What we build,
and what it solves for you
Legalcomplex builds and runs its own products for legal research and legal tech market intelligence. The design and engineering behind them is available to your team.
Products
Each one links straight at the running thing, not at a page about it.
Monocle
Invited pilotResearch you can check. Every answer is grounded in official sources and links back to the passage it rests on, and when the source is silent it says so rather than filling the gap. Legal and market research in one workspace.
Global Tax and Compliance
Opens 22 SeptemberOne search where the statute book is a different national site per country. Tax, compliance and the wider law across eight jurisdictions with full search, legislation and case law cross-linked, and a coverage directory for 236 more.
Spark
LiveWho raised what, and who bought whom, without assembling it from press releases. Fifteen years of funding rounds and M&A across more than 31,900 tracked companies, kept current by a daily sync. Two surfaces over one dataset.
Sabaio Private Intelligence
WaitlistUse AI without your data leaving your domain. A single secure gateway to every interaction with a model, for regulated enterprises, law firms and government entities that cannot put a document on somebody else's server.
Sabaio Contracts
In developmentVerify a business once instead of at every counter. The contract is the core object, e-sign is the way in, and the identity check behind it is reusable at banks, lawyers and government. Suriname first.
MCP connector
LiveThe market data where you already work, rather than in another tab. Six tools over one protocol, putting Spark inside your own AI client: Claude, Cursor and anything else that speaks MCP.
Design and Engineering
A monthly engagement for teams building AI into legal, tax and regulated work. Not an agency and not a generalist consultancy: someone who has built, shipped and verified in this market, working on your product.
Product design
Interfaces for work that has to be checkable. Design canvases, behaviour prototypes that run without a model call, and a component library the shipping code actually uses.
Engineering
Architecture, retrieval, AI integration and the plumbing underneath: adapters per jurisdiction, schema migrations against a live writer, deploys that roll back on their own.
Verification
The part most AI work skips. Evals that fail both ways, registries gated on a committed run, and checks designed so that an absent input can never read as a pass. It is also why Monocle retrieves instead of recalling: the S3 benchmark sweeps 2,716 citation statements past a model with no sources attached, and every model tested lands within a couple of points of chance.
See the benchmark results →Market intelligence
Roadmap decisions grounded in the Spark dataset rather than in anecdote: who raised, who bought whom, which segments are actually funded.
Work samples
All of it is live and public, so you can check any claim on this page against the thing itself.
Global Tax and Compliance
One search across tax, compliance and the wider statute book, answering from the official sources rather than from memory.
- 8 jurisdictions, a separate adapter behind each
- Legislation and case law in two lanes that cross-link
- A coverage directory for 236 jurisdictions
- A lane that failed says so, instead of reading as no law
Monocle Studio and Playground
The design system behind Monocle, and a prototype you can drive end to end without spending a token.
- A design canvas for the omnibox and canvas windows
- A prototype that runs the whole flow with no model call
- Every label read verbatim off the shipping code
- Timings and placements exportable as a spec
Spark, dataset to dashboard
A curated dataset of who funded, bought and built in legal tech, served as a dashboard anyone can read.
- Fifteen years of funding rounds and M&A
- Kept current by a daily sync from the source dataset
- Quarterly funding, rounds and M&A, split by segment
- Dashboard and directory read one mirror, so they cannot disagree
The company directory
Thirty-one thousand company profiles, built to be found and to stay findable.
- More than 31,900 profiles, each on a permanent URL
- Slugs that survive a company being renamed
- An equal-area world map drawn from the data, not a map library
- Carries most of the site's organic search traffic
Legalcomplex.com
The site is its own sample: everything here ships through the pipeline it describes.
- Continuous deploys with an automatic rollback
- A health endpoint that reports the commit actually running
- Content in Postgres with an editor over it
- A regression suite that asserts what pages say, not just that they answered
Government work
Public-sector engagements where the same discipline applies: definitions that hold, and a structure someone else can still run after we leave.
Belastingdienst
The Metadata Project: a metadata library of more than 8,000 definitions, a model browser to navigate it, and the guide and governance that keep it usable after delivery.
Read about the project →How we work
Engagements are limited, so each one gets real attention. Scope and rate are agreed per engagement.
- 1ApplyA short note about what you are building and what you need. No form and no lengthy intake.
- 2AssessmentA conversation about your stack, roadmap and goals. We agree scope and expectations.
- 3ProposalA one page proposal: tier, rate, duration, and what we work on first.
- 4RetainerTracked hours and a session log through the client portal, so you always know how the hours went.
Ready to talk?
Tell us what you are building and where it is stuck. If it is not a fit we will say so quickly.
Apply for an engagement