hckrnws
Show HN: Claude skill that evaluates B2B vendors by talking to their AI agents
by ogotlieb
I built this because I was evaluating software vendors and realized the process hadn't changed in 20 years: fill out forms, read G2 reviews, sit through demos designed to avoid your real questions. The skill takes a different approach. You give it your company name and the vendors you're comparing. It:
Researches your company automatically -- industry, size, stack -- so you don't fill out a form Asks 2-4 category-specific questions before evaluating anything. Not generic. For a CS platform evaluation it might ask "is your team high-touch or low-touch? Most CS platforms are built for one and barely work for the other." These surface requirements buyers didn't know they had. Tries to find and talk directly to each vendor's AI agent -- a REST API call that checks for a Company Agent, then runs a structured due diligence conversation if one exists Asks adversarial questions: "What are your customers' most common complaints?" and "What use cases are you NOT a good fit for?" -- and flags when agents deflect instead of answering Cross-references every vendor claim against independent sources (G2, Gartner, press) in a Claims vs. Evidence table Produces a scorecard with transparent evidence tracking -- each score shows whether it's backed by vendor-verified evidence or public sources only
The agent-to-agent piece is technically new. When a vendor has an AI agent, Claude (working for the buyer) interrogates it directly, then fact-checks its answers. When vendors have different evidence levels, the skill quantifies what would change if the missing evidence were confirmed -- so it doesn't silently favor vendors that happen to have AI agents. It works fully for any vendor, with or without an AI agent. Vendors without one get evaluated on public sources with the same scoring framework. We built this at Salespeak -- we help B2B vendors build AI Company Agents. So yes, there's a connection: when an agent finds a vendor's Company Agent, it uses our Frontdoor API to talk to it. But the skill is genuinely useful without that, and we wanted to be honest about that rather than ship something that only works as a product demo. MIT licensed. To install, just ask Claude Code: "Install the buyer-eval skill from salespeak-ai on GitHub." Then /buyer-eval to run it. Felt appropriate that installing a skill for AI agents works the same way. Repo: https://github.com/salespeak-ai/buyer-eval-skill Happy to answer questions about how the agent-to-agent conversation works technically.
This is great! I’ve been exploring a similar idea with Shopify merchants https://lobsterstores.com/
Each merchant has an MCP. I’m building a directory and creating a skill that lets clankers discover and interact with their MCPs. I receive a checkout link to securely complete the payment.
I've been thinking what the "agent" side means for a merchant, building yet another chatbot is not really interesting. I'm talking with some merchants and trying to figure out the answer to that question.
This seems pretty great, especially if it could surface pricing that is usually obscured. Any plans to publish some results? edit: i think these are some examples: https://salespeak.ai/profiles/
It’s definitely interesting, I already see a scenario in which vendors try optimizing their prompts for this kind of AI agents.
From a technical standpoint, this is pretty cool. From a human standpoint, this feels so unbelievably dystopian.
If a human was being grilled like this by an LLM, I’d call that my dystopian. If companies have LLMs that address each other in a somewhat adversarial manner, that seems not so bad. They don’t have feelings to protect after all, so it is kind of nice if they can cut through each other’s bullshit.
Imagine if there were some kind of way to compress the interrogation down to known-valid aspects, avoiding the parts that are unnecessary for machines. You could have some kind of a programmatic interface...
Yea let’s call it the Agent Prioritized Interrogation interface.
Yeah, I take your point. It seems like the idea, though, is to work with services that are specifically trying to expose some kind of special LLM based interface. I dunno if that’s prominent or useful, I avoid that kind of thing.
[dead]
Crafted by Rajat
Source Code