[HN Gopher] Launch HN: Opusense (YC X25) - AI assistant for cons...
___________________________________________________________________
Launch HN: Opusense (YC X25) - AI assistant for construction
inspectors on site
Hi HN, we're Roya and Michael, co-founders of Opusense AI
(https://www.opusense.com/), a tool to help engineers and
consultants automatically generate construction site reports from
typed or voice notes, plus photos. Here's a video:
https://www.youtube.com/watch?v=u3Pi1iih1_Y. Before this, I (Roya)
worked in human-machine interaction at Huawei, and before that as a
construction site inspector for civil engineering firms. I have a
PhD in Civil Engineering, and in my experience reporting was by far
the most tedious and mind-numbing part of the job. You'd walk
around a site all day taking short notes (maybe, often you'd rely
on memory) and snapping photos, then go to three more sites before
finally making it back to the office and try to remember everything
you wanted to write. Sometimes you'd fill in gaps from memory or
you'd keep it purposefully vague. Reports had to be consistent,
branded, and checked by senior engineers. It was a huge time sink
across the team. Writing reports was the worst part of the job, so
we built Opusense to get rid of it. On-site, users type or dictate
short notes (e.g. "rebar exposed east end of slab"), and the tool
turns them into full sentences, paragraphs, tables, or photo
captions in a report template that matches the firm's format. You
can work offline, and it syncs automatically when back online.
Most inspection and reporting tools are built for checklist-style
workflows (which is great for home inspections or punch lists), but
civil, structural, environmental, or geotechnical engineers usually
need freeform notes, not radio buttons. This is a particularly
good fit for LLMs because engineering field reports live in a
constrained, conventional domain: similar language, repeated
structures, and highly standardized content across firms and
projects. There's a lot of redundancy and grunt work, summarizing
the same site conditions, formatting repetitive data, translating
field notes into polished paragraphs, all of which LLMs handle well
with the right prompting and guardrails. We're not generating
arbitrary prose; we're transforming structured inputs (notes,
images, forms) into structured outputs, with firm-defined templates
and required fields that minimize the risk of hallucination. When
facts matter (e.g. test results or measurements), we keep them
grounded in the user's input, the model doesn't invent data because
there's nothing for it to invent. This makes it one of those cases
where LLMs aren't just a novelty, they're genuinely the best tool
for the job. Under the hood, we use a combination of prompt-
engineered LLMs and firm-specific formatting rules to get outputs
that don't just sound good, but also look right. We've recently
added translation features, and we're iterating quickly based on
field feedback. We charge per seat and are deployed at mid size
firms, and trialing with some multinational engineering firms who
have thousands of reports to file each week. We're also starting to
see interest from construction managers and developers who do their
own internal QA reporting. We don't have a self-serve way to try
out the product yet, because the way our business works requires
templates to be customized by company. But there's a demo at
https://www.youtube.com/watch?v=u3Pi1iih1_Y, and if you want to
poke around the UI yourself, here's a sample account to log in
with: login: hndemo@opusense.com password:
OpusenseHacker2025 The app is available for download on the
Apple and Google Play stores. When sample reports are generated,
you can log into the web interface to also view them online through
our website (www.opusense.com) with the same login credentials.
We'd love to hear how others are thinking about tools for field
work, reporting, or similar workflows (engineering, architectural,
etc.). If you've built in this space, or have thoughts on how to
improve it, we're all ears!
Author : rcody
Score : 28 points
Date : 2025-05-20 15:35 UTC (7 hours ago)
| swyx wrote:
| congrats on launch! reminds me of trunk.tools
| https://www.youtube.com/watch?v=L0kBWyziFlc and i'm not too deep
| in this industry but maybe talking to them might help.
| rcody wrote:
| Yes definitely relevant, thanks for the share!
| GuinansEyebrows wrote:
| My brain is having a hard time not "unscrambling" the product
| name to 'opensuse' :)
| jdwithit wrote:
| lol this is exactly what I came here to say. To be fair, it is
| probably not a brand that's top of mind for "construction
| inspectors" so probably won't cause much confusion within their
| intended audience.
| dughnut wrote:
| I am an engineer at an AEC firm you would probably recognize. I
| think there are a few competing products in this space. Owners
| don't care how you do CEI or have their own absurd rituals
| pioneered in the 60s or 80s. DOTs are the worst offenders and
| their project delivery practices are largely 80+ years old.
|
| My unsolicited advice is I would expect Owner-side administrators
| (IT people) to direct sales decisions, and they don't care about
| users or working products. I have only ever met one CTO in the
| AEC space who even considered end user benefit. Unfortunately,
| this means your product quality and utility is not actually
| important as evidenced by the whole Bentley product line, but
| integration with existing products is. Nobody seems to make big
| money in tech for white-collar AEC unless Bentley or Autodesk buy
| your IP. Then they will crudely bolt it onto their garbage
| software and their missionaries embedded in large companies
| disguised as technologists and CAD managers will sell it.
|
| My opinion is con-tech is totally broken for very complicated
| reasons with the private market (commercial architecture) being
| the only small voice of sanity since they compete on price
| sometimes.
| michaelbacani wrote:
| I appreciate your perspective, and while I agree that owners
| often drive sales decisions, I have to disagree on the idea
| that they don't care how inspections are performed.
|
| In our experience, owners do care because inspection practices
| directly affect the quality, consistency, and timeliness of the
| final reports delivered to their clients. These reports
| significantly influence client satisfaction and future business
| decisions.
|
| We've spoken with end clients who receive these inspection
| reports, and they consistently tell us that the quality of the
| documentation plays a major role in their choice of consulting
| partner. So while integration with existing systems is
| critical, we also believe strongly that the usability and
| quality of the product matter, because they shape the company's
| external image.
| neilv wrote:
| > _You'd walk around a site all day taking short notes (maybe,
| often you 'd rely on memory) and snapping photos, then go to
| three more sites before finally making it back to the office and
| try to remember everything you wanted to write. Sometimes you'd
| fill in gaps from memory [...]_
|
| How are the gaps getting filled in by AI?
| rcody wrote:
| What I meant was that they often don't take notes in the moment
| because they don't have a designated place to do so, and they'd
| end up having to sit down and write everything up later anyway.
| But with Opusense, they can quickly jot down short notes (voice
| or written) directly in the app, and there's no need to write
| anything afterward.
| neilv wrote:
| Thanks, I'm having a little trouble understanding the gap
| between quick notes and the AI-generated full report.
|
| I worked on safety reporting in another domain, and in that
| domain, I can't immediately think of how AI could fill in the
| gaps from notes safely. Every detail of observation,
| interpretation, and suggestion mattered.
|
| Maybe what you're doing with the construction domain reports
| is different, or you have found the right line for what you
| do and don't do?
|
| For example, are you only generating boilerplate parts that
| fabricate zero observation information? Say, if the note is
| "rebar exposed, south wall", then that becomes a sentence
| without anything added, and the rest of the paragraph is
| copied verbatim from professional standards about what this
| means?
|
| Or maybe there is potential for the AI to do harm (e.g., an
| LLM component hallucinates a typical description of exposed
| rebar, that adds or subtracts some important fact), but you
| trust the engineer to read closely and catch that every time
| before they stamp (rather than "rubber-stamp").
| neilv wrote:
| Constructive (ha) tone intended: How do you address the liability
| risk to your business?
|
| What happens if your product is involved in a fatal or very
| expensive construction incident or situation?
|
| What happens if your product is involved in a PE going to jail?
|
| One conventional startup possibility is that the startup shuts
| down, and its people move on to new startups and other
| employment. But I'm wondering whether that's different for
| startups that involve regulated safety-critical work.
| rcody wrote:
| This is a great question. We make it clear to clients that
| they're responsible for reviewing the report prior to it being
| sent out, as it ultimately carries their professional stamp.
| While Opusense streamlines the workflow and facilitates report
| writing, the final liability rests with them and so a thorough
| review prior to signing is essential.
|
| What we're really doing is shifting the process from spending
| an hour (or several, depending on the department) writing a
| report, to just a few minutes reviewing a completed draft.
| neilv wrote:
| It'll be interesting to see how different fields (outside
| tech) respond to taking responsibility for checking AI-
| generated artifacts, and signing off.
|
| In some domains, people will just rubber-stamp, but I would
| guess that some roles within civil engineering, aerospace
| engineering, etc., would remain very serious about their
| signoff responsibility, for at least a generation.
| dpass89 wrote:
| If it doesn't work out, in the construction industry, please
| contact me so we can discuss a possible industry/niche pivot.
| There is potential in a space I work in for a product like this.
___________________________________________________________________
(page generated 2025-05-20 23:00 UTC)