Hacker News new | past | comments | ask | show | jobs | submit login
Launch HN: Senpai.gg (YC S21) – Personal gaming coach for PC gamers
182 points by berkozer on Aug 11, 2021 | hide | past | favorite | 207 comments
Hi HN, we’re SenpAI.GG (https://senpai.gg/). We help gamers get better by providing real-time, personalized suggestions and feedback before, during, and after games.

It takes a lot of time and effort to become good at popular games. Even after learning a game, you need to adapt your gameplay to meta changes (game updates). We’ve developed a desktop application to accelerate your learning curve, as well as easily adjusting your gameplay as games get updated. We provide personalized recommendations before the game to set up strategies, give instant notifications and feedback while playing the game, and detailed post-game analysis to improve your gameplay.

We're friends from college and played many games together during our dorm life in the early 2010s, especially Age of Empires II (we're old-fashioned). We were very good at 2 vs 2 matches and were considered the best in our dorm. A few years later, we decided to play AoE II again and got destroyed in the first 3 matches. We googled the ways to improve our gameplay and found two ways in addition to orthodox methods such as reading guides. The first was to watch hours of streams on YouTube or Twitch. Considering we had demanding jobs by then, it was impossible to watch long videos. The second was to pay for professional feedback from “human” gaming consultants.

Then, we came up with the idea that we can mimic human gaming consultants and create a scalable system. We could use statistics to provide fundamental level suggestions to improve the gameplay. This is how we formed the basic idea behind SenpAI.GG. Since we know AoE II has a limited number of players, we decided to start with League of Legends and developed a prototype in 2018.

Our Desktop application is now available (beta) for League of Legends, VALORANT and TFT. League of Legends players need to pick the champions, runes and items just before they start a match and play. We provide champions, runes and items suggestions to improve their winning probability. Our recommendations can be imported to the game with a single click. We provide some tags pinpointing the game characteristics of opponents and teammates. For example, we have an "Early Ganker" tag for the gamers who tend to gang in the early game. After the match, gamers can take a look at their strengths and weaknesses. For instance, we provide a tag of "Early Game Gold Loss" for a gamer whose gold/minutes ratio is significantly less than the lane opponent in early game). We provide these tags based on only publicly accessible data on the official game publisher API. For example, any gamer can search for the opponents’ game data and conduct a similar analysis.

For VALORANT, we have a Voice Assistant. For example, we start a counter when a spike (Spike is a type of "bomb" with 45 second detonation time.) is planted and provide verbal notifications (10 seconds, 7 seconds, etc..). For healer agents, we notify the gamers if any of the teammate's HP is low. This information is already available on the screen (health bars) but we provide an extra verbal notification. During the match, we don’t provide any information about the opponent.

We follow the guideline of the game publishers and do not share any information or suggestion that is not available on the screen of the player. We consider SenpAI as analogous to a friend sitting next to the gamers, making recommendations based on the data they see. In the case of sports, the best analogy would be an ‘analyst’ or a ‘personal performance coach' that provides some training and insights about the opponents based on the publicly accessible data. An approximate analogy to, say, chess might be that we tell about the chess clock and provide verbal notifications about time spent while the player is thinking.

We have a Desktop application (built on Electron.js) and a web application. We have two sources of data. We have access to the official API of game developers (specifically Riot Games) and we utilize computer vision to extract information (e.g., health bar) from the game in real-time. For League of Legends, we trained a deep learning model to predict the results of matches. We provide pre-game suggestions to maximize the winning probability of this model.

It's free to use SenpAI.GG, however we have plans to launch a freemium business model inspired by popular video games. Basically, gamers will need to subscribe to unlock certain features and remove ads.

We would love to hear what you think about our application. You can download the app from https://senpai.gg/ (currently available for Microsoft Windows) or try our web application at https://app.senpai.gg/. We will be here today to answer any questions and hear your feedback in the comments!




The current marketing pitch (a personal gaming -coach-) has nothing to do with the current functionality of e.g. voicing timers or providing notifications. That's more akin to a personal assistant.

I would also say that what it's doing with Valorant is cheating. It's providing additional cues and advantages automatically, that other players have to keep tabs on manually. The other players have to risk glancing at the timer(s) and temporarily divert attention from the other parts of the screen, while the "AI" user can rely on auditory feedback that is not present in the game for everyone (and maybe was a conscious decision from the game developers).

The whole point of competition is to evaluate player vs player performance, not player+personal assistant vs player performance. If you allow uneven things like that, then it becomes an arms race and also becomes boring from both a viewer and participant standpoint. Part of the challenge of games like Valorant, League of Legends, DotA2, etc, is to learn how to manage the sheer amount of information while also engaging in fights/gameplay.

An actual coach "AI" concept could be to provide intelligent information -inbetween rounds-, not during gameplay itself.


I agree this feels like cheating. I read the Valorant page and they've basically re-implemented information that is available to you in game generally, but takes skill/timing/awareness to track and made it more obvious and automatically tracked. How is this not just a low-grade cheating program? If the game developers wanted you to have that information in the format Senpai.gg is giving it to you in, they would provide it in that format in the first place rather than using their own audio queues, omitting specific timers, etc.


In-game coaching _is_ considered cheating in FGC tournaments


We do not target tournaments - any 3.rt part application or a human coach is also not allowed as well.


Matchmaking has anti-cheat. This is cheating in an environment that disallows cheating.


Yep, for any sort of eSport you can’t have outside help/information outside of designated times if the format allows it, but also this isn’t targeted at eSports.


Yeah but it's not allowed in esports because it provides an unfair advantage. It's still unethical and provides an unfair advantage outside of the esports community, there just isn't a judge watching all the players and enforcing it.


But cheating can happen (and be prosecuted) outside of eSports. The founders should be careful.


prosecuted, lmao



This only applies to Asia. Nobody gets sued for cheating in US/UK/Can. Cheat sellers being the exception.


This is a thread about people selling a program that might be considered cheating, so I'd say that this is the only case that is relevant.


Blizzard have sued cheat makers outside Asia before.


You could go to jail for a long time. Watch it, buddy


Thanks for sharing your feedback, I agree that it takes time to learn and implement the specific actions in the game - and that is the reason why we developed the gaming coach. Ideally, we want you to learn the game dynamics so you can play better, improve faster and enjoy the game more!


This is akin to saying "if you practice with a cheat so you can see through walls, it'll train you to know where players are likely to be standing".

No, it's cheating. It provides an unfair advantage by replacing a skill with a technology. There may be good intentions, but if so they are founded on a total misunderstanding of competition.


I don't think it's quite that cut and dry - it appears to only be using data already available to the player. If anything it seems like a training queue to notice the information that's already present instead of passing it over.


Chess engines also only use data already available to the player. That simply has no bearing on whether or not it's cheating.


That doesn't sound like how it would be used though. If I can run your app all the time, and get an edge, why wouldn't I?


Transparent, shameless attempts to deflect criticism make people like you less than if you just ignore it, phony exclamation point.


Speaking as a league player and a game developer, the audio cues are 100% cheating and also explicitly against Riot's ToS as stated here: https://support-leagueoflegends.riotgames.com/hc/en-us/artic...

The relevant excerpt: "Exposing information that’s intentionally obfuscated (cooldowns or timers)"

As for all of the other match data mining, that's par for the course in competitive games these days.


> "Exposing information that’s intentionally obfuscated (cooldowns or timers)"

Doesn't this just benefit people who are good at counting ?


Competitive games have a variety of ways for players to express their skills. I'm not going to comment on whether or not it's good design, but it is clearly the intended design and that's the important differentiating factor. Competitive games are always going to benefit some players who are good at some specific aspects of them inherently by their nature.


In Dota you have to keep track of all sorts of stuff like this.

There is a decent sized list of all the timings you should keep track of with in a game, and they change from game to game. If you don't do it you're basically lost.


That's the way games work.

Doesnt having a good memory give advantage to chess players?

Or having good reflexes benefit shooter player?


Well, at least in a casino, if someone notices that you look like you are counting cards you will promptly be escorted to the exit


Dota 2 allows for a real time coach to join your team during a match at any time, it's built into the game. They have full vision/information of what your team has.

However, "Coaching is available in private lobbies, casual matchmaking, and Co-op bot matchmaking, but not Ranked matchmaking, Team matchmaking, or Tournament lobbies."


Yes, Valve has a similar vision for CS:GO as well. We don't provide any coaching services for tournament or professional events.


Providing situational feedback during gameplay by way of an overlay or audio queues is clearly cheating.

If I were an investor in this company, I'd be asking the founders what their plan is when they get banned by the major anti-cheat engines.


listening to a song that has INJECT at the right moment put in for your perfect injects isnt cheating as long as you dont play it during tournaments, its just a metronome to practice to.

Its not a service I would ever want to use because I actually enjoy games and I find coaching it to be too much to care about, but I think "audio clues to practice" doesn't meet the bar of cheating lol.


Your description doesn't sound like it's feedback based on game-state, though.


I see your point, but to me its starting to splice hairs because at the time the meta wasn't something that changed much, there was effectively a pre-determined set of actions in the first 10 or so minutes and most matches were less than 16 minutes so perfecting your opening via almost a programmatic efficiency was pretty normal.

The proper inject time (for instance) is just X*N seconds since game start, the second best time is right after that.


Ugh. Why don't the devs randomize things a bit so the game can be more interesting and fun than memorizing digits of pi?


Randomizing doesn't always make games more interesting and fun, it often makes them less skill-rewarding and more frustrating. This especially shows if you play for hours every day.


Generally I would agree, and perfected build orders are part of the reason I stopped watching.


Is there actually a song like that?


I definitely remember "maximus black" a starcraft 2 streamer talking about a song he had that had this very same setup yeah.


Cheating in video games is a growing industry. But if they push boundaries and are a US or EU company they will be sued to splinters for it.


What tort is "helping someone cheat at a video game"?


Many large studios, I specifically think of Blizzard and Jagex, have a reputation for wielding legal successfully against third party clients, phishing, trademark/branding abuse, botting, and similar activities. Further there are severe legal consequences in China and elsewhere for cheating in video games.

Even if there isn't decisive legal consequences they can carpet ban whoever they want whenever they want. Which is likely the reputation which causes the landing page of this service to be plastered with "don't worry you won't get banned" all over the place.


Cheating in a game ruins other customers experience so does have a direct monetary impact which is why games companies care about it so much.


Thanks for sharing your feedback. We understand your concern but we are very careful to not develop any feature that would be considered as cheating for the majority of the gaming and game developer.


In my experience, may of these companies (Riot, et. al) are not particularly consistent over time or in the application of even current rules. And it's also hard to divine what "would be considered cheating" by these companies as one support person may say something is cheating, and another might consider it cheating and ban your account.

It seems very fraught and risky to use for gamers who desire that their accounts don't get banned.


That's good if it helps get cheaters banned.


The idea of:

> For example, we have an "Early Ganker" tag for the gamers who tend to gang in the early game. [...] We provide these tags based on only publicly accessible data on the official game publisher API. For example, any gamer can search for the opponents’ game data and conduct a similar analysis.

also seems questionable to me. Is it common/practical to do this kind of thing in these games? It seems to me that, while it might be technically possible to get the info, it should be impractical for a human to actually do the analysis, in the timespan allowed by a pregame lobby, right?

I guess it could also depend on how much preprocessing they do... hypothetically we could imagine a game where every match is recorded and saved to a public user account, and a "coaching" AI system that extracts users tags by watching these offline, and then just queries them at match time. This analysis would pretty clearly be information that players wouldn't normally be privy to, despite being available through legitimate means.


As a League of Legends player, it's very common. Virtually everyone that I know that plays this game has some sort of overlay(LolWiz, Porofessor, Blitz.gg, etc.) that provides unimaginable level of detail about the enemy team and my team before the game even begins. I can find out what the enemy players like to do("invade", or initiate cheese fights early), roam to other lanes in the map, and more. I know what their winrate on their champion is, how many kills on average they get before 10 minutes, whether they don't ward(a crucial component of the game that opens them up to ganks if not done correctly), and who they may be connected to voice call with. If anything, it seems like Senpai.gg's tool isn't doing enough.


Well, this is what I was referring to by an arms race if these kinds of tools are allowed. It’s a considerable disadvantage to not use them, so everyone is basically forced into using them.

In my opinion for non-professional play (casual and ranked), these kinds of tools should be outright banned. The game goes from “how can I improve myself and play better” to “let’s expend the minimum effort possible solely to win”. You’re not playing to your strengths but just to the opponent’s weaknesses from the get-go. That’s just incredibly boring. Just because one can have a shortcut to a win doesn’t make for better or more interesting gameplay.

Regarding professional play, the teams have the resources to do this given the limited player pool and they’re also at the pro level anyways.


Huh, well this supports my decision to not get into MOBAs.


In Dota at least you can make your data private and your picks/habits cannot be tracked by third party websites or applications.

I feel like gaming stats should have way better privacy options in general.


That's certainly right. We don't provide any suggestion based on private data. For example, gamers cannot see the tags of an opponent if the opponent opted out to be private.


I think if people care about their data it should just be anonymized instead of hidden.

Data from games is such a good way for people to get into programming and data analysis (Speaking from personal experience).

It's easily accessible, real and has a decent level of complexity. Would be a shame for it to go away because people want to hide their data.


At least when I played, dota2 wasn’t like this (and it’s a better game, anyways ;-))

Realistically speaking this kind of stuff doesn’t really matter at a lower level anyways- everyone’s bad and makes dumb mistakes. And it doesn’t help to know about data if you don’t know how to capitalize on it.

I can’t recommend getting into MOBAs/ARTSs solo, but if you have 2-3 friends they’re quite a blast.


To be fair giving this info is not helpful if you're bad at the game itself. I've tried using it but I'm still only top 65%. Once you get to the level below pro players, there's so few people that you remember everybody's usernames or remember who plays on tuesday nights and will remember their playstyle / champions to ban.


Couldn't you look yourself up and adjust your playstyle accordingly? Like "oh, these guys will be expecting me to do X, but now I'm going to do Y instead to throw them off".


From my experience it's most useful for getting information on clear outliers. The ranking system might rank a very good player with terrible players until the ranking settles in. A few players are "boosted" by other players to reach higher ranks. In such situations it might be useful as you know that specific opponent on the other team is the one to watch out for or who to focus.

There is a lot of summary stats available, but the most useful one from personal experience is the win ratio. If the data tells you that one player on the other team wins 70 % of the games, then that's usually a clear indicator that the ranking of that player is most likely lower than it should be.

It might just be a better or worse player overall, so adapting to it might not be possible, except for knowing who to put pressure on.


Thanks for the explanation. Senpai.gg is still in Beta and we're continuously improving our features.


Is an AI that aimbots by predicting player moves with uncanny accuracy really that different from a regular old aimbot?


Another interesting point in the spectrum could be, what about a program that marks up the screen or minimap with detailed heatmaps of likely player positions based on historical data?

If that's not obviously cheating, make it time dependent, make it player dependent, etc.

If that is obviously cheating, what about producing those maps and not providing an in-game overlay?


I think it's very simple: if you'd describe its usage as a "skill", it's probably fine. Obvious "navigating this cheat menu UI takes some practice" cases aside.

If a professional team uses data analysis and then teaches their players something like "at 30s, on this map, this player rotates from here to here in 70% of games", that's just good training. If they have this data being live-streamed to their second monitor, it's cheating.


Those kinds of maps are already available for study outside of the game for DotA2, eg. here’s the analysis for a game I played. These are incredibly useful for learning and analysis after the match.

https://www.opendota.com/matches/5501229759/laning


I don't see as very different from a wallhack if it's any good if it's an in game overlay. I suppose if it's an offline thing that you can study but need to apply yourself that's no more of a cheat than any other prep.


I would say that a skilled player doesn't need to see the heat maps in real time, it would be enough to see them once or twice and they will remember because it "makes sense" to them that the heat maps are the way they are.


Nope it’s not and that’s why 100 percent if this tool is doing what it is saying, I would consider it cheating. I have tons of hours in Valorant and if this becomes common I will not play the game. I play specifically because of the learning curve and skill curve. There’s already a big enoug problem with Smurf’s and ranked boosting


big enoug problem with Smurf’s

Maybe its just because I play on Sydney servers, but I really find this a bit overblown personally -- and I've ranked up from bronze 2 to plat 1 over six months of playing. I think its honestly just that some people have "on" and "off" games, at least from the hundreds and hundreds of ranked matches I've played.


1/3 games of Mine has a smurf on my or other team that will admit it or it’s insanely obvious. I play central NA


This sounds like "Deadly Boss Mods for games other than WoW" which probably is just cheating.

I'd be really interested in a product that does more of what a human coach would do.


I was thinking the same thing. Blizzard explicitly allows this kind of thing but most games do not.

Even with DBM - there used to be an addon that told you exactly where to stand to avoid different bosses attacks. That got banned pretty quickly because it over trivialized the mechanics.


For suresies. I didn't play in Firelands but I heard some stories of the "drawing football plays on the ground" era. We used a similar addon for Sha of Fear p1 side platform but it displayed where to stand on a HUD, not on the actual floor.


I'd say DBM being PvE is a big difference. But WoW generally is a whole other beast just because of how addons are ingrained in it.


Competitive PvE exists too (speedruns, world first races, etc). In FFXIV mods are less tolerated and while some raiders use triggers (TTS voice lines triggered by enemy actions or friendly buffs to tell you what to do), many consider it borderline or actual cheating, while others are fine with it because it's similar to having a player do it (ignoring perfect accuracy and no brain capacity used). So it's a controversial area.


Thanks for your feedback. We understand your concern, but we do not share any information that is not available on your screen. In a sense, we provide an alternative interface so you can learn about the game dynamics to improve faster. All the features that we develop aims to accelerate the learning curve - so we do not share any information about your opponent, their location etc. that is not available to you while you are playing the game.


Providing an alternative interface is exactly why it sounds like cheating.


When a good significant portion of your website is dedicated to “will I get banned?” .. I don’t know, man, it’s probably not going to go over well with these game companies. Also, is AWS, NVIDIA, etc really a “partner?” Just because I use their products, or get credits, that doesn’t mean they endorse or have partnered with me?

This just feels like cheating to me in Valorant: https://vimeo.com/534438994


Getting audio queues for what is happening on the screen is cheating, pure and simple. "Game awareness" is one of the most difficult aspects to master in fps. I've been playing fps for a very long time, and I would point at the the death cues in particular as being absolutely unfair, you either have to defocus your perception to take in the kill feed(a very difficult thing to do during an intense fight), or move your eyes away from the reticle to read the feed. It would be trivial for the game devs to add this, or put a mini kill feed under the reticle(some games have this, like PUBG) but they don't, and that makes it "assistive software" aka cheating. Further, if you are working with teammates, they can't use a subtle queue like a beep, they likely have to speak, "1 down" or such, which is much more disruptive to your ability to hear footsteps. What further makes this egregious in the case of Valorant is that there isn't even hit markers, so if you are, say, shooting into smoke, this give you a significant advantage to know what's going on in a fight.

Likewise, counting bullets is a very difficult skill to master, and this, like the death notifier is a straight up replacement for that skill (with the caveat being you can't go pro gamer, lol, like it matters for the average cheater) the same way an aimbot is a replacement for the mechanical skill of mousing. Sorry, but training isn't an in-game assist.

If I saw a twitch streamer using this I'd be livid. This gross, and fuels the need for invasive 0-ring anti-cheat malware.

Not to say everything about this software is cheating, I think providing detailed character/map/mechanics analysis is fine, and a great business idea, but this real-time in-game feedback is gross, at least in the fps genre that I'm familiar with.


This is 100% cheating based on Riot's rules, only because of the Spike Timer. The rest is mostly ok. The reason for that is that there is no visual indicator in-game for the spike timer, it has to be memorized.

I'm not a LoL player but to my knowledge Riot just doesn't really enforce their own rules outside of tournaments where tools like this are not allowed. For Valorant, I have played in many tournaments, and every single one has explicitly stated that tools like this are not allowed.

There is no way this product is ethical or legal, and even if it /currently/ doesn't break any rules, Riot could just add one sentence to destroy the entire app. Seems really questionable to me.


Thanks for sharing your feedback. There is an audio guide that helps you to understand how much time left, similar to what we do.

We closely follow the guideline of the game publisher. SenpAI doesn't aim the tournament's, we would like to make coaching accessable and affordable for the all gamers who would like to improve. Similar to getting a coaching session from a good player.


Have you actually spoken to any tournament-level players about your product? Have you actually spoken to anyone at Riot about your product?

It just seems incredibly bizarre to me that you made something which so blatantly breaks both ToS and tournament rulesets. Anything that is considered "outside assistance" is not allowed during the round of gameplay. Any time coaches are allowed to talk, your app can be allowed to talk. That includes pre-game, post-game, and during tactical timeouts.

As somebody who both has played in hundreds of tournaments at various games and has run large tournaments, software like this just makes my life way harder because the TO has to require not just video recording, but also audio recording now of every person's POV just to verify that they are not cheating.

There is ABSOLUTELY a market for coaching and statistical analysis in esports, and many esports teams (at least C9, Immortals, and TSM to my knowledge) hire/contract engineers to build out data analysis systems to gain advantages. You need to focus on the outside of the game learning process - maybe even something to analyze your recordings (which already exists for CS:GO, and is way more useful than what this does).


Does the timer thing actually make the player better at estimating time remaining?

I have never played this game, but I would assume the opposite: players would get a small advantage while using it, but it would prevent their timing skills from being developed.

This is like saying "Using GPS driving directions make you a better navigator" - it's true while you're using it, but if you always use it your navigation skills will atrophy.

Do you have statistics to back up the claimed value of your program? Would be interesting to implement a 'performance evaluation' mode that would measure baseline and periodically test users without hinting so you could have stats to back up claimed benefits.


Thanks for your feedback, appreciated! We are not developing GPS in your analogy, in our opinion, the game already provides GPS via auditory information. We just help you to learn and use this information.


No. The game provides the map in that analogy and you provide the GPS.

The question was: Are you not actively preventing learning? Seems from your answers you are aware of that but pretend to not notice?


The spike timer is beyond cheating lmao. All comp rounds go down to the timer timing


It's clearly cheating. As you point out, the numerous disclaimers and reassurances should be all anyone needs to see to know that they know they're doing wrong. They're seem to think they're merely near to the edge of cheating but actually they're well over the line.

In private matches, with friends, these cheats would be acceptable. But any time unsuspecting players are on the other end, using these should be a bannable offense. A level playing field is the entire point of games like Valorant. Preventing cheating is one of the major promises of Valorant. One should not claim to love games and then work to destroy them.

Riot should absolutely ban players for using these cheats.

YC should seriously consider whether these violate the Founder Ethics rules, because they very plainly seem to. Selling game cheats should be on the list of things YC never funds. Cheats are highly toxic and bad for the world.

> Not using misleading, illegal or dishonest sales tactics.

> Generally behaving in a professional and upstanding way.

https://www.ycombinator.com/ethics/

Lots of startups make mistakes early on. Hopefully this startup will pivot away from selling cheats and into other areas quickly. I wish them sincere good luck with those endeavors.


Thanks for sharing your opinions and we truly share your concerns about ethics. In our opinion, we're providing analytical support and assistance. We don't lead unfair advantage among gamers.


If you’re providing something in game, regardless of what it is, and not all players have equal access without external software too .. it’s an unfair advantage.


Just to play devil's advocate here what about somebody who has a superior DPI laser mouse versus somebody who has a standard rollerball mouse. What about people who use monitors with higher refresh rates like 144 Hertz, what about keyboards that have no ghosting and unlimited key rollover.

Do players who can afford these premium gaming and hardware devices have an unfair advantage?

Just to be clear I don't really have any skin in the game I don't play competitive multiplayer video games at all.


Cheating can be one of those "I know it when I see it" things that can require judgement from experts in difficult cases. Competitive chess players are the best ones to judge what constitutes cheating in chess, for example.

But what this startup is doing is the Wikipedia definition of cheating, with no reasonable room for debate:

Cheating in online games is the subversion of the rules or mechanics of online video games to gain an advantage over other players, generally with the use of third-party software.

https://en.wikipedia.org/wiki/Cheating_in_online_games

And it seems pretty obvious that they know what they're doing is wrong. They just seem to be very determined to try to push forward, and seem to think they have cleverly concealed their bad behavior, hence the cover story bs about "coaching" when they clearly know what anyone would actually use their software for.

I'd guess that they also rationalize selling cheats because others do it, which is obviously no ethical defense at all.

YC probably needs to be the ones to set them straight, since they are in a position to do so, and have explicitly made it a goal to avoid funding unethical startups.


Amusingly, both those examples used to be common.

Old CRT monitors ran at up to 160-170Hz. Even at lower refresh rates motion was still clear. Key rollover really became a big issue with early USB keyboards and janky membrane setups. Many old keyboards didn't have the issue.

In my opinion, games are at least designed around the lowest common denominator. Very few twitch-shooters are popular now. Most shooters have other characters/classes that let players with disadvantageous equipment still join in on the fun. If everything is a blur playing "Scout" in TF2, you can play "Engineer" instead and let the automated turrets do the work for you.

I think there's a certain Director's Vision gaming setup. Ideally, everyone could play on a big screen, where everything is clear, not muddied by the physical realities of technology.


That comparison is like comparing someone in average tennis shoes and a cheap racket with someone using pro-level gear. It’s generally accepted that the better stuff does give you an advantage but that it is within the rules of the game to be able to use it. Particularly as the advantage is generally pretty small and mostly open to people playing at higher levels anyway. Some sports do bracket people by the equipment they use.

Whereas most software cheats like these audio cues deliberate subvert the rules to give a significant advantage even to the clueless. And aids like aimbots even more so.

But fundamentally the rules of any one game and therefore what is considered to be cheating are pretty arbitrary. However there is a strong cultural component to the rule sets that will actually be appealing for people to play.


In your opinion, what would constitute unfair advantage?


> Selling game cheats

Unless riot itself has commented on this and said that it is cheating, your moral outrage is unwarranted.

It is very much possible that riot does not consider this against the rules.


> When a good significant portion of your website is dedicated to “will I get banned?”

It means that you will, and their app will get blacklisted, and they know it. They're trying to extract cash from users before it all gets banned/closed.

These types of apps get created for every new competitive game, and after a while they get shut down and the companies usually just quietly shut down without refunding anything.


Does this provide real time "coaching"/suggestions during the game for League? I remember there used to be this application called "bwcoach" for Starcraft Broodwar, that would yell at the player if he's not building enough workers, not spending enough resources, not scouting, etc.

The capabilities of your League app seem to be easily accessible via multiple other apps (porofessor, op.gg, League client itself), and during pick/ban, suggesting champions/runes to use based purely on community stats may actually be detrimental (the player may be much worse at a suggested counterpick, than if they just played their best champion).

I think if the coach client can provide suggestions such as the following, it would provide a lot of utility for minimal effort: 1) reminder to check mini-map 2) after a kill, suggest backing vs. pushing wave to tower vs. roaming 3) itemization suggestion, which has a more objectively optimal choice based on team comp/itemization than champion selection.


As another commenter here has mentioned, in the case of LoL particularly, Riot games has banned similar apps and tools in the past. I can also see it causing "integrity of competition" issues with people, although you can certainly get live streamed coaching with professional coaching, that certainly isn't as scalable as simply running a coaching app alongside your client.


Blitz [0] gives an overlay with info like creep score in League of Legends, and character suggestions in Teamfight Tactics.

[0] https://blitz.gg/


Thanks for sharing your comments. We don't provide any tactics or actionable suggestions during the game for League.

As you mentioned, some of our features are already accessible via some other applications but we aim to provide more comprehensive suggestions.


To get to be a good player in a game, you need to master the basic skills. In LoL this would've been laning (or jungling), CSing, team fights, 1v1s, having a clue what to build, warding. If you got good at these, you could get gold or plat. Past that, it's strategy and the small things, for which an AI will never help. There's too many things to keep track of, and AIs are simply not as good as humans at context and adaptation.

So in other words, a bad player will not improve as he doesn't need to train what the AI is trying to get him to, and a better player already has a better instinctual understanding than the AI.

However, I think this idea will still succeed, even though it's basically ineffective. There's a large amount of gamers of a certain archetype, that believe they can improve by spending money on small trivial enhancements. These are the same people who gets into a hobby and buy the most expensive military grade equipment and think they're gonna become better than their peers quickly. As misguided as they are, they do exist in great numbers, and they have a hole burning in their wallet.

I think the other commenters should keep this in mind, this idea is not about actually improving people. Nor is it about cheating, if I lose to someone because they have some paltry voice timers on, that just means I suck. It's about the fact that people will pay money for the belief that they can buy skill with it. Nothing wrong with that, good luck to y'all.


> So in other words, a bad player will not improve as he doesn't need to train what the AI is trying to get him to, and a better player already has a better instinctual understanding than the AI

This is what I realized when I tried to create a similar product. In my opinion there is no real audience for casual analytics products in gaming that are focused on improvement.

If they're serious, they'll do their own analysis. If they're not serious, analytics won't help.


I think there's some value in a product that lets you make data driven insights. My own analysis usually means VOD review, which is great, but if I had useful data to explore in a more unstructured way I suspect I could derive some value for myself.

But every product I see is hyper focused on doing the actual analysis for you in a way that is always overly simplistic and virtually never useful.


What do you consider "useful data"? Most of the time raw data is easily accessible on a lot of different websites.

The problem with augmenting the raw data in some way is that you have to make opinionated assumptions which won't necessarily be relevant to everyone.


Thanks for sharing your ideas. We're targeting low-to-middle level of players and some of our features are not a huge boost for expert players, as you described.

We believe we minimize the time and effort to follow meta and help gamers to understand their weaknesses and strengths.

If we use an analogy from sports, we're more like a performance analyst but not a trainer.


The big question on my mind when reading and considering this is, who is this aimed at? Is it aimed at casual players? Is this aimed at those who want to improve or that play competitively? If it's the latter I can't imagine it being of much help in the long term. It's better to understand why things are a certain way than to have an AI tell you to just do a thing. And unless you're playing at a high enough level already, things such as synergy or composition don't matter nearly as much as comfort with a character and their abilities. And as someone who has played games competitively in the past, I never wanted something to help me with things like awareness, along the lines of what the Valorant functionality displays. Keeping one's eyes on what's generally going on in the game has become much easier over the years anyway, to be completely honest.

I think for general strategy or builds in games like League of Legends or Dota 2, written guides and/or thinking for yourself will still easily trump an AI and will further one's actual understanding of the game and it's balance a lot as well. At the last Dota 2 International tournament a team won by their player picking up a rather unusual item that surprised even the fairly knowledgeable commentators. I think these sorts of AI or data based things just end up being a crutch for the players in the middle of the skill bracket but will fall off in effectiveness once they reach the higher levels where enemies will actually think for themselves and come up with counter strategies along the way.

Also has support for CS:GO actually been approved by Valve yet? I know they did some AI showcases at their events in the past but I feel like this sort of thing, unless very limited in functionality, will go against their stance on cheating.


Thanks for sharing your ideas. We aim casual and competitive (amateur) gamers and don't provide any services for professional gamers. More specifically, we're targeting low-to-middle level gamers.

As you pointed out, some of features are not tailored made for expert players but they are being used by newbies. We aim to accelerate the learning curve of beginners.

We don't provide any service for CS:GO yet. We're doing some closed tests and developing the beta features.


As far as I know there are three types of player versus player (PVP) games: slow paced strategy games (Pokemon), fast paced strategy (Starcraft, League of Legends), action games (Call of Duty, Halo, Fortnite). For the first type of game, having a tool to teach the best strategies makes sense. For the latter two, not so much.

From personal experience, fast paced strategy and action games just require a ton of practice. I used to read up on the best COD weapons and the best League setup but that never really put me in a place of contention against top players. Regardless of how many videos I watched of the top gamers, I just wasn't good.

Question: I'm wondering what special info your app can provide players that will actually help them get better than just playing the game more. E.g. Knowing a person will "gank" more based on a tag doesn't mean the user will know how to respond to that.

Anywho, good luck on the launch! It's a big feat to even release a product - never made it that far myself haha.


I disagree, at least for fast paced strategy.

For instance in Age of Empires 2, the best way to improve is to look at a replay of your games, and analyse what went wrong. Stuff like "my economy was idle because I was focusing on the fighting" is much more flagrant then, during the game you often think it was just a few seconds, when in reality it could be a whole minute. I could see a lot of value in having an assistant that analyse your game after the fact and give you hints like: you focus too much on fighting, you have too much resource float, you have a big army but it's doing nothing, your army composition was subpar, you should have anticipated the switch to X, ... You could have it run real time as well, but then you get into the "is it cheating?" debate.

Action games are certainly more skill based as you said, and it's harder to give actionable advice.


Agreed. A product that tells me to build a pylon 10 seconds before I get supply-blocked would be amazing. Or if I have too much money and my production buildings are idle.

I've stood over friends' shoulders and done similar live-coaching. It definitely helps.


His point is it doesn't matter much if you hear that advice you still need to spend hundreds of hours improving your mechanics to actually execute that advice.


And my point is that there are many things beginners should and could do that they do not know about. Yes of course, once you have the advice you need to train and not everything is actionable. But for beginners something like a build order is actionable, and if you don't know about them, inventing them by yourself is going to take a while.


> I could see a lot of value in having an assistant that analyse your game after the fact and give you hints like: you focus too much on fighting, you have too much resource float, you have a big army but it's doing nothing, your army composition was subpar, you should have anticipated the switch to X

You're making this sound easy, but in reality it's very complicated.

How to you measure how much someone is fighting? What if they're playing a very aggressive style? What if the opponent is turtling?

What is "too much" resource float? What time period should it be measured over? What if the player correctly prioritized more important tasks over spending resources?

What is a "big army" and what does "doing nothing" mean? What if they're playing a passive style? What if they're actively roaming the map but not fighting?

Etc.

I have tried to create an analysis tool that does similar things for StarCraft 2, and it's extremely difficult because of how variable and contextual everything is.

It's easy for humans to look at these things and interpret the situation. It's way harder to create rules that accurately reflect human interpretation.


I am not saying it is easy, just that it can have value. If anything, the fact it is hard makes it more valuable.

I don't think it's hopeless though, the AI already does something similar. As a very naive implementation, you could for instance run your AI logic on the current state of the game and compare your move to the expected AI move. A bit like with a chess engine.


Completely agree. For the large majority of players, they just need to play more. Having more analysis and statistics is generally not useful until you have the basics down.


Thanks for your feedback. We do not try to minimize the time that you need to practice to play better, in a sense we help you to be more 'aware' of your current skill level (strengths and weaknesses) and what is going on at the game (meta changes etc.) to accelerate the learning curve.

Btw, thanks for your support, we appreciated it!


FPS can have great levels of strategy Quake Arena being a key example.

Map knowledge is a key in shooters along with aim and movement.


I spent a year looking into how to build esports business and related technology. The real problem with apps like this is that your business is at the whim of another business to decide if you're within terms of service. This is what happened to Visor when they tried to do the same thing with Overwatch. Moreover, even if the business doesn't think it's hacking (or you don't say it's hacking) there's the community perception of whether it's hacking as well. If you don't have the support of top tier players, they'll significantly influence perception of your product. There will also be no brand loyalty. If you are suddenly banned and can't support Valorant tomorrow, your community won't drop Valorant. They'll drop your product.

However, even if you manage to navigate all of that...each game is bespoke. There's little synergy between games to be had, so to expand into a new game requires, more or less, working from scratch. You also need game expertise in the product team to know how to expand into said game. It doesn't scale.

Finally...what's the exit plan? Who wants to take on the liabilities of this business? Perhaps you could sell back to the game makers...but why would they buy? It would be cheaper and easier to integrate what you're doing themselves, because let's be honest...what you're making is omitted by choice by the game's dev team.

This makes for a good hack project, but there's really no business here, as much as I wish there could be.


I'm currently using Gosu.ai in LoL ...it does provide some in-game commentary, basic strategy while events occur in the game. It does try to identify the "strongest" player on either side as the game progresses. I don't think this is crossing the line and could be helpful to new players. Crossing the line would be something like "Ezreal has 194 health remaining, your ult can finish him." There are other plugins that tally up the gold spent by your team and their team and try to estimate some gold advantage but it doesn't account for how much gold players are hording in their wallets.

I just tried Sempai.gg but it died about 5 minutes into the game (went black) and now won't restart. :-) It seems to provide similar information/analysis as other similar apps like Porofessor and other Overwolf plugins. I'd love to chat with the team about a wishlist of interesting stats culled from my own game history that could be useful to me.


Thanks for your feedback. We just deployed an update, please give another try. Hopefully SenpAI will work this time. We would love to hear your wishlist of stats & features for LoL!


This is one of the few genuinely great ideas I’ve heard lately. I’m honestly surprised some of these games have implemented this functionality themselves - it’d probably help reduce player toxicity and frustration amongst other benefits


There is a built in coaching system in DOTA 2.


There is also Dota Plus, with a monthly subscription, developed by the same game developer, basically the OP idea more or less


Very clever. Not a gamer anymore so won’t be a client, but it’s a great idea.

As I aged/matured/whatnot I find I have more money and less time. It’s great to have a service where I can close a skills gap time-efficiently for money.


> I have more money and less time

For me it's loss of interest, back log of bought games/gaming pc but can't get into the game anymore oh well.


The problem is that you still have to invest a shit load of time, even if you trade some for money.


Thanks for your support, appreciate it! Give it a try when you have time - hope you will like it!


This is interesting. Jumping into Warzone after everybody has memorized every corner of the map and knows where to look is a pain and something like this could help.

As a former CS player (1.6, CZ, Source, Go) I had these maps committed to memory. Now that I am far removed from school (and the maps got way bigger) this isn't super possible so I find I just get obliterated quickly then just peace out. Not sure if this could help with that as it might border on violating some sort of t&c.

I'll keep a look out for more games! Very cool.


I've always hated the map memorization thing. To me it destroys the uncertainty and exploratory aspect of a game like CS. I didn't mind it as much in Team Fortress (which is built on cartoonish excess and thus fosters a sillier and less aggressive style of play. Thinking back to when I was a regular CS player, my favorite ever map was a Katamari Damacy style giant room where the players were effectively reduced to the size of action figures and moving around was quite time-consuming. Visually it was quite crude - very basic textures and blocky objects - but it gave rise to all sorts of interesting tactical problems and solutions, while being big enough to make speedrunning impractical.

It's surprising to me that there aren't more procedurally-generated environments for multiplayer; there might not be as interesting to spectate (because you don't know where to look or what to expect), but they'd probably be much more exciting to play.


Due Process is an interesting indie-developed tactical FPS, somewhere between Counter-Strike and Rainbow Six. Its main differentiating feature is semi-random maps (and a unique art direction for this genre).

Every week, the developers proceduraly generate new maps using a theme / tileset (e.g. convenience store, chemical warehouse, gameshow studio), then remove ones that don't survive a playtest. A dozen or so maps are introduced each week and there's no way to choose one, making the pool too large for memorization to be useful.

At the start of each round, teams get some time to look at an overhead view, draw a plan on the map, and decide which of their limited resources to use (night vision goggles, breaching charges, barbed wire, etc.). While the layout is random, different areas on the map will have unique features, like a vault that can be opened with explosives or by pressing a button elsewhere, an arcade room with dim lights and cabinets for cover, or a bulletproof cashier's window.

I've been following the project for years and bought a copy when it entered early access last year. It has a friendly community (for now). Big recommendation from me. https://store.steampowered.com/app/753650/Due_Process/


I was just looking at that the other day and wondering if it would be fun. Will definitely check it out with that endorsement.


there isn't really an exploratory aspect to (vanilla) CS. it's a competitive shooter with a small number of small maps, and the weapons are pretty clearly balanced with this in mind.

mods and community maps are a different story, of course, but they diverge quite a lot from the main game.


Additional uncertainty arising from randomness in MP settings reduces the impact of skill (ie memorizing the map) so pvp designs tend to shy away from them, especially in the more esports focused side like CS. There are definitely some skills more fun than others though, otherwise everyone would still be playing Quake3.


Having consistent, memorizable maps allows someone to make progress and improve at the game by learning the map and developing, testing, and iterating on strategic positioning and movement.

Having random maps doesn't encourage that, but does encourage other things like adaptability and just pure mechanics, since you can't rely on having good positioning and map knowledge of course.


I’m in forties and haven’t gamed since about 2000. Except I once played 2 early assassin’s creed about 8 years ago. Just got an Xbox series X. It’s weird playing all the multiplayer online games. Rocket League is fun but, wow it’s difficult to master. It seems to take a lifetime of hours invested to play at highest levels. All that to say, I actually see the value of coaching in the video game realm now where I completely did not “get it” just a few months ago and this sounds promising.


Thanks for your feedback. We would love to get your feedback when we integrate to Rocket League. Hope you will master the game with the help of SenpAI.


Can you explain the advantages of Senpai.GG over Blitz or OP.GG? I have used both extensively and they offer everything you've listed here, and for more than just RIOT games.

Honestly after checking out the site I don't see anything that isn't on OP.GG.


Thanks for your comment. For LoL, OP.GG focuses on stats (post-game) and actually provides more stats than SenpAI. Blitz doesn't provide comprehensive tags at pre-game. For Valorant, both of them does not provide the features that we enable with the voice assistant.


Hey—congrats on the launch! I'm a big Valorant player (peaked Immortal 3 a few seasons back) and I've also used/talked to the people at visor.gg and pursuit.gg when they were around.

Totally understand the concerns here around being at the whim of the publisher, and previous companies have been blindsided by changes in how companies like Blizzard decide what is and isn't allowed on their platforms. Interestingly, YC has had a few of these companies go through similar experiences but I think they still think there's something to be built in this space.

For what it's worth, I think this is a good idea that's going to run into similar issues, regardless of what safeguards are put in place to avoid stepping on the publishers' toes. I'm sure there are some learnings from talking to Ivan or James from the last two YC companies that tried to do this. Also happy to share some more of my thoughts :)


Thank you very much for sharing your thoughts. We're aware of visor.gg (had a talk with Ivan) and pursuit.gg and are trying to learn from previous experience in this domain.


I'm stretching my memory a lot here so I could be wrong, but didn't Curse Voice do this early on and it was banned by Riot and had to remove any of the "assistance" it provided? I think this is a great idea, but not clear on how you're able to confidently say it's a-okay with Riot.

https://dotesports.com/league-of-legends/news/curse-voice-ri...


The cheating question has been covered more than enough so I'll ignore that.

How will you avoid having the game studio eat your lunch in the blink of an eye if your service becomes remotely popular? Look at what Dota Plus offers, and consider how the game developer holds all of the keys as well as the rulebook itself regarding this. How do you carve out a competitive advantage against that?

Moreover, how is there not extreme risk against a developer simply deeming your tool a cheat and eliminating it? That's a lot of effort struck out with one rule change, and it could be up to and including entirely eliminating your ability to provide your service, rather than something you just need to tweak around. That strikes me as an extreme amount of business risk for you.

It also seems like the games which would provide the biggest target audience for you are simultaneously the ones where there's most likely to introduce that sort of ban. Your service highly focuses towards competitive multiplayer esports games, and towards players who want to be more competitive rather than play it causally. It seems like the venn diagram of people who would use your service and people who would be most affected by bans is a worryingly overlapping venn diagram.


There’s also the danger of a game falling out of fashion after a couple of years. What do you do in that case? The training you can offer needs to be customized to each game. It has to be both useful and not considered cheating, so expanding the business to other games would be tricky.


As someone who currently plays League of Legends, my question is: What's the difference between this service and using op.gg (they have a client similar to yours) and porofesor? As far as I know, op.gg doesn't have any freemium features.

What I've seen from paid coaches is that they comment on the game as it goes on, for example telling players to attack the enemy more in lane, and I don't see how this would be replicable without access to LoL's private apis


So as somebody who played LOL, and debated paying a coach but ultimately didn't here's one person's input:

- I wouldn't have paid for what you described for LOL. (One data point)

- I wanted a practice tool better than what LOL offered. I basically had no way to practice specific matchups at a fast pace. For example if I wanted to repeatedly practice level 1 all-ins, that required committing to a 40 minute game and possibly having my team be annoyed at me. Likewise if I wanted to practice 5v5 fights where a particular ult is a game-deciding moment I had no way either.

- I don't know if I would have paid for the above, maybe I would have if I felt like it worked. Ultimately what I would want to know from a coach is -> for every moment in my replay what did I do wrong: could I have won a specific 1v1?, did I use my abilities well?, was I in the right part of the map?, what was our composition's win-condition and was I helping it enough?

So replay-analysis is what a lot of people buy from coaches, is definitely not a violation of TOS or risk of getting banned. May be worth considering that and working your way towards automation gradually.

Regardless, best of luck!


There was a similar service provided for Overwatch a few years ago that would provide information about how you played. I seem to recall Blizzard explicitly calling out that product as cheating, and the service no longer exists. Perhaps for some games this will work, but for others this seems like a risky endeavour.


I misread and was getting unnecessarily excited about the prospect of a gamer couch.


Very interesting. I like the approach, and it seems quite scalable compared to 1:1 coaching sessions. There’s a lot going on in this space at the moment.

A friend of mine recently came to me regarding a tool he’d built in the space, focused on asynchronous video based coaching (https://www.volt.school/videos/c980297a-417b-416f-947b-58a70...)

Then in doing some research for him on the space I found Metafy.gg, who are a more traditional coaching / school outfit, which have raised $5M. Tho it’s really just a marketplace.

Insight.gg was the most impressive piece of tech, but seemed to have stagnated a little.

Interested to see which models thrive in the long run.


I look forward to seeing how you differentiate yourselves from Blitz.gg in a crowded market place given you are starting with the same supported games.


Great name.

I think you're falling into the classic trap of focusing on something scalable rather than something that's effective. I'm sure that your system provides some value, but I think even a mediocre human coach would be 10x more effective. What you're providing is incremental improvements based on statistics, but often in order to progress to the next level of competition players need to reevaluate their gameplay on a fundamental level (posture, mental fortitude, interaction with other players, mental model of the game, etc).

I think getting into that human element also opens alot of interesting opportunities to become more entrenched in the competitive gaming scenes which opens up other revenue streams.


you pitch it as a training coach to help players improve but then your app just looks up the opponents and helps with timers? seems incongruent


I think a marketplace for human coaches would be useful. I just hired one, and it definitely is not efficient, to say the least. I've had coaching for two different games.

The problem with the AI-related stuff it that it is very tactical and statistical. The strategy in many games is usually way more impactful.

All the statistics you mention are commodity for League. 5 different tools provide that info. The more impactful questions to answer would be whether to stay in lane or help a teammate, freeze the wave or push.


When you add escape from Tarkov auditory radar let me know. You should be able to use software to tell me where the enemies are and what direct they are roughly as well as what weapons they’re shooting. Been looking for a good passive cheat for that game that doesn’t require DMA. I love that YC is getting into ‘passive’ game cheats. This has huge potential people pay good money for cheats.

I learned programming reverse engineering last kingdom, Everquest and others.


Oh man.. good luck. I don't think AI can ever replace human gaming coaches. Maybe for things like chess which have very strict rule-set.

Thing is, competitive games are so dynamic that there are countless options every single moment, and getting better is knowing how to choose the right option to minimize errors. Improving only comes from 3 things: Practice, watching your own games, and then practicing more. Human coaches are great because they can pinpoint tactical mistakes you've made throughout the game, as well as letting you know when you've done well, and there wasn't much you could have done better.

Things like "Early game gold loss" are absolutely meaningless, because many times that is completely acceptable in regards to your game plan. It's like saying "Opponent played better than you in the start".

These kind of things are more like "slight advantage in preparation to the match", but the Valorant stuff seems like straight up unfair advantage (i want to refrain from the word cheating but it's cutting close). Your true but "doesnt sound as good" marketing should be - we'll help you win more games up to a certain level where we aren't efficient anymore.

But hey, like I said, good luck.


Thanks for sharing comments. We don't have a plan to replace human gaming coaches. We rather consider ourselves as complementary service to human coaches. We provide some tactics and suggestions based on data whereas human coaches are capable of making complex recommendations.

Providing "Early game gold loss" tag for a single match is not a huge win, as you described. However, if the gamer has the same tag for the majority the games, it shows an indication for weakness. That's our fundamental idea behind how it helps.

We believe we don't create unfair advantage because we provide suggestions based on the already information on the screen.


How does

> For example, we have an "Early Ganker" tag for the gamers who tend to gang in the early game. [...] We provide these tags based on only publicly accessible data on the official game publisher API. For example, any gamer can search for the opponents’ game data and conduct a similar analysis.

work? Is this the sort of analysis that is humanly possible to perform before a match?


I think this goes against the spirit of the games with how you’ve implemented things currently.

My first impression was that the product/service would give you feedback post-game. Ultimately as the founders you have the final say, but I think that could be a really interesting avenue to explore instead.


Just wanted to say very cool and very wesome idea. I am someone who has invested tons of time into valorant in hopes of getting immortal. I finally got to plat 2 from silver. I’ll definitely check this out over the weekend and give feedback this could actually help me


Thank you. We're looking forward to your feedback.


Can your models explain why certain moves are better and not just recommend what to do next?


If you're referring to in-game moves (e.g., moving in the map, aiming, etc..), we don't cover this kind of suggestions.


For league of legends I can see how this can work, in fact I've used many similar tools to understand how a certain champion works.... for the other games tho - the ones that are faster - wouldn't an in-game agent (like a coach) with good suggestions work? For example, in Warzone, someone in-game could say, oh look you might have not noticed but there are enemies shooting there, either go on 3rd party or steer clear of the area.

but now I guess that's against TOS of most games, right? i.e. a voice that tells you what to do / how to do better next round. Now that would be something useful to learn faster!


Valorant's voice assistant is, at first glance, in the gray area of cheating.


Not knocking the product, which I'm sure does what it says on the tin and will be popular amongst gamers (at least until Riot either bans them or implements all of their features in the main game), but I really lament the death of old multiplayer game culture.

I miss the days when online gaming was less about studying optimal strategies to increase your rank, and more about just killing random dickhead and then shit-talking them in all chat.


Streaming probably ruined that forever


Sounds like a really good idea, if the implementation is good enough. I don't play any of those games, but I might try Valorant out just to try out your software.


Thanks for your support! It is easy to try the Valorant Voice Assistant.Please let us know if you have any trouble / feedback after you try it. Appreciated.


As a regular overwatch player I instinctively don't like this product. It is cheating and will help certain people over others.

However...

I also see a huge gap in the market for automated video game coaching and think people will pay good money for this.

If you can move more in the direction of the latter (coaching) and less in the former (in-game assistant), I think this can be wildly successful.

Otherwise, I hope all the anti-cheat products put you on the ban list. Sorry!


As someone who lived in the same dorm and witnessed the mentioned AoE2 games, I’d like to petition for AoE2 support as well. :) Congrats on the launch!


Very interesting. A personal coach is certainly the most efficient way to improve. My main concern is about the legality of such a software. Even if the data is presented on screen and available, changing the UI to help the player is not accepted in all games as it can provide a strong edge. For AoE2, part of the game is about scouting and remembering key information while managing your economy.


Thanks for the comment. We don't change the UI but provide some verbal notifications. An analogy, would be making a beeping sound when there is an idle villager.


Congrats on the launch, a question on the technical side of things -- how much computational overhead does your desktop client incur on the host machine? If you're running CV algorithms locally, would that necessitate higher minimum system performance specs beyond those recommended by Riot/other game vendors to avoid impacting the performance of the game client itself?


Thanks for the support, appreciated! We are trying to develop a lightweight CV algorithm so that will affect the performance of the game client. So far we didn't get problem regarding the FPS drop.


Small nitpick/advice, the hero subtext should be a little bit shorter and more to the point (you have 3 instances of "get better at games" paraphrasing). I like how descriptive the rest of your site's copy is, but the hero should be parseable in its entirety very quickly.


Thanks for the suggestion. I believe you're referring to "Up To Date Lol Meta Champions With Tier List" title on the League of Legends page. We'll work on that.


No I was referring to:

> GET BETTER AT THE GAMES WITH SENPAI.GG GAMING ASSISTANT SenpAI.GG is the best gaming assistant that will help you get better at the games you play. With the help of Artificial Intelligence, SenpAI.GG offers you the best guidance to help you carry your ranks to the top!


I wish I was some angry white guy from the 50s just so I could experience first hand what it’s like to hear about a computer program that teaches you how to perform better at video games.

As opposed to an actual person and an actual game.


I think your product generally sucks, and should instead be a service for pairing players with coaches that see nothing but what the player sees while they play, maybe for an hourly rate.


While I agree that their current product is pretty subpar and scummy, the vision is to replace exactly what you're describing (which already exists in some forms): an ML model for game analysis scales better and is cheaper than humans


This may be an interesting idea to pivot and apply as an assistive technology for users with disabilities, I'm not sure how many modern games are easily accessible to them.


This is an amazing idea! Thank you very much. We'll definitely consider how we can execute on this.


How do you plan on differentiating and competing against http://playvs.com/?


Other companies in this space make money off ads.


This has a similar vibe to poker site overlays. I think that industry can serve as a good model for understanding this business


Awesome. And... Aoe2 is still kicking! Maybe second most popular RTS after StarCraft 2?


By twitch viewers, AoE2 is more popular than SC2 I think.


Add Rust, developing an AK spray is not a simple task especially at 40+ years of age.


Good idea. What are the best way for status updates regarding the companies growth?


The site requests access to connected VR headsets when I open it. Is that intended?


No, it's not. It would be great if you can provide more detail so that we can fix this problem. Thanks.


Sure! After I click on valorant on the main page, this notification pops up in firefox on Windows with an Oculus Rift connected. https://imgur.com/sfcjaP3


How is this different from metafy.gg who just raised a pretty large round?


metafy.gg is a market place that gamers can find gaming coaches. We're a desktop application providing similar range of service.


Please launch this for COD!


Absolutely! This would be pretty awesome for Warzone and/or CS:GO

(Maybe BF when that one finally arrives)


Thanks! COD is in our pipeline - cant give you the exact timeline but we definitely would love to support COD players as well!


a HUD for games

noticed dota either made the game more technically friendly or provided more info in-game (either with a battle pass HUD or just more info in the overlay)

cool that yall are making this for every game


Do y'all have interest in fighting games, specifically SSBM?


Unfortunately, we don't plan to support fighting games in near future.


How do you make money?


We have a freemium business model. Premium users have access to all features and no ads. We drive revenue from free users through advertisements.


They could be a universal game assistant sold as a subscription service if they could generalize it to most games.


I noticed advertisement on their desktop client.


Good idea. Lemme know if you are going to IPO. Thanks.


If you don't have trainers for EVE Online ... ;)


Unfortunately, we don't support EVE Online.


Love the senpai/kohai reference in the name.


Thank you.


looks nice ! still working on mine at saltymotion.com Good to see there is widespread interest in that field.


i guess the pun on AI wouldn't work, but shouldn't it be called sensei?


I hate that launch hn’s have become a full wall of text detailing the founder’s origin story and whatnot instead of a simple TLDR of what their company does.


No Dota 2 :(




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: