Mike vs Comet Browser

“Self-hosted legal AI that runs on your own Claude or Gemini API key is genuinely clever — the pricing model alone makes this worth exploring. The codebase is clean and the tabular citation view is the kind of UX detail that shows someone actually thought about the legal workflow. Deploy this for any firm that's been priced out of Harvey.”

“Solo dev projects in legal tech carry serious liability risk — if the model hallucinates a clause or misses a citation, the consequences aren't a bad tweet, they're malpractice exposure. Until this has real-world usage data from actual attorneys and independent security audits, enterprise law firms should stay cautious. Also, Claude Sonnet or Gemini Flash are not the same as GPT-5.5 fine-tuned on case law.”

“The category here is AI browser agent, and the direct competitors are Arc with Browse, Chrome's built-in Gemini integration, and every Playwright-wrapper startup that launched in 2024. The specific scenario where Comet breaks: any website with a CAPTCHA, a bot-detection layer, or a dynamic login flow — which is most of the websites people actually need agents to navigate. My 12-month kill prediction: Google ships Gemini-native agentic browsing into Chrome for free and Comet's entire distribution thesis evaporates. To earn a ship, Comet needs to demonstrate a reliable task completion rate above 80% on a published, third-party benchmark — not a cherry-picked demo on a frictionless checkout flow.”

“Open-source legal AI is the first credible wedge against the Harvey monopoly on AI-native law. When every solo practitioner and boutique firm can deploy their own matter-scoped AI workspace for free, the power dynamic in legal tech shifts permanently. Mike is the kind of project that looks small today and reshapes an industry in five years.”

“The thesis Comet is betting on: within 3 years, the browser's primary interface is intent-driven rather than URL-driven, and the agent layer sits below the UI rather than on top of it as an extension. That's a falsifiable, specific bet — and it's one I think is roughly on time, not early. The second-order effect that matters here isn't faster form-filling; it's that Perplexity captures the session-level data that Google currently owns through Chrome, which fundamentally shifts who can build the best personal web model. The dependency that has to hold: agent reliability needs to hit a threshold where users trust it with consequential tasks, not just toy demos, and that threshold is further out than Perplexity's beta launch implies.”

“The tabular review UI is genuinely beautiful for a developer-built open source project — it solves the 'show your work' problem that makes lawyers distrust AI outputs. If the UX holds up under real document loads, this is the design template for AI tools in trust-sensitive industries.”

“The buyer here is unclear in a way that matters: is this a consumer product funded by attention and ads, or a prosumer tool with a subscription model? 'Free beta with pricing TBD' is not a business model, it's a deferral, and for a company that's already raised at a multi-billion valuation, that deferral is a red flag. The moat problem is real — Perplexity's agent layer is only as defensible as its model quality and browser telemetry, and Google can replicate both with Chrome's existing install base. What would need to change: a clear pricing architecture that shows users pay for task completion or saved time, not for a browser they'll abandon the moment Chrome ships the same capability.”

“The job-to-be-done is clean and singular: complete a web task I would otherwise have to do manually. That's a real job, and most tools in this space make users context-switch between a chat interface and a browser, which is exactly the friction Comet eliminates by collapsing them into one surface. The onboarding question I'd need answered before moving this to a strong ship: does a user reach a completed task in their first 2 minutes, or do they spend that time granting permissions and configuring agent scope? The opinion the product needs to have — and may not yet have — is which tasks it's opinionated about doing well versus which it declines, because an agent that attempts everything and fails unpredictably is worse than one that does three things reliably.”