Selected work

Three systems, one content engine.

A public healthcare data platform needed a steady supply of trustworthy insights, publication-quality visuals, and constant quality control. Our principal led the platform's delivery and personally designed and built the three AI systems below. Identifying details are withheld; everything else is as-built.

Case study 01

Tessera: daily autonomous research for a public data platform

Autonomous agentsRetrieval & synthesisEditorial pipeline

The problem

A public data platform goes stale without a constant stream of new insights. Producing them normally means analysts spending hours a week scanning news, journals, and datasets for material, and that scanning is the first thing dropped when real work gets busy.

What we built

Tessera is an autonomous agent that scans the public web every day for emerging topics in healthcare and aging, filters them against the platform's editorial priorities, and drafts structured insight candidates: claim, evidence, sources, and a suggested visual. A human editor reviews and promotes; the agent never publishes on its own.

The result

A daily pipeline of vetted insight candidates feeding the platform's content calendar, with batch runs producing 15 publishable insights at a time. Daily scans since mid-July 2026 have captured more than 150 structured signals, every one carrying its provenance trail. The agent supports the process; every greenlight is a human call.

Daily

autonomous scans, on schedule, unattended

15

insights produced in a single batch run

100%

human-reviewed before anything publishes

Case study 02

Emblema: from written insight to finished infographic

Generative designBrand systemsSelf-serve tooling

The problem

Every insight worth publishing needs a visual, and every visual used to need a designer. The design queue became the bottleneck between "we know something" and "the public can see it."

What we built

Emblema takes a written insight and produces a branded, publication-ready infographic: correct typography, correct palette, correct data presentation, exportable for web and print. It's self-serve, so the person who found the insight can produce the visual, and the brand system is enforced by the tool rather than by review cycles. The five-color data palette was validated colorblind-safe before launch, and eight named styles cover the common insight shapes.

The result

The design bottleneck is gone from the publishing path. Visual output scales with the insight pipeline instead of with headcount, and every graphic that leaves the tool is already on-brand.

Zero

design-queue wait between insight and visual

8

infographic styles at launch

Self-serve

analysts produce finished graphics themselves

Case study 03

Sentinel: continuous QA for a live public platform

Automated QAContinuous monitoringMulti-audience reporting

The problem

A public platform spanning dozens of data products, articles, and interactive pages can break quietly: a data refresh shifts an axis, a link dies, a number stops matching its source. Manual spot-checking catches a fraction of it, late.

What we built

Sentinel audits the live platform against two other views of the truth: the production codebase and the canonical published data. Any disagreement becomes a tracked finding. It runs 46+ distinct checks across 8 suites, roughly 384 check instances per sweep, every weekday morning, and writes five audience-tailored reports: developers, data team, communications, design, and leadership.

The result

Defects surface in hours instead of whenever someone happens to click the right page. In its first sweeps it caught a public page returning a server error and a broken dollar figure inside a live calculator. Leadership gets a trustworthy quality signal; engineers get specific, reproducible tickets.

46+

automated checks in continuous operation

8

audit suites, from data accuracy to accessibility

5

audience-tailored reports from every run

The transferable part. Most organizations need the same three shapes: a research pipeline, a tool that removes a bottleneck, and a quality monitor. We build them against your workflows and your data.
Contact

Want one of these?

Tell us which workflow hurts. We'll tell you what the version for your organization looks like, what it costs, and how long it takes.

Email to book a call