HAQQ Legal AI on Mobile
Bringing legal understanding to anyone with a phone
916 followers
Bringing legal understanding to anyone with a phone
916 followers
We built HAQQ because understanding legal situations shouldn’t depend on who you know or whether you can afford to “just ask a lawyer.” Today, HAQQ Legal AI is available on mobile. Upload a contract. Ask a legal question. Get structured, jurisdiction-aware legal work with risk flags and exportable outputs. Not generic chat. Legal reasoning powered by Justinian®. Know exactly where you stand, wherever you are.
Lovable
Most AI tools optimize for answers.
Legal work requires structure.
When you ask a generic chatbot to analyze a contract, you get commentary.
When you use HAQQ, you get a formatted risk memo you can export.
We built HAQQ because legal drafting shouldn’t cost $300/hour for a first draft.
It should start structured.
Happy to answer anything today.
@stephane_boghossian Quick question on naming: your comment mentions JUST and Justinian, but the listing is HAQQ. Are these all the same product, or is JUST a specific feature? I genuinely wasn't sure after reading.
Lovable
@jared_salois Sorry Jared indeed error in typo here. We were going to name our app Just but we changed it recently and forgot to change my comment here - my bad - thanks for noticing !
@stephane_boghossian
Hey Stephanie, congrats on the launch! Genuine question, ow are you handling user questions right now, and has that been a pain yet or not really? Just trying to learn what's real this early. No worries if you're heads-down.
@stephane_boghossian When a contract includes a choice-of-law clause that points to a different jurisdiction than where the user actually operates — which jurisdiction’s law governs your risk analysis, and can you flag the delta between them when courts in the user’s location have historically overridden those clauses?
Lovable
@aafif82 Sharp one. Default is we run the analysis under the contract's stated choice-of-law clause — but we flag your operating jurisdiction as a second lens, because that's where you'd actually litigate. When local courts have a history of overriding the clause (consumer, employment, and data-protection contexts are the usual suspects), we surface that as an explicit risk delta rather than burying it. The goal is you see both, not one.
Loving the focus on lowering the barrier to entry for legal clarity. access to justice is a real mess for small teams and freelancers qq. how does it handle multi-language contracts? @stephane_boghossian
Lovable
that's right!@vikramp7470 Justinian can generate 30+ language contracts tapping into 80+ jurisdiction !
QApilot's CoWork
Lovable
@jsurendranathreddy Yes — contracts, ToS, privacy and refund policies are all in scope, and the analysis is jurisdiction-aware so it doesn't treat a US ToS like an EU one. Cross-border SaaS is exactly the messy case we built for. Curious which countries you're juggling — that's usually where the real divergence shows up.
The UX looks fantastic! I double down on @vikramp7470 , lower the barrier to entry for legal clarity is great.
What document types does it handle beyond PDF? Could I attach an xlsx for example?
Lovable
@vikramp7470 @daniellebe Thanks Daniel. Beyond PDF we handle Word, plain text and images today, and xlsx is on the near list — spreadsheets come up more than you'd think with deal terms and pricing schedules. Out of curiosity, what's the xlsx use case for you? Helps me prioritize.
@stephane_boghossian most Due Dilligence questions end up in xlsx files, and investments are priced in an xlsx (I would not expecte legal text in there, but for sure relevant context for the contract itself)
StartupBase
Everyone's tried to make a base LLM a lawyer. Everyone knows how that goes.
Jurisdiction-aware reasoning with risk flags is a different thing entirely. What does Justinian actually add on top of a base model?
Lovable
@attacomsian Fair skepticism — most "AI lawyer" demos are a base model with a system prompt. Justinian is the layer on top: jurisdiction-aware retrieval over real legal sources, a risk-flagging pass that's separate from generation, and grounding so answers cite something instead of confidently making it up. The model is the engine; the value is everything wrapped around it that keeps it from hallucinating a statute. Happy to go deeper. https://haqq.ai/justinian
Love seeing legal access pushed down to "anyone with a phone." I work in fraud/scam protection and the hardest part for victims is almost never the law itself — it's not knowing they have options, or being too ashamed to ask. Curious how you're handling the trust/accuracy bar on high-stakes questions where a wrong answer does real damage. Congrats on shipping.
Lovable
@peterdigitalis This is the part that keeps me up at night, honestly — your point about people not knowing they have options is spot on. We bias toward grounding answers in cited sources and flagging uncertainty instead of projecting false confidence, and we're explicit that it's a first read, not a substitute for counsel on high-stakes calls. Wrong answers do real damage; we'd rather say "here's what to check" than bluff. Appreciate you flagging it from the fraud side.
@stephane_boghossian That's exactly the right instinct — "here's what to check" beats a confident wrong answer every time, especially when someones already panicking. In fraud the shame is half the problem people don't ask until it's too late, so anything that lowers the bar to a first read without pretending to be the final word is genuinely useful. Grounding in cited sources and flagging uncertainty is the honest version of this. Congrats again on shipping.