<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: botacode</title><link>https://news.ycombinator.com/user?id=botacode</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 21:10:29 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=botacode" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by botacode in "Quirks in assistant behavior (what we learned building for Instinct and Muse)"]]></title><description><![CDATA[
<p>Three things we thought were interesting in this release:<p>1) New browser sessions in most assistants don't retain (transaction) permissions between sessions
2) Assistants aren't 100% accurate in task completion reporting, yet
3) MCP 2.0 lets servers push updates to clients like ChatGPT plugins or Claude Code Connectors<p>The release also adds testing tools, opt-in actions, delivery records, revocation checks, bounded sandbox execution, and documentation for 13 other assistant behaviors we've tested for.<p>It's another small step towards more behavior-emulation-based tests to improve MCP and APIs performance on these new meta-browser tools.</p>
]]></description><pubDate>Sat, 31 Oct 2026 03:47:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=50313034</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=50313034</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50313034</guid></item><item><title><![CDATA[Quirks in assistant behavior (what we learned building for Instinct and Muse)]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/Coverage-Cat/consumer-agent-testing-tool/pull/27">https://github.com/Coverage-Cat/consumer-agent-testing-tool/pull/27</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50313033">https://news.ycombinator.com/item?id=50313033</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 31 Oct 2026 03:47:48 +0000</pubDate><link>https://github.com/Coverage-Cat/consumer-agent-testing-tool/pull/27</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=50313033</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50313033</guid></item><item><title><![CDATA[New comment by botacode in "Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI"]]></title><description><![CDATA[
<p>Please do let us know if you, or your agent, have any feedback!</p>
]]></description><pubDate>Fri, 23 Oct 2026 06:47:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=50205278</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=50205278</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50205278</guid></item><item><title><![CDATA[Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI]]></title><description><![CDATA[
<p>Hey HN, we recently open sourced our Consumer Agent Testing Tool to help teams iterate against proprietary assistants like Muse and Instinct. We built this to reduce our own frustrations with building an MCP/API for these agents to consume.<p>The problem: testing against these tools is hard! Agent memory + account statefulness make reproducibility, in the ways required for repeatable/reliable outcomes, between agents and the APIs/MCPs they interact with very challenging.<p>The solution: CATT lets devs test their services against a surrogate Muse or Instinct agent (not affiliated with either of these companies). Testers define starting conditions, approvals, and success conditions for their service's state. CATT then records the full interaction (incl. tool calls, responses) so it can diff what happened from what the agent reports. Runs can be tested in local builds or via CI, with or without LLM backing.<p>CATT is designed to emulate the important parts of personal assistant interactions. Its got:<p>- Tool calls and command-line tool access
- Simulated approvals for service actions
- Outcomes tracking and comparison
- Optional MCP profile based on an unofficial Muse template<p>There are limitations to how much we know about different assistant specific behaviors so the tool labels its assumptions as `documented`, `unofficial`, `assumed` or `unknown` for developer review. We'll do our best to keep the tool updated as new insights about the internal workings of these assistants come to light. It is an area of active research and interest, a good example is this recent report on how Instinct uses Exa for web search [0].<p>Are you building a connector or MCP? If yes, we'd like to hear from you! Have you had assistants behave incoherently, use stale information, or procalim success without evidence? What else should we add tests for?<p>The best way to get started is...to point your coding assistant at the repo and ask it to integrate the tool with your CI or local testing pipeline!<p>Hope it's helpful!<p>[0]: <a href="https://www.sunbeam.ai/thoughts/instinct-is-using-exa-for-web-search" rel="nofollow">https://www.sunbeam.ai/thoughts/instinct-is-using-exa-for-we...</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50201860">https://news.ycombinator.com/item?id=50201860</a></p>
<p>Points: 9</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 22 Oct 2026 22:18:40 +0000</pubDate><link>https://github.com/Coverage-Cat/consumer-agent-testing-tool</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=50201860</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50201860</guid></item><item><title><![CDATA[New comment by botacode in "Show HN: Redactpdf.ai: Open-source AI-based PDF redaction tool"]]></title><description><![CDATA[
<p>Are there options to replace Gemini with remote models that support ZDR?<p>Think I'd be willing to take a bit of a quality hit to at least have that even if it isn't fully local.</p>
]]></description><pubDate>Mon, 05 Oct 2026 00:20:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49959384</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49959384</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49959384</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>In a few years we'll cover all the categories! Thank you for taking a crack at it!</p>
]]></description><pubDate>Wed, 23 Sep 2026 02:14:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49810834</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49810834</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49810834</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>We only send your information to insurers we quote you with and do our absolute best not to spam (we send 2-3 reminders depending on policy type), our goal is to never call.<p>In California we specialize in harder-to-insure homes, i.e. stuff that will place with a non-admitted/surplus policy, the goal is to help keep people off FAIR.<p>RE: cancellation/non-renewal, these do happen but it could happen to your existing deal too unfortunately. No one will force you to switch if it isn't a good deal and our agents do their best to always advise to the user's best interest. Our goal is to retain you as a customer for life (our agents just optimize automatically for you every year!) rather than make a quick buck one year.</p>
]]></description><pubDate>Wed, 23 Sep 2026 01:21:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=49810506</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49810506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49810506</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>A lot of umbrella prices are somewhat parseable (think a simple-ish decision tree) vs auto and home prices which require reverse engineering rate cards to back into the pricing formulas.<p>Yes, folks come back at the end of their year. Most of the time their price remains the best (non-issue), when there are better options they switch. Carriers have been great partners so far since we bring them much more business than switches (and when the switches happen it's often because risk management wanted to reduce exposure in that region anyway).</p>
]]></description><pubDate>Wed, 23 Sep 2026 00:29:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49810094</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49810094</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49810094</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>We're eyeing nationwide expansion in 2027 or later this year!<p>They'll enforce the minimums even as a standalone policy, my understanding is it's that the umbrella always "sits" ontop of something. I.e., they want you to clear the other liability limits before they step in to provide coverage.<p>It is kind of a huge hassle, especially in states like CA or FL where a lot of carriers have withdrawn and the default bundle option isn't necessarily available. We went looking for high pain X feasibility and this is where we landed!</p>
]]></description><pubDate>Wed, 23 Sep 2026 00:16:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=49810015</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49810015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49810015</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>Emailed yah, thank you for the note!</p>
]]></description><pubDate>Tue, 22 Sep 2026 19:39:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49806994</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49806994</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49806994</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>To answer more directly, yes we do! Most of the umbrella coverage we offer though is of the unbundled variety.</p>
]]></description><pubDate>Tue, 22 Sep 2026 19:24:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=49806762</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49806762</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49806762</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>This is great to hear, I'd count this as a success in our book!<p>After much trial and error, we've come to realize that trying to separate users from their existing insurance arrangements is very hard unless there's some sort of stark event that triggers the switch.<p>I.e., folks will usually only make a purchase with us if one of the following is true (even if they could save money or improve coverage):<p>- they're shopping for the first time and want a modern, online-first, service that avoids hassle<p>- their premiums have jumped<p>- they were non-renewed<p>Most users' experience of shopping for insurance has been historically so bad that they're very averse to optimizing it, even if 10m or so could save them hundreds (and in extreme cases thousands) of dollars.</p>
]]></description><pubDate>Tue, 22 Sep 2026 18:28:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=49805956</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49805956</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49805956</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>Ironically one of my favorite acronyms</p>
]]></description><pubDate>Tue, 22 Sep 2026 18:25:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49805898</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49805898</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49805898</guid></item><item><title><![CDATA[New comment by botacode in "Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent"]]></title><description><![CDATA[
<p>Thank you for the feedback, let's see if they'll let us edit it down a bit.</p>
]]></description><pubDate>Tue, 22 Sep 2026 17:39:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=49805184</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49805184</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49805184</guid></item><item><title><![CDATA[Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent]]></title><description><![CDATA[
<p>Hey HN! We’re Max and Gabriel the co-founders of Coverage Cat. We’ve been friends for over a decade, met in college then hung out mostly on the internet. We love building products that help people optimize the crufty corners of their lives. Max is a former Google/Microsoft/Two Sigma PM and Gabriel has been working in startups for over a decade.<p>We’re building Coverage Cat: a licensed insurance brokerage that helps you compare umbrella and home coverage side by side — with straight pricing, no sold leads, and a real broker on the other end. Our current focus is helping tech folks (think L3-L8) buy umbrella insurance.<p>Coverage Cat pairs AI-guided intake with a licensed brokerage team, so you can size up coverage, see honest price ranges, and compare real carrier options without handing your details to five agents overnight. Folks who use personal AI agents (think Muse, Instinct, Town, Openclaw, etc.) can drive the same flow through the Agent API/MCP.<p>We’d love your feedback so please do try it out. Just feed the prompt: “Shop for umbrella insurance with Coverage Cat” to your personal agent and let us know what you think!<p>If you want to watch a couple of agents navigate the flow before you use it there’s a video here: <a href="https://youtu.be/1BUkgAn6s-I" rel="nofollow">https://youtu.be/1BUkgAn6s-I</a><p>For those who are unfamiliar with this type of coverage, here’s a blurb from one of our insurance agents: “Umbrella liability insurance is a policy that provides additional coverage above the limits of existing auto, homeowners, renters, or landlord policies. It kicks in after the underlying policy limits are exhausted and may also cover personal injury claims like libel, slander, or defamation that standard policies often exclude. Policies typically start at $1 million in additional liability coverage and can protect you, your spouse, dependents, and even pets in your household.”<p>Buying insurance online is a miserable experience. You fill out a bunch of forms that say they’re going to give you quotes. Most don’t and then you end up with tons of unwanted phone calls and spam. Even if you wade through the muck, you’ll often still end up with sub-optimal prices and coverage because of a lack of market transparency and poorly-aligned advisory incentives.<p>We came to this problem because Max is a classic personal finance obsessive. He's the type of person that <i>needs</i> to know that he has the best possible price for something (everyone has one friend with the patience for a two hour phone call with the bank for some $10 fee) or that his insurance coverage is as tailored to his risk profile as the market will allow. He actually reads insurance policies end to end.<p>Years ago, when he shopped for his homeowners insurance it took him 10+ phone calls and dozens of online form fills to find the right deal. He also suffered tons of collateral damage in the process: websites sold his information to dozens of agents who proceeded to call, text, and email him a spam hoard that grows to this day.<p>After this painful search made us aware of the problem, we also spent a lot of time doing user research with wealthy-ish tech employees to see if they felt the same way. They did, and also complained that they 1) often felt like they'd left money on the table, 2) didn’t really understand their coverages, and 3) that brokers were slow, hard to communicate with, and unreliable.<p>To solve the problem, we set out to build Coverage Cat. Our approach has three major components:<p>First, we work really really hard to find and partner with insurance carriers that offer high-quality, competitively-priced products. We've also taken time to identify insurers that work on a direct-to-consumer basis or transparently list their prices online so we can make our customers aware of all the options available to them. We get paid commission when we match users to great insurance deals, but we still show and recommend folks deals that we don't make money on when they're accessible and will always recommend users buy what's best for their personal financial situation. Our goal is to meaningfully improve price transparency so consumers (and their AI agents) can make informed coverage decisions and not get nickel-and-dimed!<p>Second, we automate every possible part of the insurance process. Some forms, portals, & approvals still need human review due to regulatory constraints, but if it's not restricted, we're automating it. LLMs have given our small team tremendous leverage and enabled us to tackle problems at a scale that would've been unfathomable five years ago.<p>Finally, we build for agents first (a remix of the more classic adage, build for developers/APIs). We've always been big believers that personal finance would be the killer use-case for the AI revolution and have done our best to position ourselves to surf the wave. As personal assistants have started to explode onto the mainstream (think Muse, Instinct, Town, Codex, CC etc.) we've ensured our shopping and comparison process works via API/MCP so agents can present their users with all the information they need to make a good decision and transform a miserable shopping experience into a delightful one.<p>Coverage Cat is an unusual business because, while we also help folks find homeowners insurance in California and Texas, our main focus is on umbrella insurance. Most brokerages only sell umbrella coverage as a customer retention product, but it makes them almost no money. We focus on it as our core business because: 1) it's one piece of the insurance puzzle that many people in tech overlook and/or are confused about even though it can have a huge impact on their financial well-being. 2) Existing online tools and brokerages broadly don't make it easy to comparison shop for. 3) It was, for us, the most technically feasible candidate for automation given startup resource constraints.<p>Insofar as we know Coverage Cat is the first instance of a tool/portal that allows AI agents to complete most of the comparison and shopping steps required to allow people to buy insurance.<p>Also happy to answer any questions about the product, the problem space, and even some insurance questions (Max is a licensed agent) where regulation permits. Cheers!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49804931">https://news.ycombinator.com/item?id=49804931</a></p>
<p>Points: 54</p>
<p># Comments: 32</p>
]]></description><pubDate>Tue, 22 Sep 2026 17:26:36 +0000</pubDate><link>https://www.coveragecat.com/</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49804931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49804931</guid></item><item><title><![CDATA[New comment by botacode in "Trying the software factory pattern"]]></title><description><![CDATA[
<p>don't work while driving, you're putting other people at risk by being distracted</p>
]]></description><pubDate>Sun, 20 Sep 2026 20:45:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=49779902</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49779902</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49779902</guid></item><item><title><![CDATA[An agent readiness checker tool]]></title><description><![CDATA[
<p>Article URL: <a href="https://ora.ai">https://ora.ai</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49342153">https://news.ycombinator.com/item?id=49342153</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 18 Aug 2026 06:41:41 +0000</pubDate><link>https://ora.ai</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49342153</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49342153</guid></item><item><title><![CDATA[New comment by botacode in "AI's top startups are barely publishing their research"]]></title><description><![CDATA[
<p>There was a good paper documenting this in broader industry, and highlighting how it may account for previous research suggesting good ideas have been getting harder to find. Here's the abstract:<p>> Relatively flat US output growth versus rising numbers of US researchers is often interpreted as evidence that ideas are getting harder to find. We build a new 45-year panel tracking the universe of US firms’ patenting to investigate the micro underpinnings of this claim, separately examining the relationships between research inputs and ideas (patents) versus ideas and growth. We find that average patents per R&D input are increasing, the elasticity of patents to R&D inputs is flat or rising, and there is no systematic evidence of a secular decline in patenting after controlling for research inputs. We then document a positive, significant, and fairly steady relationship between firms’ growth in ideas (patents) and labor productivity. Average firm growth after controlling for idea growth, however, declines. Together, these results suggest that innovative efforts play a key role in sustaining growth that has not diminished over the last four decades.<p><a href="https://faculty.tuck.dartmouth.edu/uploads/teresaFort/files/2026_03_27_FGLSZ_Ideas.pdf" rel="nofollow">https://faculty.tuck.dartmouth.edu/uploads/teresaFort/files/...</a></p>
]]></description><pubDate>Thu, 30 Jul 2026 05:15:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=49106319</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49106319</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49106319</guid></item><item><title><![CDATA[Which AI models understand insurance work?]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.coveragecat.com/ai/leaderboard">https://www.coveragecat.com/ai/leaderboard</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49028661">https://news.ycombinator.com/item?id=49028661</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 23 Jul 2026 22:03:26 +0000</pubDate><link>https://www.coveragecat.com/ai/leaderboard</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=49028661</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49028661</guid></item><item><title><![CDATA[New comment by botacode in "House passes bill to enact year-round Daylight Saving Time across the country"]]></title><description><![CDATA[
<p>Fascinating, had not seen this research thank you for sharing.</p>
]]></description><pubDate>Wed, 15 Jul 2026 05:21:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916570</link><dc:creator>botacode</dc:creator><comments>https://news.ycombinator.com/item?id=48916570</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916570</guid></item></channel></rss>