Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations

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?

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.

> 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.

why would i pay $499/month for this when codex costs $199/month and can do everything you described

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.

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.

ofc you might argue that nothing in work is private but I do think you have some margin for improving the detail here.

why would i pay $499/month for this when codex costs $199/month and can do everything you described

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?

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.

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

> Rageprompting

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 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.

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.

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

interestingly, even embeddings seem to bucket "no" and "nooo!" somewhat similar, but are pretty different when viewed from a user satisfaction perspective.

although we had a few customers who come to us after running this for a while so at smaller volume it does work well.

i mean i would get codex to build everything you just described

It's still a prompt, it's just not a static one. Either way props for building a company from it.

we're still learning and so our the prompts haha, whats your take though

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.

i mean i would get codex to build everything you just described

Do it then.. the hubris of vibecoders is really something.

Would you?

Looking forward to your "show HN" post.

lol true but then you’re just building another us :D

we're still learning and so our the prompts haha, whats your take though

Would you?

Looking forward to your "show HN" post.

lol true but then you’re just building another us :D

Do it then.. the hubris of vibecoders is really something.

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.

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

on a satirical note: we also have an mcp server/api endpoint if you dont want the ui

Backed by Y Combinator

Google

Exa

Corgi Insurance

Orchid

Lopus AI

Google

Exa

Corgi Insurance

Orchid

Lopus AI

why agnost

Your evals pass. Production still fails.

Agnost finds the missed failures in real conversations and turns them into fixes your team can review.

Google

“In collaboration with Agnost AI, we have integrated comprehensive observability features into MCP Toolbox for Databases.”

Exa

“Agnost AI is very useful in tracking analytics and error rates.”

Ishan GoswamiMember of Technical Staff, Exa

Corgi Insure

“Our Voice BDRs got meaningfully better at booking meetings once Agnost AI surfaced the patterns behind the conversations that actually converted.”

Ana Paula OlaizFounding GTM, Corgi Insure

1,247feature requests surfaced from user chats

“Agnost AI showed me users were asking for features we don't even have. I had no idea. All that feedback was just sitting inside conversations we already had.”

“Agnost AI is how we make our agents better. We see what to improve, ship it, and move faster. Simple as that.”

Lopus AI

16/18autonomous PRs merged

“Agnost AI spotted bugs buried in our agent's conversations and opened PRs to fix them overnight.”

Aamish Ahmad BegCo-Founder & CEO, Lopus AI

PRICING

Start free.
Scale when you're ready.

The earlier you start ingesting conversations, the smarter your agent gets, so connect today.

STARTER

Free

Intent & sentiment signal extraction
Automatic agent improvements
Failure detection & resolution
Natural language data queries
Up to 1,000 messages / mo
7-day data retention

Best for teams shipping agents that need to get better fast.

Start free

PRO

$499/mo

Everything in Starter
Up to 100,000 messages / mo
90-day data retention
Priority support
Founders Slack channel

Best for growing teams scaling agent volume without a sales call.

Start now

ENTERPRISE

Custom

Custom data retention
Audit logs
Custom SLAs & SLOs
Custom improvement workflows
Priority feature requests
Founders Slack channel
Unlimited time with the founders

Best for organizations running agents at scale.

Let's chat

frequently Asked Questions

Hacker Times

Hacker Times

Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations

Discussion

Discussion

Your evals pass. Production still fails.

Start free.
Scale when you're ready.

FAQ

Hacker Times

Hacker Times

Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations

Discussion

Discussion

Your evals pass. Production still fails.

Start free.Scale when you're ready.

FAQ

Start free.
Scale when you're ready.