Auditober 2026
Get into your sandbox, build your entry and send it in. The walkthroughs below show each step.
In the app: workflows and evidence flows.
Built externally: dashboards using MCP data, and plugins extending our existing plugins.
Submit by
Cutoff time and timezone
to be confirmed.
You can enter multiple categories.
No category needed in your email.
Join with your work email on the Auditober signup page. Signup joins the update list; your invitation gives you sandbox access. You need the invitation and a web browser. To enter the event, email your submission files.
Your sandbox has two parts. The app holds your team's copy of the Bluth Company audit data. The Swarm agent is an AI assistant that works in the app for you. Use only mock data; keep your organization's data out of the sandbox.
Each team shares a $50 Swarm agent allowance across the event, subject to a daily limit. See AI allowance. Your own AI agent is optional; its provider's account requirements, usage limits and charges apply separately.
Awards are for practitioners working in an organization's internal audit function, according to the event page. Full eligibility rules have not yet been published. Ask the organizers if you are unsure whether you qualify.
Clips marked Illustration show an example setup or conversation.
The icons across the top take you to Dashboards, one page for each kind of record (risks, controls, issues, policies and the rest), My Items, Templates, Time and Admin. Hover over an icon to see its name. The bee logo at the top left opens the Activity Hub, where the agent's suggestions wait for you. Every record has its own page, and you can share any page's link with your team.
Everyone who signed up from the same company is on one team. People given accounts for the event start as admins; teammates you add later can be Users or Admins. As an admin, you can see and change everything your teammates build. People who signed up with a personal email address each get a team of their own. To see who is on your team, click the Admin icon (the last one in the top bar), then User Permissions.
Other teams cannot browse your sandbox. Check your submission files and linked workflows for private data before sharing them. Review the submission checklist before emailing your entry.
Conversations with the agent are recorded so we can improve the product, and the AssureSwarm team can read them. The chat shows a notice when recording is on.
My Work lists the workflow steps assigned to you and the ones ready to start. It is the first place to look when you come back to the sandbox.
Open any risk, control, issue or policy to see its fields, its linked records, its documents and the workflows that run on it. Click a title or a field to edit it in place.
Every team starts with the same fictional company, so entries can be compared fairly. Your copy holds 744 records: 200 risks, 200 controls, 129 compliance requirements, 53 processes, 47 policies, 28 issues, 18 remediations, 20 financial statement line items, 16 people, 14 systems, 10 models and 9 audits. They are joined by 2,223 links and worked on by 50 workflow templates with 236 runs in progress or complete.
Change anything you like. Your edits stay in your team.
These eight ideas explain the records, workflows and agents you will use in your sandbox.
Every record is an item: a risk, a control, an issue, a policy, an audit. Each item type has its own fields, set by the team's admins. An admin can add a field or a new item type.
See Create or change a record for the steps.
A workflow is a piece of audit work written down as steps, so agents and auditors run it the same way every time. You define it once as a template, then start a run of it on an item, such as a walkthrough on a process. Each step has instructions, a result that records what was done, and approvers who sign it off. An approved step locks.
A step can send a form to someone who is not running the workflow, such as a control owner who has to answer three questions. Use a form only for information you cannot get any other way. The person running the step writes their work in the step result, and sign-off is the step's approval.
Items link to each other: a risk to the controls that address it, a control to the process it sits in, an issue to the control that failed. Steps link to the items they test. These links are what let a dashboard answer which processes have no tested controls?
The Universe dashboard draws every item and link as one graph. Pick an item to focus on it and see what sits one or two links away, such as every control, workflow and issue connected to one process.
The app has 19 built-in dashboards, all filled from your team's data: Universe, Org Chart, Executive, Operational, My Work, AI Activity, Capacity Monitoring, Workflow Runs, Risks, Third-Party Risk, Policy Lifecycle, Policy Exceptions, Audit Plan, Model Inventory, Issues and Remediations, RCM, Compliance Requirements, SOX Program and Workflow Coverage.
For your Auditober dashboard entry, build an HTML dashboard outside the app, using data from the AssureSwarm MCP. See what to build and which files to submit.
Agents never change your records directly. Everything an agent wants to do arrives as a suggestion in the Activity Hub, which opens from the bee logo at the top left. Click a suggestion to see each proposed change marked on the page, then approve or reject each change with the check or the X, or all of them at once. Nothing is saved until you do. The AI Activity dashboard shows every suggestion and what happened to it.
The Model Context Protocol (MCP) is the standard way an AI agent connects to an outside system. AssureSwarm is built on it. The Swarm agent uses MCP to work in your sandbox, and you can connect Claude, Codex, Muse or a Copilot Studio agent the same way. Every agent has only the access of the person who signed it in, and its changes go through the same suggestion review.
Use Bring your own agent below for the connection steps and troubleshooting.
You can do each task by hand in the app or ask the agent to do it. Switch between the two with the buttons on each task. Copy a prompt into the agent chat and replace any details in square brackets. Review the agent’s suggestions in the Activity Hub: open it with the bee logo at the top left, then approve or reject them (see Suggestions and review).
By hand
To change a record, open it. Click the title to rename it, or click the description to edit it. Every other field is in the Details card on the right: click a field, change it, and click Save changes. Click All n fields to see the ones that are hidden.
With the agent
Create a new risk called “Vendor invoices are paid twice” for the Accounts Payable process.
Rename the risk “Vendor invoices are paid twice” to “Duplicate vendor payments”.
By hand
Links you add by hand are related
links. To remove one, click the X next to it.
With the agent
Link the “Duplicate vendor payments” risk to the three-way match control.
Link every accounts payable control to the Accounts Payable process.
By hand
With the agent
Build a reusable workflow template for reviewing vendor master data changes. It should run on Process records, with human review where judgment or sign-off is needed.
Strong workflows keep human sign-off to the points where it adds judgment. Add a form to a step only when someone outside the workflow has to supply information.
By hand
With the agent
Run the walkthrough template on the Accounts Payable process.
Set [reviewer name] as the approver for the steps in that workflow, with a due date of [date].
Do the next ready step in that workflow using its linked records and documents, and draft the step result for my review.
Draft the ready workflow steps assigned to me in one pass and report anything that still needs my input.
Review the draft results, then approve each step yourself. Only a person can sign off a step.
By hand
On a record, upload a file into any document field. Links to online documents go on steps only.
With the agent
Attach a mock file to the chat, then copy the upload prompt. For an online document, use the link prompt.
Upload the file I attached as supporting evidence for [step name] in [workflow name] on [record name].
Link [document URL] as supporting evidence for [step name] in [workflow name] on [record name].
Attach the evidence before asking the agent to do the step.
Use mock files only. Nothing from your organization belongs in the sandbox.
By hand
There is no search across all record types. Start from the list or dashboard closest to your question.
With the agent
How many high or critical residual risks do we have, by category?
List every overdue remediation with its owner.
There are three ways to put an AI agent to work in your sandbox: the Swarm agent, which needs no setup; Claude, Codex or Muse with the Auditober plugin; or an agent you build in Microsoft Copilot Studio. Each one signs you in through core.assureswarm.com, gets only the access your account has, and sends every change to the Activity Hub for you to approve.
The Swarm agent at demo.assureswarm.com runs on Google's Gemini model and is already connected to your sandbox. Follow Sign in to the Swarm agent and start asking. Its chats use your team's AI allowance.
The Auditober plugin connects your own agent to the sandbox and gives it the skills the Swarm agent uses. It also adds auditober-info, which answers questions about the event from this guide. Your agent runs on its provider's allowance or billing, not your team's.
Claude Code: run these in a session, start a new session, then run /mcp, select plugin:auditober:auditober and choose Authenticate.
/plugin marketplace add rp4/auditober-plugin
/plugin install auditober@auditober-pluginClaude Desktop and Cowork: download auditober.zip and upload it as it is under Customize, then Plugins. Sign in when Claude asks.
Codex: run these in a terminal. The last command starts the sign-in.
codex plugin marketplace add rp4/auditober-plugin
codex plugin add auditober@auditober-plugin
codex mcp login auditoberMuse is Meta's personal AI agent. If you don't have it yet, sign up at ai.meta.com/muse and redeem referral code FQFWPK in Muse's settings within 48 hours of signing up. Then follow the Muse steps in the plugin's instructions. We have not tested Muse with the sandbox yet, so email support@assureswarm.com if a step doesn't match what you see.
Each sign-in opens core.assureswarm.com in your browser. Sign in with your Auditober email address, check the Authorization Request and choose Authorize Access. Then run coach-setup, or ask what is in my AssureSwarm workspace?
Copilot Studio connects to the sandbox's MCP URL directly, without the plugin. You need maker rights in your organization's Copilot Studio.
https://core.assureswarm.com/mcp
Copilot Studio options that need a manually registered OAuth client are not available on the Auditober sandbox. Use dynamic discovery.
Other MCP clients, such as ChatGPT, GitHub Copilot and Gemini CLI, can use the same URL. Add it as a remote server with OAuth sign-in.
Still stuck? Email support@assureswarm.com and name the tool you were connecting.
You can enter a workflow or evidence flow, a dashboard or a plugin. The four categories are risk assessment, testing, operational audit and most creative. You can participate in multiple categories; you do not need to specify a category when submitting.
For a plugin entry, start from an existing AssureSwarm plugin and extend it outside the app. Use the Bluth mock data to test your entry.
node setup.mjs (Node.js 20 or later) and enter the MCP URL when it asks. Copy a skill, change it, and run your version from your own agent. The plugins page lists every variant.Send all Auditober submissions to support@assureswarm.com as email attachments. Submitting an entry means you agree to the open-source contribution terms below.
Accepted files are Word documents (.doc or .docx), PowerPoint presentations (.ppt or .pptx), HTML files (.html), Markdown files (.md) and plugin ZIP files (.zip). Keep the combined attachment size to 25 MB or less.
Auditober submission: [team name] / [entry title].Entries close on October 31, 2026. The exact cutoff time and timezone are still to be confirmed. Keep a copy of your sent email and attachments.
For corrections or questions about an entry you have sent, reply in the same email thread and identify the entry title. If your email bounces or your mail service rejects an attachment, contact support@assureswarm.com without the attachment and describe the problem.
Every Auditober entry is a contribution to the audit community's shared playbook. By submitting an entry, you grant AssureSwarm and anyone who receives the entry a perpetual, worldwide, royalty-free and irrevocable license to use, copy, modify, publish, distribute and build on it, in whole or in part, for any purpose. AssureSwarm may release any entry to the public under an open-source license of its choosing, without attribution and without payment beyond any prize awarded.
Once you submit, the solution is the community's to use. Neither you nor your team will hold exclusive rights to it, and you may not restrict how others use, adapt or share it. Submit only work you have the right to contribute. If your employer may have rights in what you build, confirm with them before you submit.
The event page lists four category winners. Each wins an AuditKeyboard and a QAIP readiness review from Cherry Hill Advisory; the winners also share $1,000,000 in AssureSwarm subscriptions. Winners are planned for November.
Entries will be shared anonymously with participants, under the open-source contribution terms above. The full judging process, panel, announcement date and prize terms have not yet been published. The date sandbox access ends has not been announced either. Keep your own export and contact the organizers if any of these details affect your entry.
Say what you were trying to do, what you expected, and what happened. If your team's AI allowance has run out, you can still write and send feedback by hand.
Bring questions about your sandbox, your entry or the submission steps.
Book your office hours and choose a time on the calendar.
Each team shares a $50 AI allowance for the whole of Auditober, with a daily limit on top. The top of the agent shows what your team has used today, for example Team budget $0.00 / $25.00 today
. The allowance covers the Swarm agent's chats, feedback drafting and document reading, and it does not reset each month. When it runs out, the agent tells you and stops making AI calls. The app, the dashboards and any agent you connect yourself keep working. Your own agent uses its provider's allowance or billing, separately from the included Swarm allowance. Check the amount shown in the chat for your team's current daily limit.