Rendered at 05:57:19 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
m_kos 12 hours ago [-]
> Rageprompting
Lovely name! I implemented profanity monitoring in my Hermes setup to identify "learning opportunities" for my agents. It is quite useful. If you are budget-conscious, one challenge is determining what is the smallest number of previous rounds that Hermes needs to correctly infer what it did wrong. Curiously, Claude Code is horrible at figuring out what it did wrong. I often read its memories, and they are rarely useful.
laalshaitaan 12 hours ago [-]
haha yea, i even got the domain rageprompt dot com like a couple of days ago lol i love the name too.
for profanity, did you define keywords or just let the agent figure out rage stuff?
how many rounds did you set for the hermes? claude doesnt work yea on its own, one of my friends set us up for their claude lol
gabriel666smith 6 hours ago [-]
I built an in-house version of this a couple of years ago for where I was working. My concern would be that by excluding observability, you might end up creating a really selective dataset, whose conclusions you're then asking companies to take seriously when allocating resources to different possible roadmaps.
My guess would be that agent logs would highlight obvious feature requests and bugs for smaller companies - like customers expecting an AI video editor product to be able to add subtitles to a video by itself.
For larger companies who deal with a higher volume of inbound customer support / agent requests, there will probably be big, noisy, already-known-by-the-team query clusters that make up big portions of the dataset - for example, "billing issue with my subscription". After those big clusters you'll likely have a really long tail of different queries, and - without deep observability - no real way to rank their importance. I also think you'd be unlikely to understand the root cause of the product issue in a complex developed product with lots of users solely from agent logs. Most product teams can't make good product decisions consistently, and they're working with a lot more data.
If coupled with staying out of evals (which, btw, I wouldn't find trust-building, if I were a potential customer of yours), I think that it might be difficult to provide genuine value in this space for larger orgs - without evals it's easily dismissed as just fancy & mostly-contextless sentiment analysis.
But I hope I'm wrong! I do think that (though each org's needs probably have to be catered to in a very boutique way) there are huge gains available by rolling LLMs & language analysis into existing product workflows, and that what you're pitching is absolutely a part of what companies should be doing. We are, of course, meant to actually listen to customers - and LLMs/agents should be making that easier, not harder. Absolute best of luck!
laalshaitaan 5 hours ago [-]
i like these kinds of critiques, we don’t think conversation logs or analysis on top of it is alone enough to replace observability or evals. imo they answer diff questions for diff use-cases.
we're betting that there is a TONNN of product signal buried in conversations that observability misses, esp around like raging, writing in all caps, repeated prompts, frustration loops, and subtle hidden feature demand. thats also why we use per-customer taxonomies instead of a shared one. evals will still be needed.
the root cause is harder, especially in more mature agents. we're using this more as a discovery layer for evals or even just whats happening kind of things, then letting teams go deep into the actual conversations and decide what to take action upon
benswerd 10 hours ago [-]
Without using agnost, what are some basic SQL queries I can run on my data to find outliers I'd otherwise be missing?
How far can I get with just keywords, common phrases, boring traditional analysis?
Depending on what I measure there, when is the right time for me to consider upgrading to something like Agnost/what is a specific example of what it will find that traditional/rigid analytics approaches will miss?
AjmeraParth 9 hours ago [-]
keywords and sql rarely work - you can not find the repeated hidden feature requests, cause we don't know them at the first place yet, or a frustrated user puts vague signals as ugh, ahh, or just an 'f!' (and added modalities, accents and languages makes it much more challenging)
interestingly, even embeddings seem to bucket "no" and "nooo!" somewhat similar, but are pretty different when viewed from a user satisfaction perspective.
A sweet spot on moving to Agnost is the time when you get higher inflow of conversations you can't manually read or listen, and want to clusterize them into things which matter, with the outliers highlighted
StackOptimist 5 hours ago [-]
[flagged]
kianN 6 hours ago [-]
I see a fair number of comments here advocating for either codex to hand-roll this themselves, or to simply punt to SQL. I do want to advocate for the difficulty of the problem, even if I can't speak to the company itself.
At the scale of a few hundred to a few thousand documents, especially short documents, there are a few out of the box methods that can yield reasonable results, whether it be embedding clustering or leveraging LLMs for tagging.
However as your (1) datasets gets larger (2) documents expand from tweets and text messages to 30+ minute conversations and (3) you build downstream analytics on top of the learned semantic units, you really start to feel the limitations of LLMs and embedding for reliable annotation. That doesn't even get into the nuances associated with taxonomy management, seasonality, and model drift.
TLDR; this problem solved effectively has a lot of value and is a lot harder than it seems.
laalshaitaan 5 hours ago [-]
yea, at our volume which we still consider small as we've been able to figure out a way with llms & embeddings, its still fine. + we onboarded a voice ai company with more than 2 hour calls and thats when it was super hard to solve since there were so many elements to consider.
model drifting is something a lot of folks do face after 5th/6th turn as per my understanding and it usually the median, how did you tackle it if you have yet?
also yea, thats why we went for a per customer taxonomy than a general one, yeilded better results + easier to improve upon.
kianN 4 hours ago [-]
To clarify, I wasn't criticizing your approach or product, more responding to the people dismissing the problem you are solving.
Regarding my experience, I have done a fair amount of work in the contact center space with long calls. I used statistical Bayesian approaches which I found to be much more resilient especially on long documents than embeddings/transformers. It also provided a joint modeling foundation for classification with much lower label requirements than BERT or traditional ML.
laalshaitaan 2 hours ago [-]
im hearing this for the first time and damn! i just told this to my cofounder/cto and he said hes gonna give this a shot in the coming days.
damn, i read bayesian in statistics like years ago, never thought itll come back this way
kianN 1 hours ago [-]
Happy to chat more in depth if more details would be helpful. I think my contact info is accessible from my HN profile.
rjnz199 4 hours ago [-]
the hard part isn't extracting quotes, it's attribution – separating what the user actually felt from the agent's own framing, and sentiment that flips inside one session.
vivzkestrel 11 minutes ago [-]
did you actually use AI to write that? it sounds like an "the hard part is not A but B" which is literally what every LLM model generates
laalshaitaan 4 hours ago [-]
seems ai slop
r_thambapillai 6 hours ago [-]
Great launch!! There’s a lot of very silly comments of people saying they will vibe code this… errr good luck being the slop version of this startup. :/
It’s a cool product and I’m curious to see where you go. We build an MCP factory, where our enterprise customers use our product to build MCPs that their employees use in Claude or Codex. What would be cool for me is if I could use this to surface insights to them, rather than just to our team.
laalshaitaan 5 hours ago [-]
i love this comment bec we started as analytics for mcp servers haha! we then expanded to conversations bec thats where most mcp servers were being used lol.
we havnt figured out yet how to do the b2b2b kinda thing where we surface insights for a multi-tenant sort of approach but i've gotten this now twice in the last hour so happy to chat.
what would you want them to see first though, are these semantic insights like we do today or more around deterministic tool calls/etc metrics?
r_thambapillai 4 hours ago [-]
our current prototype of this functionality is fairly basic and surfaces things from the underlying chats like: Users want a "create ticket tool", or "The run SOQL query often fails because it references fields that don't exist. You should provide documentation of the actual fields". Happy to chat if you want to you can find me on bookface as the founder of credal
laalshaitaan 4 hours ago [-]
oh gotcha, yeah happy to chat more! yeah DMing
mellosouls 8 hours ago [-]
Well, good luck with the launch, this seems like an interesting product with potential.
However privacy is central in a service like this and I think you should probably beef up your representation of how you deal with that.
eg. "We use each customer’s data only for that customer" - well that customer may have hundreds of staff; how are they being consulted and onboarded wrt their own voices (or is that transcripts?) and messages being used in this way?
ofc you might argue that nothing in work is private but I do think you have some margin for improving the detail here.
laalshaitaan 8 hours ago [-]
[dead]
petesergeant 7 hours ago [-]
My junior developer has a Claude Cowork skill she built to do this over about 25,000 messages a week to our agent, and it seems to work pretty well. Struggling to understand what $499/month would buy us here?
laalshaitaan 7 hours ago [-]
oh damn, can you share what the skill is actually doing for you like on a daily basis: is it creating clusters, scoring known issues, or finding new patterns? and what data points are you giving it to if any w the messages?
usually a boundary for us is usually where a skill/claude analysis needs to maintain/make changes/pass it to an agent as a workflow
for the pricing we're still learning and building as many custom features/requirements as possible bec we wanna make sure we deliver way more value than what we charge today.
petesergeant 7 hours ago [-]
Classification of types of user frustrations and sentiment analysis, content trends, engagement and gap analysis, as well as then looking at changes from the previous week. We also look at how certain queries turn into actions in the system (eg: which users take actions we offer them). We run it once a week, rather than every day, and it provides an exec-facing overview, as well as areas for support to dig further in to. While it's some good work, as far as I'm aware it's almost all just a text prompt and a connection into Langfuse.
laalshaitaan 7 hours ago [-]
okay nice, also is it safe to assume you do once a fortnight releases then? like look at the last week's data then use it for product decisions the coming week?
also have you updated/made any changes to this skill that has improved it significantly?
and anything you hate/wish it had as of today? wanna learn if there's any painpoints around this? is it keeping the skill updated, getting useful signal from the clusters, or turning the findings into something the rest of the team can actually act on?
zuzululu 13 hours ago [-]
why would i pay $499/month for this when codex costs $199/month and can do everything you described
laalshaitaan 12 hours ago [-]
codex is great for like a one-time/overview analysis on a handful of transcripts. we usually serve to companies where the volume is >10k messages & continuous ingestions + with claude/codex it messed up this + metadata linking of the user like what plan are they on, when is it expiring, etc.
although we had a few customers who come to us after running this for a while so at smaller volume it does work well.
zuzululu 12 hours ago [-]
i mean i would get codex to build everything you just described
dakolli 9 hours ago [-]
Do it then.. the hubris of vibecoders is really something.
embedding-shape 7 hours ago [-]
Reminds me of what people been spitting in my face (with a slight variation) for much of my career:
> A (vibe) programmer knows the value of everything, but the cost of nothing
ImPostingOnHN 11 hours ago [-]
Would you?
Looking forward to your "show HN" post.
laalshaitaan 11 hours ago [-]
lol true but then you’re just building another us :D
sahitya_ 2 hours ago [-]
[flagged]
synapsehire 6 hours ago [-]
[flagged]
WangYixiao 13 hours ago [-]
[flagged]
czeizel 8 hours ago [-]
[flagged]
lnenad 10 hours ago [-]
I thought startups wrapping prompts would require something a more complex than semantic analysis, which is literally what this is. And for 500 bucks. Wow. Props for being able to sell this.
I don't get the appeal of the UI, why is it so complex/convoluted.
laalshaitaan 10 hours ago [-]
lol i wish it was just wrapping prompts but things got harder once our customers grew bigger, we had to build queues. we had to do context management for bigger conversations and bunch of metadata fields started coming in per customer.
lnenad 9 hours ago [-]
It's still a prompt, it's just not a static one. Either way props for building a company from it.
laalshaitaan 9 hours ago [-]
we're still learning and so our the prompts haha, whats your take though
dakolli 9 hours ago [-]
How is it just a prompt? Like hey, I hate AI companies with a passion but I think this is a lot more than just a prompt.
lnenad 9 hours ago [-]
I don't hate AI companies. The key value proposition is gather data > feed it to AI for semantic analysis (does the actual work, is a prompt) > display it in a UI
laalshaitaan 9 hours ago [-]
on a satirical note: we also have an mcp server/api endpoint if you dont want the ui
Lovely name! I implemented profanity monitoring in my Hermes setup to identify "learning opportunities" for my agents. It is quite useful. If you are budget-conscious, one challenge is determining what is the smallest number of previous rounds that Hermes needs to correctly infer what it did wrong. Curiously, Claude Code is horrible at figuring out what it did wrong. I often read its memories, and they are rarely useful.
for profanity, did you define keywords or just let the agent figure out rage stuff?
how many rounds did you set for the hermes? claude doesnt work yea on its own, one of my friends set us up for their claude lol
My guess would be that agent logs would highlight obvious feature requests and bugs for smaller companies - like customers expecting an AI video editor product to be able to add subtitles to a video by itself.
For larger companies who deal with a higher volume of inbound customer support / agent requests, there will probably be big, noisy, already-known-by-the-team query clusters that make up big portions of the dataset - for example, "billing issue with my subscription". After those big clusters you'll likely have a really long tail of different queries, and - without deep observability - no real way to rank their importance. I also think you'd be unlikely to understand the root cause of the product issue in a complex developed product with lots of users solely from agent logs. Most product teams can't make good product decisions consistently, and they're working with a lot more data.
If coupled with staying out of evals (which, btw, I wouldn't find trust-building, if I were a potential customer of yours), I think that it might be difficult to provide genuine value in this space for larger orgs - without evals it's easily dismissed as just fancy & mostly-contextless sentiment analysis.
But I hope I'm wrong! I do think that (though each org's needs probably have to be catered to in a very boutique way) there are huge gains available by rolling LLMs & language analysis into existing product workflows, and that what you're pitching is absolutely a part of what companies should be doing. We are, of course, meant to actually listen to customers - and LLMs/agents should be making that easier, not harder. Absolute best of luck!
we're betting that there is a TONNN of product signal buried in conversations that observability misses, esp around like raging, writing in all caps, repeated prompts, frustration loops, and subtle hidden feature demand. thats also why we use per-customer taxonomies instead of a shared one. evals will still be needed.
the root cause is harder, especially in more mature agents. we're using this more as a discovery layer for evals or even just whats happening kind of things, then letting teams go deep into the actual conversations and decide what to take action upon
How far can I get with just keywords, common phrases, boring traditional analysis?
Depending on what I measure there, when is the right time for me to consider upgrading to something like Agnost/what is a specific example of what it will find that traditional/rigid analytics approaches will miss?
interestingly, even embeddings seem to bucket "no" and "nooo!" somewhat similar, but are pretty different when viewed from a user satisfaction perspective.
A sweet spot on moving to Agnost is the time when you get higher inflow of conversations you can't manually read or listen, and want to clusterize them into things which matter, with the outliers highlighted
At the scale of a few hundred to a few thousand documents, especially short documents, there are a few out of the box methods that can yield reasonable results, whether it be embedding clustering or leveraging LLMs for tagging.
However as your (1) datasets gets larger (2) documents expand from tweets and text messages to 30+ minute conversations and (3) you build downstream analytics on top of the learned semantic units, you really start to feel the limitations of LLMs and embedding for reliable annotation. That doesn't even get into the nuances associated with taxonomy management, seasonality, and model drift.
TLDR; this problem solved effectively has a lot of value and is a lot harder than it seems.
model drifting is something a lot of folks do face after 5th/6th turn as per my understanding and it usually the median, how did you tackle it if you have yet?
also yea, thats why we went for a per customer taxonomy than a general one, yeilded better results + easier to improve upon.
Regarding my experience, I have done a fair amount of work in the contact center space with long calls. I used statistical Bayesian approaches which I found to be much more resilient especially on long documents than embeddings/transformers. It also provided a joint modeling foundation for classification with much lower label requirements than BERT or traditional ML.
damn, i read bayesian in statistics like years ago, never thought itll come back this way
It’s a cool product and I’m curious to see where you go. We build an MCP factory, where our enterprise customers use our product to build MCPs that their employees use in Claude or Codex. What would be cool for me is if I could use this to surface insights to them, rather than just to our team.
we havnt figured out yet how to do the b2b2b kinda thing where we surface insights for a multi-tenant sort of approach but i've gotten this now twice in the last hour so happy to chat.
what would you want them to see first though, are these semantic insights like we do today or more around deterministic tool calls/etc metrics?
However privacy is central in a service like this and I think you should probably beef up your representation of how you deal with that.
eg. "We use each customer’s data only for that customer" - well that customer may have hundreds of staff; how are they being consulted and onboarded wrt their own voices (or is that transcripts?) and messages being used in this way?
ofc you might argue that nothing in work is private but I do think you have some margin for improving the detail here.
usually a boundary for us is usually where a skill/claude analysis needs to maintain/make changes/pass it to an agent as a workflow
for the pricing we're still learning and building as many custom features/requirements as possible bec we wanna make sure we deliver way more value than what we charge today.
also have you updated/made any changes to this skill that has improved it significantly?
and anything you hate/wish it had as of today? wanna learn if there's any painpoints around this? is it keeping the skill updated, getting useful signal from the clusters, or turning the findings into something the rest of the team can actually act on?
although we had a few customers who come to us after running this for a while so at smaller volume it does work well.
> A (vibe) programmer knows the value of everything, but the cost of nothing
Looking forward to your "show HN" post.
I don't get the appeal of the UI, why is it so complex/convoluted.