Iterative refinement for everything

Kaizen with power tools

OnnAI offers a toolkit, methodology, and specialized AIs for automated iterative refinement. Its ecosystem of 30 composable tools lets you build custom refinement loops — a stochastic search across solution spaces powered by non-deterministic software. You define the standard. AI does the work. You can see how it got there.

# Define the standard. AI does the work. You can see how it got there.

> 8 times onn contract.md "tighten — close loopholes, remove ambiguity"

a2c3d4e  define "Deliverables" in section 1 — used but never defined
b4d5e6f  add limitation of liability cap tied to contract value
c6e7f8a  replace "reasonable efforts" with "commercially reasonable efforts"
d8f9a0b  add mutual indemnification clause — was one-sided
e0a1b2c  specify governing law and dispute resolution venue
f2b3c4d  clarify IP assignment — distinguish pre-existing from work product
DONE after 6 rounds
Seminar. Consulting. Software.

OnnAI teaches organizations how to use AI to build iterative refinement into their workflows — then gives them the tools to do it.

Seminar

Half-day and full-day sessions that teach the kaizen methodology. How to write personas, define loss functions, build loops, and review logs. For teams of 5 to 500. Remote or on-site.

Consulting

We build your first kaizen loops with you. We audit your document workflows, write the personas, configure the tools, and run pilot programs until your team owns the process.

Software License

The full toolkit — 30 tools that compose into custom kaizen loops for your domain. One license, your infrastructure, your data. macOS and Linux.

30 tools
Composable. Individually Testable.

Each Onnai tool does one thing. Composed through pipes. You edit plain text files, in English. No Python, no code.

onn
Intelligence

Composable AI. Cloud models, local models, and Onnai's specialized models, in any combination.

ito
Memory

Memory for AI. Intent-first, moments instead of commits. Why instead of what. Full tree snapshots, content-addressable. Undo, branch, search. So easy, even an AI can use it.

zen
Orchestration

A shell rebuilt for AI. No quoting nightmares, no $ expansion. times runs N iterations. while runs until completion. each maps over file sets. Built in RPN calculator.

squawk
Communication

Optimized messaging for kaizen coordination. Hash-chained audit log. Sockets locally, multicast on LAN, encrypted over the Internet. Build bots in one line.

Composition

Every kaizen loop is assembled from composable tools. Different domains, different pieces, different loops. The building is part of the engagement — we help you design the loops that fit your workflow.

Persona

The role, the standard, the review criteria. This is the loss function — it defines what "better" means for this document type.

You are a regulatory affairs specialist. Review against ICH E6(R3). One change per round. Read .context. DONE when submission-ready.
Tool Allowlist

Which commands onn can run. Minimal surface area. Enforced by the OS-level sandbox — onn proposes, the sandbox disposes.

ito cat grep wc squawk
Prompt

The optimization target for this run. Specific criteria that tell onn what dimension to improve along.

$ 10 times onn protocol.md "improve — ICH E6(R3), completeness, no ambiguity in endpoints"
How it got there

Every change logged with intent. Content-addressed. Immutable. The audit logs, review record, and revision history — all in one.

$ ito history
a3f912c define primary endpoint
b7e44d1 add stopping rules
c912fa3 clarify inclusion criteria
DONE after 3 rounds
Your models or ours

Onn talks to any model — our specialist AIs, cloud APIs, local inference, or any combination. We offer unified billing for organizations that want one vendor. For sensitive documents, run everything locally. Your data never leaves your machines.

Skills

Skills on demand

OnnAI's pre-built specialists you call by name. Editor, Writer, Auditor, Translator — an ever-growing library. Some are fine-tuned models, some are proprietary system prompts. No persona files to write. Billed as inference.

Cloud

Unified billing or BYOK

One invoice for all inference across your organization, or bring your own API keys. No per-seat LLM subscriptions, no surprise bills.

Local

On-premise inference

For regulated industries, classified environments, or anywhere data can't leave the building. Onn connects to local models — Llama, Mistral, Qwen, whatever you run. Same kaizen loops, zero network calls. We help you set it up.

One license. Everything included.
$2,995
Up to 8 users · macOS and Linux
All 30 tools — the full toolkit
Snap-together loop builder
Persona library over 40 templates
Cloud and local model support
Sandbox and audit pieces
Updates for 12 months
Priority support
Half-day Seminar (Silicon Valley)
Consulting Available
All tools are written in C · Zero bloat · No Python supply chain risk
Get started → hello@onnai.ai

Travel billed separately for on-site events. Volume licensing available.
Unified inference billing available as an add-on.

Kaizen for…

The same pattern applied to every domain where text artifacts are iteratively refined against a definition of "better."

Keep me in the loop

Product updates, new features, the occasional blog post. No spam.

Investor Deck

Enter your email to access the deck.