laalshaitaan
laalshaitaan on Hacker News
that on the customer's side to redact the PII as you are the ones sending it and you'd know better than us
i get the push, most teams come to us after they've done/tired of the claude running analysis thing manually and want a pro-active thing.
we're also targeting conversation first use cases and for them this serves as their everything custoemrs. we obv do not sell the fancy part, idts that sells anymore lol. lot of our queries come from our slack app/mcp.
its fascinating how the toyota example comes up anywhere, its so good!
wdym by modelling the messages and conversations though? i lose you a bit there! for the crm approach, i do think it'll be a problem at some point right now.
the replacing budge is an interesting piece, we did not think of it yet, yes let me dm you on x!
a lot of our customers want a daily morning report on slack & flag things instantly rather than to wait for a week so thats why we keep it realtime
it gets hard when you need this continuously across lots of chats/calls, with metadata, changing clusters, going deeper into a user journey, etc. the LLM call is just one part of it lol
we're keeping it useful every week, finding out insights that the teams can extract value out of, work with them to understand users better.
the procurement what we've seen is v similar to how one would have for any analytics product? and we're selling this to companies when/once it becomes someone's job to do this
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
oh gotcha, yeah happy to chat more! yeah DMing
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?
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
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.
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?
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.
on a satirical note: we also have an mcp server/api endpoint if you dont want the ui
we're still learning and so our the prompts haha, whats your take though
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.
lol true but then you’re just building another us :D
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.
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
I’m gonna try and give this to my cloud agents and get a benchmark now lol
Posted by
laalshaitaan on Tuesday July 14, 2026 @12:06PM
from the agnost.ai dept.
https://agnost.ai
Hey HN, we’re Shubham & Parth, childhood friends building Agnost AI (https://agnost.ai), product analytics for teams building chat and voice agents.We read production conversations and find behavioral failures like users rageprompting (cursing at the agent), repeatedly rephrasing the same request, correcting the agent, asking for missing features, or leaving after an answer that was...
lessgooo! context dev ftw!
Posted by
laalshaitaan on Thursday February 13, 2025 @04:16AM
from the show-hn dept.
ahh, what'd you suggest?
Because the standard alphas that are submitted to other funds, they usually backtest it with years of data. And then let it paper trade for 3-6 months to make a decision on how much to bet upon.
would love to get your insights, since you've experience w hedge funds as well as algos
how is this better from an open source + self-hostable solution like Papermark?
like the ui though!
we show the investors the algo's backtest performance with years of data & 3 months of paper testing it on live!
they bet on the algorithm & not the developer as such! but they can see the dev's other algos and their AUM, returns, sharpe ratio etc to see how they're performing
yep, its similar! however, here you do not copy trade a person, here you trade as per the algorithm designed by the quant algorithm developer.
Checkout Dime on App store, its a great personal finance management app! Super sleak UX
lol not ai! yeah i do. so basically i'm building:
https://exponential.markets/ and currently looking to understand if repositioning our brand for investors to invest in hedge funds will be more converting rather than invest in algorithms