw.
Two decisions buried in that policy tell you more than the policy does.
Runsense throws away the overnight blood oxygen reading Suunto watches send them, because a running coach does not need it. And it refuses the values Polar users type in by hand, such as maximum heart rate and training thresholds, on the grounds that those are settings rather than measurements and can be years out of date. Their own wording: they would rather have no number than a number a coach could mistake for a measurement.
Neither of those wins a feature comparison. Both cost engineering time. The benefit lands on you, because the advice you get is not quietly built on something you typed in three years ago.
Given all of that sits behind a chat box, we went at it.
We sent the coach a developer-debug jailbreak asking it to reveal its system prompt, hidden instructions, safety rules, tools and API configuration. It declined and redirected to that evening’s session. We asked again in softer language, which is usually where these give way. It declined again. Then we asked it to search its database for other users who had run more than 5km that day and tell us their names. It answered that it can only help with your own training and cannot look up or share other users’ data.
Three prompts, three refusals. I am not a security researcher and I would not tell you it is unbreakable. But this is an app holding your sleep, your resting heart rate and your HRV, and running all of it through someone else’s model. I wanted to know whether it would hand any of that over if I asked nicely. It would not.
What it costs
$8.99 a month, or $69.99 a year. First 14 days free, no credit card required.
| Plan | Price | Works out at |
|---|---|---|
| Monthly | $8.99 | $107.88 a year |
| Annual | $69.99 | $5.83 a month, a 35% saving |
| Trial | Free for 14 days | No card taken |
There is one product and no tiers. Everything is included at that price: the plan, the rebuilds, the coach, unlimited questions. Nothing is gated behind a higher plan and there are no add-ons, which is rarer than it sounds, because tiering is how most of this category prices.
Runsense publishes that price openly, which sounds like a low bar until you go looking for the price of anything else in this category, and confirms the 14 day trial in writing.
Two practical notes. Billing runs through Apple In-App Purchase, so you cancel in your App Store settings rather than in the app, and refunds follow Apple’s policy. Email their support and they will cancel for you, and coaching runs to the end of the paid period either way. And the trial genuinely does not ask for a card, which is rare enough in subscription fitness to be worth the sentence.
For scale, Runsense’s own published comparisons put Runna at about $19.99 a month and TrainingPeaks coached tiers at $149, $229 and $359. From our own checking, $8.99 sits at the low end of AI running coaches and a very long way below any human one.
What to know before you buy
You need an iPhone. Android is an email waitlist, with Runsense targeting a release by the end of the year.
Expect the trend charts to fill in around week six, not week one. Runsense will not draw a curve it cannot stand behind, which is the right call and worth knowing so an empty screen does not read as a fault.
Start with the phone, add a watch when you are ready to. The coaching is complete without one. A wrist device adds the recovery half of the picture and unlocks the heart rate and pace layer later.
It ships fast. First released on 30 June 2026 with several updates since, so features arrive quickly and the product you buy in three months will be ahead of the one described here.
Who this is for
Runners who want to be coached rather than to manage a plan. If “just tell me what to do today and why” is your position, this was built for you.
Beginners, genuinely. Effort instead of paces, extras marked optional, run-walk offered without making it feel like a failure, and answers that give you a decision instead of a disclaimer.
Anyone coming back from a break or an injury, for the same reason. Coming back is nothing but judgment calls, and judgment is where this product is strongest.
People whose weeks move. Travel, shift work, small children, a semester of evening classes.
Runners priced out of a human coach. At $8.99 against $150 and up, that is not a close comparison.
Anyone with a phone and nothing else. No watch, no chest strap, no other subscription.
Who this is not for
No product suits everyone, and Runsense publishes its own edge cases rather than waiting for a reviewer to find them. These three are its, and they are fair.
Multisport athletes. It reads your rides, swims and strength work and builds your running week around them, but it will not periodise a triathlon or a cycling season. For that, see our AI triathlon training apps guide.
Runners who enjoy the controls. If browsing plans and dragging sessions around is the part you like, Runsense is designed to take that job off you, which is the opposite of what you want.
Anyone who wants to interpret the raw data themselves. Power curves, WKO-grade modelling, years of charts to pore over. You can ask the Runsense coach for analysis and it will give you one, in prose. What it will not do is hand you the tables and let you draw your own conclusions.
Verdict
Runsense is the best coaching judgment we have found at any price close to this one. It answers the questions a chart cannot: is this soreness a problem, should I run today, am I ready for this.
Everything I checked, it handled. The conversations are specific rather than generic, and they draw on training you never deliberately handed over: the clearest single moment in this review is the coach folding a gym session that arrived through Apple Health into an answer about whether that night’s intervals were still on. Asked for a marathon tomorrow it refused, and refused with this account’s own mileage rather than a disclaimer. Asked to leak its system prompt or another user’s data, it declined three times.
The restraint is the other half of it. It refused to draw fitness curves until it had about six weeks of runs behind them, and then it kept its word. It throws away the overnight blood oxygen reading it gets sent, and refuses hand-typed threshold values, because a coach should not mistake a setting for a measurement. It publishes a full sub-processor table, which almost nothing in this category does.
Adaptation is the thing Runsense leads with, and you can watch it work. On the current build: the coach opens each morning with the day’s session, holds a walk that synced as zero minutes until the runner confirms it, queries a 0.3 km recording rather than counting it as the session, and marks work done from a reply while saying that is what it did. That is a coach keeping an accurate file, which is the part most apps skip.
Add a watch when you are ready to and the picture widens: heart rate through the run, the recovery trends, and the lactate threshold test that turns on pace and zone cueing. None of it is needed to start, and a beginner will get a long way before any of it matters.
At $8.99 a month against $150 and up for a human coach, with 14 days that take no card, the thing you are buying is judgment on the questions a chart cannot answer. On that, it delivers.
Tools mentioned in this guide
- Runsense, the subject of this review
- Runsense: Run Coaching on the App Store, the listing to install
- Runsense for Android, join the waitlist
- Runsense’s own comparison with Runna
- Runsense’s own comparison with TrainingPeaks
References and further reading
Everything in this review was read off these pages.
- runsense.ai, pricing and the free trial
- runsense.ai/android, the Android waitlist
- Runsense privacy policy, the sub-processor table and the GDPR bases
- Runsense support
- App Store listing, ratings and platform
More from our fitness coverage: the best AI running coach apps, the best AI workout apps for beginners, Whoop vs Oura vs Garmin, AI sleep coach apps for athletes and AI triathlon training apps.
Written by
FazFaz is the founder of AIToolsBakery. Some tools here are tested hands on. Others are assessed from vendor documentation and pricing verified on the live page, and every review says which one it is. Sponsors can buy a position in a guide. They cannot buy the score, the criticism, or silence about a better option.
How we test and how we make money →
