Self-hosted · Your providers · Approved connections

AI departments built aroundhow your company works.

Create departments with specialists, instructions and approved tools. Ask in plain English. Get an answer, a validated file or a proposed code change back.

Map your first department See how it works

Illustrative department run

Marketing departmentOne request

Draft Thursday's launch brief, with the positioning we agreed and sources for the numbers.

Marketing department agentReads its instructions, then splits the work

Market ResearcherSource the numbers and cite them
Content StrategistDraft the brief in our positioning

CheckedPDF structure · renderingPassed

Published filelaunch-brief.pdf

Demo

Seventy-three seconds, end to end.

One request becomes governed work: a department agent thinks, delegates to a specialist, checks primary sources, runs commands in a disposable sandbox, and hands back something that was validated before it reached you. The chat you see working is a recording of the product, not an animation of it.

Jump to

Illustrative product data · Marketing department shown

Asking

Start with a sentence.

Day to day, you can write requests in ordinary language. The department's configured instructions, specialists and skills provide the working context.

When missing information would materially change the result, the agent can ask a clarifying question before continuing.

Message it from

SlackDirect messages
Microsoft TeamsPersonal chats
Agent FactoryIn the app

Your administrator connects the company once; each person then links their own account.

Chat · one request, start to finishIllustrative

Departments

A department, not one generic chatbot.

Each department has its own instructions, model route, enabled skills and specialist roster. The main agent can delegate focused work and return one combined result.

Start fromMarketingEngineeringResearchOperationsSalesCustomer SupportBlank department

The Agent Factory company overview listing Engineering, Marketing, Customer Support and Operations department agents, with their schedules and running workflows. — Four departments here because four were set up. Add as many as your company has, from a preset or from blank.

Knowledge

Shared knowledge with visible boundaries.

A department can keep shared memory and reusable skills from its work. Personal preferences stay private to each account, and the Evolution workspace shows what the department has retained.

Evolution · department memoryIllustrative

Everything the department has retained is a file you can open, edit or delete — durable memory the whole department shares, skills it learnt from real work, and a profile that stays private to one account.

Shared where it should be

Department memory and reusable skills apply to everyone working in that department, not only to the person who saved them.

Private where it should be

Personal preferences are scoped to your own account. They shape your work and stay out of the department's shared knowledge.

Open to inspection

The Evolution workspace shows what the department has retained. Managers manage its reusable skills from Capabilities.

Execution

A disposable workspace when the work needs one.

Interactive chats can use a server-side sandbox for code, files and document generation.

The sandbox does not mount the host filesystem and is removed when the turn ends. Files that should remain available must be published.

Published workflows support governed research, generation and specialist delegation. Sandbox-backed code, browser and desktop execution stay in interactive chat.

Sandbox · this turn only

$read competitors-2026.xlsx
✓five competitors parsed
$python compare.py
✓comparison table written
$build board-onepager.pdf

board-onepager.pdfPublished

Everything else is removed with the sandbox

Connections you approve

Company and user setup are both required before a connection can be used.

GitHubUser-scoped connection
FigmaUser-scoped connection
SlackDirect messages
Microsoft TeamsPersonal chats
Approved custom MCP serversUser-scoped, from your allow list

The Capabilities Connections tab: company connections for GitHub, Slack and Microsoft Teams above a person's own connected GitHub and Figma accounts, each shown separately. — Company connections are set up once for everyone. Your own accounts are linked separately and their tokens stay on your account — a colleague in the same department never borrows them.

Repeatable work

Turn proven work into a versioned workflow.

Save the steps and instructions, publish an immutable version, then run it manually or on a schedule. Add human input or approval nodes wherever a person needs to decide what happens next.

The Workflows screen showing the Competitor pulse workflow: three nodes, two connections, draft revision two, with Open canvas, Publish and Start run actions. — Nodes and connections are edited on a canvas. Publishing freezes a version, so a run you read months later is the workflow that actually ran.

A published version is immutable. Every run reuses the same saved steps, instructions and published version — editing the workflow publishes a new one rather than changing what already ran.

Put an input or approval node anywhere a person needs to decide what happens next. Nothing moves past one until someone does.

Published workflows support governed research, generation and specialist delegation. Sandbox-backed execution is currently limited to interactive chat.

The Runs workspace in Agent Factory showing a workflow run held at an approval step, with the drafted output to review and Approve and continue or Reject controls. — An approval node stops the run and waits. The step that produced the work is right there to read before you decide.

Control

Checked before publishing.

Generated PDFs are checked for structure and rendering. Word, spreadsheet and slide files receive format-specific validation.

Invalid files are refused and reported clearly, rather than silently delivered or automatically retried. You decide what happens next.

PDF · Word: Available to managed departments
Spreadsheets · Slides: Need the relevant enabled skill and the sandbox
Pull requests: Need an enabled skill and a GitHub connection

Validation · before publishingIllustrative example

board-onepager.pdfstructurerendersPublished

comparison.xlsxopens3 sheetsPublished

deck-draft.pptxopensRejected

A refused file is reported, and left for you to look at

Model routing

Any provider. Pinned, not guessed.

Hermes stays the model and credential authority. Agent Factory stores each department's route and pins the exact provider and model into every published version.

Automatic fallback and dynamic routing are deliberately off. A run that used one model cannot quietly become a run that used another, which is what makes an old run worth reading months later.

01Workflow node: Set on one step, wins over everything below
02Specialist: The researcher can run a different model to the writer
03Department default: What everything else in the department uses

The Usage screen grouped by model, showing billed cost, calls and cache traffic for claude-opus-5, claude-sonnet-5, gpt-5.6-luna, claude-haiku-4-5 and gemini-3-pro side by side. — Five models from three providers in one period, each attributed separately. The route a published version ran on is pinned into that version.

Spend

Enforced before the call, not after the invoice.

Every governed model call is recorded against a department, a person, a provider and a model — with cache traffic and reserved cost separated out. Prompts and responses are never stored in the usage record.

Daily and monthly limits are checked atomically before the call reaches the provider. A department that has spent its day is stopped, not invoiced. Members see themselves, managers see their departments, administrators can look company-wide.

Before the call — admission, not reconciliation
Per department and per user — either can carry a limit
Unknown prices — reportable, but need an override before a hard cap is honest

The Usage analytics tab: spend over time as a daily bar chart, with spend by department and spend by person broken out beneath it.

The Budgets tab showing a company monthly limit on track at fifteen per cent and a Marketing daily limit nearly spent at eighty-nine per cent. — Cost is reserved before each governed call, so a limit that is already spent stops the next call rather than reporting it late.

Sheet 01 · General arrangement

Deployed on infrastructure you control.

Agent Factory is yours to run. Your records, your providers, your infrastructure — and what a department retained or failed at is something you look up rather than ask someone for.

Records you hold

Your company records live in PostgreSQL. Runtime profiles, transcripts, connected-account tokens and execution state are held alongside them, all of it deployed under infrastructure you control.

A boundary you can describe

Connected providers and approved MCP servers receive the context required for authorized work. Sandbox network access depends on deployment configuration.

Failures that stay visible

A run that fails stays on the record with what failed and where. Nothing retries on its own — you look at it, change the request, and run it again.

Questions

The ones we get asked first.

What can a department actually do?

Research, writing, analysis and published files. Additional spreadsheet, slide, code and pull-request capabilities depend on the skills you enable, on the sandbox, and on the connections that department has.

Does it work while my laptop is closed?

Agent Factory runs on its server. Gateway messages and scheduled tasks can run without your laptop, assuming the deployment and the services it depends on stay available.

What does it remember?

Personal preferences are scoped to your own account. A department can also retain explicit shared memory and reusable skills, which you can inspect through the Evolution workspace. Managers manage the department's reusable skills from Capabilities.

Which tools can it access?

Only the supported integrations and approved MCP tools configured for that user and that deployment — GitHub, Figma, Slack, Microsoft Teams and custom MCP servers on your allow list. It does not provide arbitrary browser automation.

How is company data controlled?

Agent Factory is self-hosted, but authorized providers, integrations and network-enabled sandboxes receive the working data they need to do the job. Administrators configure permissions, egress and DLP appropriate to their environment.

Where does code actually run?

In a server-side sandbox attached to an interactive chat. It does not mount the host filesystem and is removed when the turn ends, so anything worth keeping has to be published. Sandbox-backed execution is not available to published workflows.

Will it do things without asking me?

In a chat it answers what you asked. In a workflow you decide where the input and approval nodes go, and the run holds at one until a person decides. Schedules run the version you published, on the times you set.

What happens when a file or a run fails?

A file that fails validation is refused and reported rather than delivered. A failed run stays on the record with what failed and where. There is no automatic retry — you look at it, change the request, and run it again.

Can I put a ceiling on what it spends?

Governed model calls are tracked by department, person, provider and model, and administrators can configure daily or monthly limits where reliable pricing is available for the models in use.

Do I need to be technical to use it?

Day to day you write requests and read what comes back. Standing the deployment up, connecting the company and setting permissions is a job for whoever looks after your infrastructure.

Map your first department.

Tell us what work one team does today. We'll map it to a department: its instructions, the specialists it needs, and the connections that work would depend on.

We'll also be straight with you about which parts need an enabled skill, a sandbox or a connection you don't have yet.

Or write to us directlycontact@joebasset.com

Department briefNew