Discussion

See every request. Automate any workflow.

ksri: Related. We have several third party web apps in use. These apps don't expose a public api, but they are all single page web apps. We wanted to connect claude code to these web apps for our limited use case.We opened chrome, navigated the entire website, the downloaded the network tab as an har file. The asked claude to analyze and document the apis as an openapi json. Worked amazing.Next step - we wrote a small python script. On one side, this script implements stdio mcp. On the other side, it calls the Internal apis exposed by the 3rd party app. Only thing missing is the auth headers..This is the best part. When claude connects to the mcp, the mcp launches a playwright controlled browser and opens the target web apication. It detects if the user is logged in. Then it extracts the auth credentials using playwright, saves them to a local cache file and closes the browser. Then it accesses the apis directly - no browser needed thereafter.In about an hour worth of tokens with claude, we get a mcp server that works locally with each users credentials in a fairly reliable manner. We have been able to get this working in otherwise locked down corporate environments.

Barbing: ZatannaKampala (had to double check it wasn’t Harris)Just mulling these names over, how’d you come up with them?PS: clear value prop!

Sytten: Interesting product (Caido co-founder here). It is very hard to nail auth, probably the most underlooked aspect by end users. We are working on something similar for PoC reproduction of vulnerabilities.Fingerprinting is also a hard thing to match perfectly, I would be curious to know what your strategy is on that. My experience has been that unless you bundle multiple TLS lib it is almost impossible to do at 100% because none of the lib cover all the TLS extensions.

alexblackwell_: We’re currently running a variety of stuff for TLS/HTTP2. If you download you can see the full trace of the connection. We dump the TLS connection byte for byte with the different structured subsections. With tls.peet.ws and bogdann finn’s tls-client (which we use parts of with some modifications) I would say that http3/tcp fingerprinting is probably the remaining issue. We currently don’t support http3 connections (they’re niche + apple system proxy doesn’t support them well), and TCP fingerprinting is a bit too low level to build out tooling in GO currently. Possibly for a later release. Curious if you’ve tried bogdann finn/the existing tooling?

namanyayg: Smart! That's what I do as well for customers when they ask me to build a vibe coding layer on top of their SaaS platform.Takes very little time and tokens and I get to plug into their platform in seconds.

dataviz1000: I built the same thing as this just for websites. [0] I'm more interested in using Claude recursion to tune itself -- the agent writes itself, the agent -- than hacking websites. It is a good demonstration that 47 iterations of a recursive Claude agent writing itself to decompose any transport.I've tested it against YouTube, Twitch, Ticketmaster, and Yahoo Finance. It will detect any transport like JSON, WebSocket, GraphQL, SSE, Protbuf, UDP, WebRTC, ect.. It after 3 hours and some coaching succeeded in reverse engineering ChatGPT + Cloudflare Turnstile but I didn't merge that into it yet.It works by Claude using the Chrome DevTools Protocol (CDP) intercepting all traffic.[0] https://github.com/adam-s/intercept?tab=readme-ov-file#how-i...

namanyayg: Nice ty for sharing I was going to build something like this for a customer.I think just downloading all network traffic and giving it to claude code is the fastest and cheapest approach for 99% use cases.

lyime: [delayed]

madradavid: Congratulations on the launch.Totally unrelated, I am just curious about why you chose the name, as someone who is Ugandan and was born in raised in Kampala (which is the Capital City of Uganda BTW).Congratulations again.

iconicBark: I was caught off guard as well!!

alexblackwell_: It was the (generated) name of the Conductor workspace when I started the project. We were going to rename it before launch but the name stuck lol :)

alexblackwell_: Super cool. I think this is where most automation is heading . Would be curious if you could one-shot the auth flow using Kampala and completely ditch the browser. Also FWIW you can import HAR into Kampala and we have a few nice tools (like being able to a/b test payloads/replay requests) that meaningfully reduce integration time.

IMTDb: Congratulations.How do you handle SSL pinning ? Most of the apps I interact with have some sort of SSL pinning, which is the hard part to circumvent. I tried Kampala but got stuck at the usual place; as soon as I enable it, chatGPT stops working. Most of my iPhone apps stop responding etc.I would love to try using this tool to build an agent that can simply subscribe me to my gym lessons instead of me having to go on the horrible app. But even that relatively simple (iOS) app stopped working as soon as I enabled the proxy.

alexblackwell_: We’ve essentially been using that “recursion” to tune our agent. Having the agent build itself is not something I would have ever thought of though. Curious if you find it genuinely creates specific enough tools for it to be worth the setup time? I have a claude skill that takes in a chat and then offers tools/fixes to system prompt. Have found that + the anthropic harness engineering blogs to be super useful in making the agent actually do the work.

alexblackwell_: I’ve probably spent on the order of months of my life in proxyman/charles/burp/powhttp. All are great, but I’ve never been completely satisfied with the UX/features for building automations. As far as differences; we don’t modify TLS/HTTP2 connections, have a fully featured MCP (each UI action is an api action by definition), and have built more robust automation tooling in the app itself. The goal is to be an AI-native burp suite/powhttp with Proxyman-like UI.

alexblackwell_: Unfortunately we can’t do much around SSL pinning yet. Not sure how deep you want to go, but there are several Frida scripts that patch common pinning implementations.I also think mitmproxy (open source) has an option to spin up a virtual Android device that can bypass pinning via AVD. I have not tested how reliable it is though.FWIW, it could also be a cert trust issue. I would try a quick Safari search to confirm the cert is fully trusted. ChatGPT is pinned, but the gym app makes me think it might be a trust or config issue on your device.Happy to take a look as well. Email me at alex at zatanna dot ai.

telecuda: Congrats. You may want to consider dropping the "reverse engineer" language though, since most every application's ToS is clear on that being prohibited. Perhaps just "replay any application" or similar.

alexblackwell_: Yeah agreed this messaging is a bit confusing. Our focus is on helping people build automations, not do any mass-scale scraping.

5701652400: smeels like severe breach of ToS. virtually every single website and app mandates not to reverse engineer and not to temper with inner workings (including client-server networking).side note, YC25/YC26 batches have multiple startups that blantly violate ToS and sitting on a timebomb just pending a lawsuite and Cease and Desist Letters.

5701652400: guess time to move to gRPC and private encryption.

ghoshbishakh: Wireshark + some post processing?

peterabbitcook: It seems like it’s quite HTTP-centric (like most of the web…). I didn’t see anything on the page about this - can it also intercept / “reverse engineer” service calls that go over gRPC or WebSocket? I’m guessing at least a partial “yes” if the gRPC traffic uses grpc-web/Envoy?Seems like a great product, potentially quite powerful for automated testing of SPAs.

alexblackwell_: Yep we handle gRPC and websocket. gRPC is a bit sketch/hard to do because of the way the protocol is designed. FWIW not many sites implement gRPC (some google sites and spotify being the only two I can think of), and if they do they usually have decent APIs. Feel free to try and lmk if you have any issues!

5701652400: so how do you parse gRPC binary? unless you have proto definitions, it is blackbox and is totally unsuable, isn't it?

avaer: Automations are also often prohibited by TOS.

alexblackwell_: gRPC obscures the keys not the values. Enums and signed ints are sort of tricky, but the latter is just a mapping problem and the former can be figured out through some logical deduction. gRPC isn't designed to obscure request content, but for over the wire efficiency.

alexblackwell_: The goal is not to scrape sites en-masse, but to allow people to automate their existing workflows and actions that they perform already via a browser. I understand the concerns around this being unethical, and it's something I spent a lot of time thinking about when I worked on automations previously. I've written a decent amount about how I don't think that sneaker bots or ticket bots are ethical. I don't support mass scraping websites/making the web more inaccessible for others.I do have to push back on the ToS comments though. Automation is used daily by nearly all companies. RPA is a billion dollar industry. Browserbase raised at 300M valuation. Is using puppeteer to automate a form submission a violation of ToS? If so then why is using a screen reader not? Is it the intention? Why is hitting network requests directly different? I personally don't think that automation is unethical (as long as it is not affecting server capacity). I don't think the answer to the ethical problems in scraping is just not to automate at all. Open to disagreement here though.

teraflop: > Is using puppeteer to automate a form submission a violation of ToS? If so then why is using a screen reader not?Without taking a position on the ethics of automation, surely this isn't a serious question? Things that the ToS prohibits you from doing are ToS violations, and other things aren't.For instance, from AirBnb's terms of service: "Do not use bots, crawlers, scrapers, or other automated means to access or collect data or other content from or otherwise interact with the Airbnb Platform."There is no similar prohibition against using screen readers.

alexblackwell_: My broader point is that these ToS clauses are often so broad and vague that they're essentially unenforceable and not meaningful in practice. For example, "Do not use bots" covers a pretty substantial amount of ground, and intention isn't exactly something you can screen for. Is an autofill chrome extension a bot? If so what separates that autofill from accessibility extensions? Is someone using Whispr flow to fill forms considered a bot? AirBNB doesn't block Google's crawler. Why? A company can enforce its TOS as it wishes. My general point is that the waters are murky, and that automation is a sort of sliding scale.

ImPostingOnHN: > For instance, from AirBnb's terms of service: "Do not use bots, crawlers, scrapers, or other automated means to access or collect data or other content from or otherwise interact with the Airbnb Platform."> There is no similar prohibition against using screen readers.A screen reader uses automated means to access or collect data or other content from or otherwise interact with a platform.

doc_ick: This makes me want to never create a public service again.

alexblackwell_: Definitely get that. Being hammered by scrapers is a massive PITA (especially with latest aggressive AI crawlers). We focus primarily on allowing people to automate their existing workflows. For all hosted workflows we have rate limits to prevent mass scraping/affecting server workload in any real capacity. In fact, because we don't load js/html and hit endpoints directly I would guess that we consume less server resources in the end.

doc_ick: Oh no I’m not worried about the resources or rate limits.If I’d make a mobile app and users simply use your automation service instead of my mobile app, I’d lose traffic/money/motivation to improve it.If they run into issues from your service now it could make my app look bad while the error isn’t with the app.See tailwind for an example tale.

Sytten: We are in Rust so our options are more limited. Make sense the golang ecosystem is pretty good for that.

mil22: Ah yes, AirBnB, the company that famously hacked Craigslist to achieve viral growth by using a bot, crawler, scraper and definitely automated means to access and collect Craiglist's data and other content from and otherwise interact with the Craigslist platform.

theParadox42: I got banned from Hinge for reverse engineering their proxy and filtering through hundreds of profile per minute. The bot would auto filter 80%, and I could go through the last 20% as it goes, with a slick interface to view multiple profiles at once with keybindings.It’s pretty funny to see that in their demo video given it’s a blatant violation of their ToS.

jackjayd: 5 years ago I used a similar approach for one of GCPs internal APIs (I think they've since released a public API that covers the use case I had). Was a bit of a pain to do manually, so it's cool to see how trivial this has become for models now.

rexpop: Business is just what you can get away with, apparently.

lchengify: Very cool. I've also had to do multiple versions of something like this ... also for healthcare. I got very good at Sikuli and Charles Web Debugging proxy back in the day.

arjunchint: Hey Alex, we had similar thoughts at Retriever AI of moving from webpage interactions to reverse engineering the underlying APIs.Compared to your our approach, we are doing this entirely within a browser extension so meeting users where they already doing their existing work.Within the extension just record doing a task, we reverse engineer the APIs and write a script. Then execute the script from within the webpage so that auth/headers/tokens get automatically added.You can just prompt to reuse the tools at zero token cost.

kang: how does this work? for eg, how is it possible to even deduce bitcoin structure from rpc list?

alexblackwell_: sorry a bit confused on your question here. If you're asking about JSON RPC we handle this via parsing. The AI can then handle deducing structure most of the time given enough context

kang: ya, unless its very trivial, AI won't be able to "deduce the structure most of the time".

5701652400: so if API is published, there is nothing to reverse engineer.and if API is not published, and you MITM with self-compromised CAs, and then use it (commercially?) you ~100% breaking ToS.this is just un-ethical. or YC does not have regard anymore for such things?

ImPostingOnHN: Some people may believe in equal measure that intentionally trying to break interoperability is unethical. Especially if it's my data.

5701652400: show me one ToS for any major service that has "interoperability" in their clauses."interoperability" is never the case in the agreements.it is very stupid decision from business perspective. and unless legally required (like in agriculture or something, "right to repair"), no sane business will provide this to their customers.

jasonlotito: > this is just un-ethical.There is nothing unethical about this. You can technically do this with a browser and its dev tools.You being here is far more unethical than this app.

5701652400: > You being here is far more unethical than this app.how am I being far more un-ethical again?did I develop an AI tool to massively assit people breaking ToS and Copyright? (which is legaly punishable)

5701652400: > 300MFTX also raise lots of money. so did Terra/Luna. large valuation does not mean you cannot end up in life inprisonment for fraud.> Why is hitting network requests directly different?again. business publishes their official API. prohibit automatic and tool use in their ToC.you go pass that and access what they do not release publicly.this is borderline Copyright infringement, Trade Secrets theft, and violation of ToS.> others do itno they don't. "assisting screen reader" in ios. does not intercept MITM network traffic, attempts de-obfsucate, decrypt, bypass TLS and CAs with fake CA roots with intent to "udnerstand inner workings".this is very far from the "assisting user". you do not need that level of breaking into internals.and besides. if app really wants to assit user there are legitimate ways to do so, like accessibility labels in ios, exposed by app itself to OS. crucial point here - app already exposes it itself.I mean, if you get legal permission from business owner to run this tool and expose their API. sure, run whatever you want (as long as your ad-hoc contract allows). and if you cannot get this contract, you are clearly breaching use and going directly agains what business intended.you are not assisting any user here. you are trying to directly steal trade secrets to replicate their business.

chakintosh: This dropped just in time as I was building an app that could leverage this. Is it legal to reverse engineer an API and hit a website to extract data ? In the eyes of Apple's guidelines, they can nuke apps off the App Store if they detect you're using something like this to pull data without an official API

laxpri: cool . can you give me the link of the tool

laxpri: Interesting , I am curious how this gonna reverse engineer a perfect webapp that have many guards like captcha,cookies,auth.etcjust looking for what is USP(unique selling point) herehappy for you though if this actually works