Strategy Workspace BR60_03
Loaded
Ask Starling anything…
Pricing

Plug in a fully contextualized AI chief of staff.

Starling runs on your organization’s sovereign intelligence, so it reasons from your business instead of generic patterns.

Create Your Org Brain Seat 1, $99/mo.
What you get

Your memory, and everything it becomes.

1. Your Sovereign Repository.

Starling starts by provisioning a Notion workspace, where it writes your Constitutional Memories — the fifteen fundamentals every business needs to codify. Cancel and the repository remains yours. The First Fifteen give any advanced AI model the ability to extrapolate additional memory, so you stay because Starling works better for your team, not lock-in.

Constitutional Memory — your sovereign repository of First Fifteen fundamentals
Ask Starling anything — Smart OS chief of staff drawing from governed memory

2. Starling at Smart OS.

After establishing your Constitutional Memory, Smart OS activates and Starling becomes a model-agnostic AI chief of staff. It assembles context for session-based AI, helping you draft, decide, and plan with governed memory. Ask it anything about your business, and it keeps that context current as the work moves.

3. Starling with Smart Office.

With your foundation in place, Starling builds out your extended canon and architects your active work, so every project and campaign inherits the latest context. As work completes, Starling extracts the patterns, and your repository becomes a compounding asset.

Starling with Smart Office — projects and campaigns inheriting your governing strategy
What drives cost

Where your token usage actually goes.

Org Brain flowchart — Org Library, Workspace, and Resources

Translating between lossless memory and lossy documents.

Your Org Library is your memory repository — where all work originates. It stores lossless Markdown artifacts that minimize token usage. This means everyday strategic queries are covered by your seat cost under normal use.

Two Workspace operations convert your memory from/to the lossy documents that drive heavy token usage: Excavation parses uploaded context, and Delivery turns out the finished documents that leave the building.

Both live in a separate repository, Resources — uploads coming in, work going out. You spend on translation between lossless memory and lossy documents. Your memory stays light and governed.

How model selection works

Starling works with the best of every model: Claude for work, GPT for voice, and Gemini for deep analysis.
They draw from the same pool, each on its own meter. Costs are transparent in your settings.

Claude

Claude Work

Build canon, convert documents, run strategy and queries.

Meters by tokens.

GPT

GPT Voice

Talk to your brain, hands-free, for quick answers.

Meters by the minute.

Gemini

Gemini Analysis

A second-model pass when you want one.

Meters per run.

Create Your Org Brain
Seats & scale

Start with Seat 1. Invite your team.

Starling starts with a single seat — the Owner, who builds your Constitutional Memory. Once you define your canon, you can invite your team.

Every business needs a dataset for AI and somebody to administer it. Starling provides the standards, across four types of memory: System, Persistent, Active, and Learned.

System memories are what every organization runs on. Persistent memories rarely change. Active memories are the daily work. Learned memories are institutional wisdom.

Sovereign Repository — your Org Brain, governed at the root by the Owner
Why now

It stopped being hypothetical.

A leading AI lab had to pull its newest frontier models to comply with a government directive. Access only returned three weeks later.

The models weren’t the problem. The dependency was. When your workflow lives inside the AI, their compliance decision becomes your outage.

Starling holds your memory in a repository you own and reads it with whichever model is available — so no one provider stops your work. Governed memory produces better intelligence than AI memory: it stays current, it doesn’t drift, and every model reasons from the same truth.

A dependency tree whose single trunk branches down into a stack of nodes — one severed link collapses everything below it
Founding Members

Declare your data independence.

Starling — your Constitutional Memory speakable across models

Starling MX is early software. Onboarding works end to end and your repository is real and permanent from day one — but you’ll be among the first organizations through the door, and you’ll hit rough edges. In exchange you get direct access to the people building it, and your feedback shapes what ships next.

Complete onboarding and your Constitutional Memory is yours to keep, in a Notion workspace you own. Cancel any time and it stays yours.

Become a founding member Seat 1, $99/mo.
FAQs

What you need to know

What exactly is Starling?
An AI chief of staff that runs on your organization’s governed memory. It reasons from your business instead of generic patterns, and works on any model.
What does the $99/mo seat include?
A governed intelligence system built in your own Notion, plus everyday usage — querying, light edits, day-to-day strategy.
What is Constitutional Memory?
The First Fifteen foundational memories every organization needs to codify — your values, competitive position, business model, revenue strategy, product roadmap, brand, and core metrics. Once you define them, Starling can extrapolate additional memories.
How are excavation and delivery billed?
Everyday work comes with the seat. Excavation and delivery draw usage as you translate to/from lossy documents.
Do I keep it if I cancel?
Yes. Your Constitutional Memory lives in your own Notion and is yours to keep and run on any model.
Will my data be used to train a model?
Never. The AI reads your canon, reasons over it, and forgets.
Get Started

Put your intelligence
to work.

Create Your Org Brain