ENGAGE ANTHUS
How an engagement works
Two ways to work with us, and both start with a conversation. Run our open-source solutions yourself, or have us build and run them with you in your AWS account. Your experts stay in the loop either way. You own and keep everything we build for you. Our solutions are open source and stay open. Integration code specific to your project is yours and private, and anything it depends on in our public projects stays public.
- Our team
- Stage done
We start with a pilot, score the result, and then decide what to build or stop.
01 / Two ways in
Open source, or built and run with you
Open source
The code is public on GitHub. Run it yourself.
Cyclotron, Chatticus, Papyrus and Primus are open source, and so are the technologies under them: Kanbus, Tactus, Biblicus and Auritus. Each solution has its own site with the repository and a quickstart.
We build and run it with you
We deploy it in your AWS account, integrate it with your systems, and operate it. Then we either keep running it with you or hand it off.
This covers all four solutions, and custom AI work that fits none of them. Tell us the problem and we start from there.
02 / Where we start
Three examples
These are shapes engagements often take. They aren’t a menu. Most real problems don’t fit one box, and we take on AI solutions work of any kind.
Classifier lab on Primus
We take a high-volume judgment call your team already makes (a score, a flag, a routing decision) and turn it into a classifier with confidence gating: the model handles the clear cases and routes the rest to your reviewers.
We’ve run this pattern for a call-center QA operation across years of production, hundreds of models, and millions of interactions, with expert feedback compounding into a data flywheel the whole time. You get that architecture, sized to your judgment task.
The loop itself is now open source as Cyclotron: a cyclotron is one AI decision that learns from your team’s corrections.
Factory-run software project
We build your software the way we build our own: work tracked as Kanbus issues in the repository, agents doing the implementation, and a human approval trail on every merge.
Anthus runs its own projects this way, including this site.
Newsroom for a publication
We stand up Papyrus as your editorial pipeline: stories move through Kanbus-governed stages from pitch to draft to published, with a human editor approving each move.
Anth.us runs its own newsroom on it, and the board is public, so you can read the record behind the newest articles before you buy the pipeline.
03 / Month one
What a first month produces
- A pilot with fixed scope
One judgment task, one project, or one publication track, scoped before we start. If you don’t know what you need yet, the first month is discovery, and it ends with a scoped proposal instead of a guess.
- A scorecard or a board you can inspect
The same record we use internally: accuracy by slice, issues moving through Kanbus, or stories moving through the editorial pipeline.
- A decision point
At the end of the month you have real evidence to decide whether to extend, expand, or stop.
04 / Month six
What month six looks like
Picture the same judgment task half a year in. Your reviewers still see cases, but only the ones the system can’t clear on its own, and that queue has been shrinking each month as the scorecard fills in. A correction one of them made in week two is now a written policy line the system applies every time.
When someone asks why a verdict changed, you open the record and point at the version, the numbers it cleared, and the person who approved it. Nothing runs on a guess, and nothing runs on us: the model, the pipeline, the board, and the record are yours.
05 / Tell us
Four things that help us reply
The form has one open question. Answer these four in it, in a line each. Rough answers are fine, and “I don’t know yet” is a real answer.
- Which solution or problem? Cyclotron, Chatticus, Papyrus, Primus, or the problem in your own words.
- Rough volume or scale. Decisions a month, documents, users, whatever fits.
- Do you have an AWS account? Yes or no. We work in yours.
- Timeline. When you need something real in front of your team.
PRESS START
Bring us the problem.
Tell us the problem, even if it’s half-formed, and we’ll scope the first month together. Anything you send goes through a short contact form.