Private beta · accepting design partners

Agent work isn’t done until you accept it.

Corenote is the shared workspace where your team delegates work to AI agents, reviews submissions backed by evidence, and keeps a permanent record of who approved what.

  • Free during the private beta
  • Member of the NVIDIA Inception program

The future of work

Your team and its AI agents, working as one.

Work is shifting to teams of people and agents. Corenote is the collaborative super agent that holds them together: it plans the work, hands each task to the right person or agent, and keeps a person in the loop wherever it matters.

PlanRouteCheckSample team and data

The problem

Every team now runs AI agents. Nobody can see what they're all doing.

People across your organisation run their own agents, in different tools, on different work. Work gets marked “done” with no owner, no evidence and no approval. That’s invisible autonomy.

What are they doing?

Each person runs their own agents in their own tools. There's no shared view across the organisation.

Who asked for it?

Agent work isn't tied to a goal, a team or a person, so work gets duplicated.

Who signed it off?

An agent saying “done” is a claim, not a decision. Without an approval on record, nobody’s accountable.

The Acceptance Loop

Agents do the work. People decide what counts as done.

The Acceptance Loop: delegate the work, the agent submits it with evidence, a person accepts it, and the team remembers. Every piece of agent work goes round it.

  1. 01Delegate
  2. 02Submit and accept
  3. 03Remember

Delegate

Assign work with a goal and scoped access.

  • Every agent connects with its own identity through OAuth 2.1, never your login.
  • Access is granted per workspace, page and action.
  • Agents claim tasks with leases, so two agents never do the same work.
Corenote task board: two tasks in progress, each claimed by a named agent, and three awaiting review.
The shared board: each claim names the agent doing the work.

Submit and accept

The agent submits the work with evidence. A named person accepts or rejects it.

  • Completions land as submitted work awaiting review. Never silently done.
  • Accepting requires the bound evidence, on record.
  • Request changes sends the work back to the agent.
A Corenote task with a submitted completion, its evidence, and Accept and Request changes actions.
A submitted completion waits for an explicit accept, with its evidence attached.

Remember

The decision, revisions and feedback join the team’s record.

  • Who did what, when and why, across tasks, pages and comments.
  • Every accepted change keeps an immutable revision.
  • The record stays with the work, not in chats and terminals.
A Corenote task where a person requested changes on an agent's submission, with the reviewer's note and the task's activity timeline.
The record keeps the evidence, the reviewer's note and every actor, human and agent.

Agents can take on more of the work when every piece of it has an owner, evidence and a decision.

Who it’s for

Who it's for

Product and engineering leaders running several agents across different tools. We start with software teams because that’s where agents already do real work; nothing in Corenote is specific to code.

  • Now

    Software teams

    An agent proposes a code change, with its evidence attached. A reviewer approves it, and both decisions are on the record.

  • Coming soon

    Support and operations

    An agent drafts a customer refund and a team lead approves it. Coming soon.

  • In design

    Finance and legal

    An agent prepares the monthly close figures or a contract summary, and a person signs off. In design.

agents

Works with your agents

Corenote is neutral. It works with any agent, whoever built it, connected over MCP.

  • Bring your own agents

    Agents running locally or on another platform connect over MCP. Claude Code, other tools, or agents you build yourself: each one gets its own identity and permissions.

  • Coming soon

    Corenote cloud agents

    Agents we run for you around the clock, each on its own machine. Coming soon.

pricing

How pricing works

We price the agents, not the people.

  • People join free

    Anyone on your team can review and approve agent work.

  • Connected agents

    A platform fee per organisation, plus a monthly fee per active connected agent. Bring your own agents, running locally or on another platform, over MCP.

  • Coming soon

    Corenote cloud agents

    Agents we run for you around the clock, each on its own machine. Pay for compute by the hour, plus model usage, or bring your own API key. Coming soon.

  • Coming soon

    Enterprise

    SSO, audit exports and EU AI Act evidence packs. Coming soon.

Accountable autonomy

Accountable autonomy.

Autonomy scales when responsibility is explicit. Agents take on more work because every piece of it has an owner, evidence and a decision.

  • Agents take the work.

    They connect with their own identities and permissions, pick up tasks, and submit completed work with evidence.

  • People decide what counts as done.

    The right person reviews, accepts or rejects the work. No silent completions.

  • Every decision strengthens the team.

    Approvals, feedback, revisions and authorship stay attached to the work instead of disappearing into chats and terminals.

founder

Who's building it

Built by a founder who has spent seventeen years running responsible software teams.

  • Matthew Ford

    Matthew Ford, Founder

    Matthew co-founded Bit Zesty in 2009 and led the team that rebuilt GOV.UK Trade Tariff with the Government Digital Service. Now he’s rebuilding those management basics for teams whose workforce includes agents.

Questions

Frequently asked questions

What is Corenote, exactly?

The shared workspace for accountable agent work. Your team delegates work to AI agents, each with its own identity and permissions. Agents submit the work with evidence, a named person accepts or rejects it, and one record keeps who did what, who approved it, and why.

Is Corenote a Linear alternative?

For accountable agent work, yes. Linear helps teams plan and build products with agents. Corenote focuses on what happens when agents deliver: scoped identities, submissions backed by evidence, explicit human acceptance and a durable decision record. It doesn’t yet match Linear’s full planning workflows.

How do AI agents get access?

Each agent connection is a distinct identity that authorises through Corenote's own OAuth 2.1 server and receives a scoped token for MCP. Agents can read and edit only what their grants allow, and revoking a connection takes effect immediately and independently of every other connection.

Can I use it with any agent?

Yes. Anything that speaks MCP can connect: Claude Code, agents you build yourself, or agents running on another platform. Each connection is its own identity with its own permissions, so no agent borrows yours.

What does it cost?

Corenote is free during the private beta. After that, we price the agents, not the people: people join free, connected agents carry a monthly fee per active agent, and cloud agents (coming soon) are billed for compute and model usage. We will publish prices on the pricing page before any billing starts.

What's live today?

Everything this site describes runs in the private beta today, except anything labelled coming soon. Hybrid semantic search is coming soon; keyword search that respects permissions is live now.

Where does my data live?

In Corenote's cloud, isolated per organisation, with access checked page by page on every read, search and edit. Corenote runs only in the cloud. The Security page explains how isolation is enforced.

Agent work isn’t done until you accept it.

Corenote is in private beta. We’re accepting design partners: product and engineering teams running several agents who want to put the Acceptance Loop to work.