.theseoINSTITUTE FOR VISIBILITY
About this choice

We only save your display preference in a preference cookie, for up to 180 days on this device. No CRM or advertising data. Your tracking consent stays unchanged. If cookies are blocked, your choice may not be saved.

Discover
Close

In short

How Jarvis connects context, approval and organisational memory

The organisation demo shows how a task, permitted context and human approval fit together. With a personal Jarvis brain, you manage your documents and connect supported AI apps.

Start and Solo available online in the Netherlands

Conceptual illustration, not a client result or proof of product functionality.
Conceptual illustration, not a client result or proof of product functionality.
Can you trace why knowledge applies before entrusting work to an organisation brain?

Five phases, with approval before external action

The organisation workflow starts with a defined task. Relevant, permitted context is selected, an appropriate AI role prepares a draft, and a person reviews the exact version before an external action. Approved knowledge can then be recorded for later work. These steps explain the design of the broader organisation workflow. They do not mean a personal Start or Solo subscription runs autonomous tasks, routes work between colleagues or sends messages for you.

Keep the source and status with the statement

A useful shared statement needs more than its wording. Record its source, the people or work it applies to, its version, when it is valid, its status and who approved it. A proposed rule should remain distinguishable from an agreed rule. If a price list and a contract conflict, do not average the amounts or silently choose one. Make the difference visible and ask the responsible person to resolve it. Keep the previous version and the reason for the correction available.

An audit trail is not a quality certification

The design calls for a record of who acted, when and on which version. That is different from copying every prompt, document or secret into a log. Access to sensitive records needs its own scope and purpose. A history can help explain a decision, but it does not prove that the decision was correct. It is not a security certificate or a guarantee that every organisation control has been implemented.

Read the unfinished work alongside the interface

The organisation demo uses fictional data to illustrate tasks, approvals and knowledge proposals. Trying those examples does not approve a real customer action or establish a live organisation setup. Shared team access, multiple brains and the wider organisation workflow remain distinct from the personal product. The personal workspace lets one user maintain documents and connect supported AI apps; it does not automatically collect all conversations or execute tasks independently.

Choose a plan for the AI apps you use

Start and Solo are available online to individuals and businesses in the Netherlands. Both include one user and one brain. Start supports two AI connections and seven days of document history. Solo supports three connections and thirty days of history. You pay for your AI apps and model usage separately.

Team plan in development

Jarvis Team

€99.00 per month

Personal, including VAT

Business, excluding VAT €81.82 per month

Team plan in development

Jarvis Business

€249.00 per month

Personal, including VAT

Business, excluding VAT €205.79 per month

Try the manual template or the fictional demo first

You can first use the free business-brain template to describe your business, offer and working agreements. The linked template and organisation demo are in Dutch. Neither requires you to buy a subscription just to explore the idea. For a team use case, bring the sources you want to manage, the people who would use them and the decisions that need approval. That establishes what would actually be required before any wider implementation is agreed.

The boundaries at a glance

Organisation demo status
Preview
Human approval required
Yes
Own model subscription separate
Yes
Usage meter
No
Same gross amount by country in the preview
Yes
Demo with fictional data
Yes
Account required for demo
No
Production isolation proven
No
Production authentication connected
No
External security certification
No

Start, Solo and plans for teams

Start and Solo are available online in the Netherlands. Book a call to discuss your requirements for Team or Business.

Next steps

Can you trace why knowledge applies before entrusting work to an organisation brain?

Read the complete original page
All information

Explore the details at your own pace.

JARVIS / PRODUCT AND CONCEPT

How does an AI organisation brain work?

What is included in Start and Solo?

Jarvis Start and Solo give one person one document workspace. Save text and Markdown, edit documents, use document history and choose which compatible AI connection may read or write. Your own AI app and model usage remain separate.

Start includes two AI connections and 7 days of document history. Solo includes three connections and 30 days of document history. These are connections to your own AI apps, not autonomous workers. Team and Business are still in development and cannot be ordered here.

Use Jarvis from your own TheSEO account. A free account and a Jarvis subscription are separate choices. With an active Jarvis subscription, you can open your workspace and manage your subscription from your account.

The product page shows which plans you can order. Choose your language and whether you are buying as an individual or a business. Before payment, you will see the amount, subscription period and terms for your choice.

View current plansOpen my Jarvis

The five-step cycle below is a design for organisation and agent work. In Start and Solo you use documents and your own connected AI. Saved documents do not pass through a mandatory team approval process.

Further reading: the broader organisation concept
The material below describes a broader organisation brain and its fictional demo. Tasks, team roles, approvals, automatic knowledge distribution and the twelve demo screens are not included Start/Solo features. Examples and historical development statuses below are not a current release or security declaration. The personal workspace and current plans are described separately above.
~/jarvis/werking/01-dagcyclus[run]
Section 01 · The daily cycle

One assignment, five phases

Everything below on this page is connected to this cycle

An assignment comes in, receives context, is delegated, passes by a human and only then becomes part of the memory

The four visible steps are shown on the Jarvis hub; here, writing back counts as a fifth phase, because that is precisely where the difference lies between a smart chat and a brain that will still know tomorrow what was decided today. The example below is schematic: it shows the form of the cycle, not a real customer assignment.

FIG.01: The daily cycle as a terminal[#----] sheet 1/5
jarvis · organisation brain · schematic example
you > write the monthly message for this month's customers
[01 assignment] recorded with objective, desired output and ownera human or a connected AI prepares the assignment # a question without an objective first prompts a question in return
[02 context] only sources permitted for this role and scopethe server first filters by organisation, role and objective, and only then ranks by relevance # retrieval is also authorisation
[03 delegation] research, content, sales or support takes it onthe role receives minimal permissions and delivers a draft with supporting evidence...
[04 approval] a human reviews the exact versionWAIT FOR APPROVALuntil then, it remains a draft and nothing is sent out # no email, no publication, no payment
[05 storage] approved knowledge becomes memory, the rest does notthe item is given a source, scope, version, validity, status and approval, and the entire process is recorded in the logbook
[#####] 5/5 cycle closed · the next assignment starts with what has been recorded here
the loop, in brief: recorded → context determined → delegated → human approval → stored · what enters the logbook during each phase is set out in the logging protocol
5W.01 · phases in the daily cycle
6W.02 · fields per memory item
5W.03 · statuses per memory item
0W.04 · meters on prompts or tokens
W.01 to W.04 · product properties, not results, usage figures or customer numbers.
$ cat 01-wat-een-organisatiebrein-is.md
DOC.01

What an organisation brain is, and what it is not

In short, such an organisation brain is a shared, controlled memory for your company, plus the orchestration of who and what is allowed to draw from it. It stores the things currently held in people's heads, chats and separate documents: how you work, what you agree, which version applies, who approved something and why an earlier choice was reversed. And it passes that knowledge to the AI tools you already use, instead of each tool maintaining its own incomplete version of the story. Jarvis is our implementation of this: a knowledge and orchestration layer between your people, your sources and ChatGPT, Claude and Codex.

It is useful to first say what it is not, because the term borders on three things that closely resemble it

It is not a note-taking app. A second brain in the personal sense, like those people build in note-taking tools, belongs to one person and has no roles, no approval and no demonstrable audit trail. An organisation brain is shared by definition, and within a month, shared memory without permissions and provenance becomes a cluttered attic.

It is not a new chatbot.

Your AI tools remain in place and you keep your own subscriptions; the brain sits alongside them and supplies them with information. And it is not a search index of your files. A search index finds documents. A brain knows which document applies, since when, to whom, and who determined that.

The difference lies in that final word: validity

Almost any AI setup can retrieve text. Almost none can explain why that text is true now. That difference is precisely what an organisation brain adds, and it is also why the rest of this page is about metadata, statuses and approval rather than smart answers. The intelligence comes from the language model you already have. The reliability must come from somewhere else.

If you want to test the idea without software first, you can

The free company-brain template NL is the manual version: a single fillable file that tells your AI who your company is, what you provide and how you work. That works surprisingly well until several people start writing in it and no one knows which version applies any more. From that point onwards, you no longer need a file but a system, and that is where this page begins.

$ cat 02-waarom-elke-sessie-leeg-begint.md
DOC.02

Why every AI session starts empty

Anyone who works with AI every day knows the pattern. This morning, you explain in ChatGPT how your quotations are structured, what tone you use with customers and which margin you never reveal. This afternoon, you open Claude for another piece of work and that conversation starts from zero. Tomorrow, your colleague uses the same tool and explains the same things again, but slightly differently. Two different truths do not arise because someone is careless, but because there is no place where the truth belongs.

There are three causes, and they compound one another

The first is the session boundary: by design, a chat is a conversation, not an archive. What it contains is context, not knowledge. The second is the tool boundary: memory features offered by the tools themselves reside in that single account and that single tool, so as soon as you switch tools or a colleague joins in, they disappear. The third is the human boundary: most of what a company knows has never been written down. It is in the head of the person who devised it, and that works until that person goes on holiday.

Skills solve part of that, and we share them for free: a skill is an instruction file that gives your AI a consistent working method for one task

But a skill teaches the AI how to do something, and that is different from remembering what applies in your organisation. The skill is neither the engine nor the memory: it says how a quotation should be structured, not which rates you charge or which customer received an exception last month. Those two layers need each other. The skill teaches the AI, the brain is where the memory lives.

The consequence of that empty start is not just lost time

The main problem is that you can never say with certainty what an AI based something on when it wrote it on your behalf. As long as that remains the case, you can use AI for drafts, but not for work for which someone is accountable. The entire structure below exists to restore that certainty, and this comes at the expense of speed in exactly one place: approval. That trade-off was deliberate. The theory underpinning this design, from stateless models and context rot to retrieval and MCP, is explained in detail in how an AI brain forgets nothing between chats NL.

~/jarvis/werking/02-geheugenitem[ok]
Section 02 · The anatomy

One sentence, six fields around it

This is the brain's smallest building block and, at the same time, its most important one

A memory item is not the sentence itself, but the sentence plus everything needed to assess whether you may trust it

Without those six fields, a memory item is a claim; with those fields, it is a verifiable fact. The content below is a schematic example, not a real client rule.

FIG.02: The anatomy of a memory item[##---] sheet 2/5
memory itemschematic example · six mandatory fields
textA quotation remains valid for thirty days.on its own, this sounds clear, and that is precisely the danger
sourcevoorwaarden.md · owner: managementfile, system, owner and a reference you can open
scopeorganisation · applies to sales and quotationswho it applies to: organisation, team, role, client or process
versionv3 · reason: period shortened after review · previous version retainedcontent hash, reason for the change and the version it replaced
validityeffective from: 01-07-2026 · review: in six monthseffective date, expiry date and time of reassessment
statusactive · not: proposal, in review, conflicting or replacedone of five states, and only active items count towards answers
approvalauthorised actor · timestamp · exact version v3who approved it, when, and for which immutable version
# without these fields, a system can answer, but cannot explain why the answer currently applies
# THE HONEST EVIDENCE · NOT A DEMO

We use this system ourselves every day. Every agent session, every task and every decision is logged in it and can be reviewed. Our own product documentation, pricing files and release status are stored in that brain and published from it, so this explanation has the same source as the one we work with ourselves. If a page differs from that source, the page is wrong. The part that is not yet finished appears below, explicitly identified.

$ cat 03-hoe-kennis-binnenkomt.md
DOC.03

How knowledge enters

Knowledge enters through four routes, and the difference between those routes determines how strict the subsequent gate is. The first route is the person who records something: someone writes down an agreement, a rate or a working method and submits it to the brain. The second is a source that you connect: a document, a system or a file that the owner designates as the authoritative location.

The third is what emerges from the work

During an assignment, an AI role discovers something that is apparently true, for example that a client prefers to be updated by telephone, and proposes it as a memory item. The fourth is a proposal from outside your own brain: we can offer generic product knowledge or an improved working method.

That fourth route warrants a separate sentence, because it contains a boundary that many systems do not have

Our superbrain contains generic product knowledge, policies and proven patterns. A client brain contains the sources, people, rules and context of one organisation. Improvements can be proposed from the top down, but client content does not automatically flow in the other direction and is not used to train anything. The precise intent behind that separation is explained in the in-depth article on the superbrain and client brains.

What all four routes have in common: nothing enters as ready-made truth

A submitted item receives proposal status. It is immediately supplied with its six fields, because a proposal without a source cannot be assessed and is therefore returned rather than stored. Its status changes only after approval, and only then does the item count when the brain provides context for a subsequent assignment. That is why the memory grows slowly, and that is precisely the intention: a brain that swallows everything it encounters becomes unusable within a quarter.

There is a second filter as well, and it may be the least intuitive part of the entire design

When the brain retrieves context for an assignment, relevance is not the first criterion. It first filters by organisation, role, classification and purpose, and only then ranks by content relevance. A source may match the question perfectly and still not be permitted for the agent, the person or the task. Being able to find something and being allowed to use it are two different things, and applying them in that order is the difference between a useful assistant and a leak.

~/jarvis/werking/03-goedkeuring[ok]
Section 03 · The gate

From proposal to active

Between entering and counting, there is one gate, and that gate is a person. In this system, an approval is not a button but a recorded event: an authorised person approves an exact, immutable version, with a consequence that can occur only once. The five requirements at the bottom of the figure are the properties that make an approval usable as evidence.

FIG.03: The status gate of a memory item[###--] sheet 3/5
STATUS · PROPOSAL Submitted, not yet valid The item exists, can be found and does not count towards answers. A proposal without a source or owner does not progress beyond this column.
→
STATUS · IN REVIEW A person assesses the exact version The reviewer sees what is changing, where it came from and what the consequence is. For higher-impact changes, the policy may require two reviewers or a waiting period.
→
STATUS · ACTIVE Applies, and counts as context From now on, every connected AI uses this item. The approval remains attached to it: the actor, timestamp and version can be retrieved later.
Side path: conflictingIf two sources say different things, that is not a problem to be averaged away. The conflict is made visible as a review task, together with the sources, instead of producing a confident answer.
Side path: replacedA new version does not displace the old one, but changes its status to replaced. The previous text, the reason for the change and the approver are retained, because otherwise you cannot reconstruct a correction later.
[1]exact version · the approval points to an immutable content version, not to a text field that can still change afterwards
[2]authorisation · the server checks the role, organisation and task scope, not the button in the interface
[3]deliberate intent · the reviewer sees the action, destination and risk before approving
[4]idempotent consequence · the same approval cannot accidentally cause two emails or two payments
[5]audit and revocation · the timestamp, actor, reason and any revocation are recorded

There is a pitfall that we explicitly identify because it can break any approval system: approval fatigue. If the system asks for a click at every small step, people start clicking blindly and the gate becomes a formality. The solution is not less control but better grouping: define low-risk steps in advance as policy, show only decisions with a real consequence, and bring exceptions to the fore. The detailed reasoning appears in human approval.

$ cat 04-bronherkomst.md # why provenance is not a luxury
DOC.04
source provenance · schematic example
theseo ~ %
source: terms v3 · since 12 May
applies to: projects, not services
may be changed by: the owner
traceable, and therefore verifiable

Source provenance: why knowing where something comes from is not a luxury

Take the sentence from FIG.02 again: a quotation remains valid for thirty days. On its own, that is a perfectly sound rule. But as soon as someone uses it, questions arise. Does it apply to all services or only to projects? Since when? Is it in the terms and conditions, in a price list or in the notes from a meeting last year? Who may change it? An AI that neatly retrieves the sentence and confidently quotes it does exactly the wrong thing: it gives you an answer you cannot verify.

Provenance is therefore not an additional field but the core of the memory.

If you do not retain the metadata, you retain only text, and text without context is why people start double-checking AI answers. The aim is not for the brain always to be right. The aim is for you to be able to establish within thirty seconds what an answer is based on, so that you can decide for yourself whether to adopt it. That is a more modest promise than infallibility and a far more useful one.

Conflicts are product data, not an error.

If the CRM, the price list and the contract state different amounts, their average is not an answer but a new falsehood. The brain should show that conflict together with the three sources and turn it into a review task. The conflict status and the eventual resolution themselves also become part of the trail, so that you can later see why that choice was made. In practice, this is one of the most useful features: it exposes contradictions that had gone unnoticed in the organisation for months.

Maintenance is also needed, and that may be partly automated

A scheduled session can review sources that have expired, check links and flag inconsistencies. What such a session may not do is independently replace pricing policy, contract text or customer knowledge. The result of automated maintenance is therefore always a review task, never a publication. The full details, including the minimum fields per item, are set out in source provenance and knowledge architecture; the broader design choices are set out in the knowledge section.

~/jarvis/werking/04-log[ok]
Section 04 · The log

Enough evidence, as little content as possible

Logging is what enables you to establish afterwards what happened on your behalf

At the same time, a log that copies everything is a second copy of your trade secrets in a place no one thinks about

The principle is therefore clear-cut: record who did what and when, and which version was involved, but do not duplicate the content. The lines below are a schematic example of what such a trail looks like, not a real log file.

FIG.04: jarvis tail audit.log[####-] sheet 4/5
$ jarvis tail audit.log● append-only
09:12:04TASKactor: human · organisation: acme · route: /work · objective: monthly update # request-id recorded
09:12:05CONTEXT3 sources permitted, 2 rejected due to scope # which ones, with version and owner
09:12:41AGENTrole: content · tool action: prepare draft · duration: 36s · status: complete
09:13:02BLOCKEDexternal sending attempt · reason: no approval yet # draft remains a draft
10:04:19APPROVALactor: authorised user · version: v7 · result: send, once only
10:04:20MEMORYitem v3 → replaced · new item active · reason recorded
10:41:57EXPORTactor: administrator · secrets masked · data from other organisations excluded
[+] RECORDED
  • request-id, time, actor, organisation and route
  • changes to authentication, roles, connectors and subscription entitlements
  • versions of sources, memory items, agents and approvals
  • tool action, result status, duration and error category
  • support access, export, deletion and incident status
[-] NOT RECORDED BY DEFAULT
  • full prompts and full answers
  • the content of documents
  • API keys and tokens
  • payment card details
  • special categories of personal data

If content logging is nevertheless temporarily required for an incident, that is not a silent exception: that logging is assigned a purpose, an owner, a time limit, an access policy and proof of deletion. Critical audit events are intended to be append-only and time-synchronised, only authorised roles are given access, and an export masks secrets and excludes data from other organisations. The full protocol, including the retention periods, is set out in the logging protocol, and what happens during an incident is set out in the incident process.

$ cat 05-het-spoor-teruglezen.md
DOC.05
audit.log · schematic example, no content
theseo ~ %
09:14 · task received · role: owner
09:15 · draft created · awaiting approval
09:41 · approved by a human · sent
# who, what, when and based on which source: yes. The content of messages: no.

How to read that trail

A log that no one reads is a reassuring sound, not a control. The practical question is therefore: which questions can you answer with it, and where do you look. In the interface, this runs through three entry points. From a task, you see that task's entire progression: which context was provided, which role worked on it, which draft resulted, who gave approval and what happened afterwards. From a memory item, you see the reverse path: which versions have existed, why it was changed, who approved it and which source underlies it. And from a person or role, you see what happened under that authority.

The questions this answers are perfectly ordinary questions

Why did that message to that customer state a period of thirty days? Who approved our use of that wording? When was that rate changed and on what basis? Has anyone from outside the team ever looked at this file? With a standalone AI chat, the answer to those questions is by definition: we no longer know. With a brain that has an audit trail, the answer is a line containing a time, an actor and a version.

Two things are important to state honestly here

The first: a trail proves what the system did, not that a decision was wise. Logging is not a quality mark. It makes assessment possible, nothing more, and that is already a great deal. The second: how robust this is for your organisation depends on what is listed further down as an open point. The design is fixed and visible in the demo; part of the production controls for the team brain is still a work in progress.

For those who want to see it for themselves: the interactive demo NL is the real interface with fictitious sample data and works without an account

You can click through it, approve a draft, assess a knowledge proposal and explore the payment step in the organisation demo. The guided tour with an explanation for each screen is on the platform tour, and the register showing which documents are valid and which are still drafts is in the documentation.

~/jarvis/werking/05-boundaries[ok]
Section 05 · The boundaries

What Jarvis deliberately does not do

The boundaries below are product features, not small print. They get in the way at precisely those moments when a system without boundaries seems faster, and that is the point. Each rule is a request you could make, followed by what happens.

FIG.05: boundaries.conf[#####] sheet 5/5
boundaries.confproduct rules, not terms imposed afterwards
send that message to the client immediately, I will read it laterBLOCKEDNo silent external action. Email, publication, contract or payment does not go out without the agreed human approval. The draft remains ready, while sending waits.
use what you learnt from that other clientBLOCKEDNo mixing of knowledge between client brains. What is in one brain stays there. There is no free exchange, and client content is not used for training.
just save this as truth, I will look up the source laterSENT BACKNo memory item without provenance. Without a source, owner, scope and validity, it remains a proposal. The brain would rather leave the question open than store a claim that nobody can verify.
those two sources contradict each other, just pick oneREVIEW TASKNo smoothing over conflicts. When sources conflict, a review task is created with the sources attached, rather than a confident answer that happens to choose one of them.
charge me for last month's AI usageDOES NOT EXISTNo billing per prompt, token or call. We do not put a meter on your usage. Your model costs run through your own subscription with your own provider, and that subscription remains yours.
apply that improvement of yours to our entire brain straight awayAS A PROPOSALNo automatic adoption from above. We can offer an improvement, but your organisation decides. A proposal only becomes active after passing through the same gate as all other knowledge.
just give me the logs with the full prompts in themRESTRICTEDNo content logging by default. The log proves who did what and on which version, and does not duplicate your documents and prompts. A temporary exception during an incident is given a purpose, time limit and proof of deletion.
you are certified, aren't you, just add thatREFUSEDNo claiming certification that does not exist. There is no certificate, and citing someone else's standard is no substitute. Until there is valid external certification with a defined scope, we will not market it that way either.
$ cat 06-wat-nog-niet-af-is.md # open points
DOC.06

What is not yet finished

Start and Solo are available to order; the organisation brain for teams is still in development, and that is not modesty but a status. What there is of the team brain is a working interface containing the core interactions: assignments, approvals, memory proposals, knowledge reviews, inbox, task statuses, subscription changes and the five-step onboarding process. And we identify what is not yet there just as precisely, because a product page that shows only the attractive part is exactly the kind of source we would reject in the brain itself.

Still open for the team brain:

For the organisation brain, the security page describes checks on authentication, separation between organisations, external connections and ongoing operations. It also lists exercises and reviews for a wider release. Read about security and privacy.

The pricing reflects the same honesty.

Start and Solo are available online to individuals and businesses in the Netherlands. Team and Business are in development. Book a call to discuss how your team would use Jarvis. Compare Jarvis plans.

What is already correct: the demo NL is the real interface with fictional sample data and works without an account, the pricing model without a usage meter is a verifiable property rather than a promise, and the working method shown on this page is the one we ourselves use every day. The current status of each gate is available in machine-readable form in the documentation, and the underlying materials are in the trust centre, including documents that are still labelled as drafts there.

~/jarvis/werking/06-entry-ladder[ok]
Section 06 · The entry ladder

Try it yourself first, then start independently

You can start using Jarvis yourself, yet there is still an order below. An organisation brain that does not suit your situation is costly in a way that has nothing to do with the price. The sequence below helps with that: first the free template, then the demo, and only then a conversation.

$ cat entry-ladder.shthree ascending rungs
entry-ladder.shfree · look · start
RUNG 1 · FREE
available today
The company brain template: the manual version A single fillable file that teaches your AI who your company is, what you provide and how you work. The free template NL is the paper-based predecessor of everything on this page: the same idea, without roles, without approval and without a log. Works in Claude, ChatGPT, Codex and Cursor, and you do not need anything from us to use it. $ download bedrijfsbrein.md · 0 euros · no account
↓
RUNG 2 · LOOK
without an account
The interactive demo: the real interface If the template becomes unmanageable because several people are writing in it, you will want to see what this looks like as a system. The demo NL is the working Jarvis interface with fictional sample data: approve a draft, assess a knowledge proposal, see where the payment gate remains closed. The explanation for each screen is in the platform tour. $ open /jarvis/app · fictional data · no registration
↓
RUNG 3 · START
independently or together
Start independently, or first tailor it together You choose a plan and start independently NL. If business agreements or customisation are involved, we go through four things together: the use case, individual, team or multiple brains, the plan, the sources and AI accounts required, and the agreements concerning terms, privacy role and price. If it is not a good fit, we will say so, and the template from rung 1 is then a perfectly good final destination. $ order Start and Solo online · book a call to discuss team plans
# the rungs are ascending but not compulsory: rung 1 remains free and complete, even if you never go any further.
$ cat plannen.mdpay for your brain, not per AI query
Brain Start €9 /month incl. tax 1 organisation brain · 1 user · 2 AI employees
Brain Solo €29 /month incl. tax 1 organisation brain · 1 user · 3 AI employees
Brain Team €99 /month incl. tax 1 organisation brain · 5 users · 10 AI employees
Brain Business €249 /month incl. tax 3 organisation brains · 20 users · 50 AI employees

The cards show Dutch monthly prices for individuals, including VAT. You pay for your AI app and model usage separately. Compare Jarvis plans.

~/jarvis/werking/07-further-reading[ok]
Section 07 · Further reading

Where the evidence is

This page describes how it works. Every promise made here has a document or screen somewhere that explains it in detail. Below you can see where it is, sorted by what you want to know.

We provide the AI employee through Mansotti, the company of which TheSEO is the trading name, with the same core rule as above: output remains a draft until a person approves it. That is a different proposition from Jarvis. Jarvis manages the memory and coordination of the AIs you already have; the AI employee is for anyone who wants to hand over a recurring task completely.

$ jarvis --interactief # seven questions, seven answers
DOC.07 · FAQ

Frequently asked questions

How does an AI organisational brain work, in brief?

In five phases. A task is recorded with its objective and owner. The brain determines which sources are permitted for that role and scope. The work goes to the appropriate AI role, which produces a draft with evidence. A human approves the exact version before anything is released externally. Only then does approved knowledge become part of the memory, together with its source, scope, version, validity, status and approval. Each phase leaves an entry in the log.

What is the difference compared with ChatGPT's or Claude's memory?

An AI tool's memory resides in that tool and that account. If you switch tools, or a colleague joins in, it starts again. An organisational brain sits alongside them and passes the same core knowledge and agreements to every connected AI, together with roles, provenance and approval. You retain your own subscriptions with your own provider; the brain does not replace them, but supplements them.

What exactly is contained in a memory item?

The text itself plus six fields. Source, with the file, system, owner and a traceable reference. Scope, meaning who it applies to. Version, with a content hash, reason for the change and the previous version. Validity, with the effective date, expiry date and review point. Status, one of five states: proposed, under review, active, conflicting or superseded. And approval, with the authorised actor, the time and the exact version that was approved.

What is logged and what specifically is not?

Logged: request ID, time, actor, organisation and route, changes to authentication, roles, connectors and subscription entitlements, the versions of sources, memory items, agents and approvals, the tool action with result status, duration and error category, and support access, export, deletion and incident status. Not logged by default: full prompts and answers, document contents, API keys and tokens, payment card details and special categories of personal data. If content logging is temporarily required for an incident, it is assigned a purpose, an owner, a time limit, access controls and proof of deletion.

Can the brain send something without my knowledge?

No. Email, publication, contract changes and payments are subject to the agreed human approval, and until that approval is given, output remains a draft. An approval points to an immutable version, is checked server-side against the role and scope, and has a consequence that can occur only once, so the same approval cannot accidentally cause two emails to be sent. The time, actor, reason and any revocation are recorded.

Does knowledge from different customers remain separate?

Yes, that is a product principle: customer brains are logically isolated, there is no unrestricted exchange between brains and customer content is not used for training. The TheSEO superbrain can offer generic improvements as a proposal, but a customer brain never adopts them silently across the organisation, and customer content does not flow back automatically. The negative test set intended to demonstrate this in production is still outstanding, and we explicitly state that alongside it.

How much does it cost and how do I get started?

Start costs €9.00 and Solo costs €29.00 per month including VAT for individuals. Business prices are €7.44 and €23.97 per month excluding VAT. You can try the free template or the demo first. When you choose a plan, you see the amount, subscription period and terms before paying. Compare Jarvis plans. Book a call.

DOC.08 · Next step

And now

If you take one thing away from this page, let it be this: the difference between a smart AI and a useful organisational brain lies not in the answer, but in the question you can ask afterwards. Where did this come from, who approved it, and since when has it applied? As long as you cannot answer those questions, AI remains a tool for drafts. Once you can answer them, you can entrust it with work for which someone is responsible.

Section 08 · Next step24/7 accessible · sales@theseo.nl
Schedule a conversation ↗ NL
$ whoami
Written by GianlucaFounder. Has been building visibility for Dutch businesses since 2017, in Google and in AI answers. More about the institute.

Product boundaries

What is the current Start/Solo workspace?

A personal document workspace for one user and one brain, with text and Markdown, document history and explicitly authorised AI connections. Your own AI subscription remains separate.

Are the twelve demo screens included?

No. The public concept demo presents a broader organisation system with fictional data. Team work, autonomous tasks and team approvals are not included in Start or Solo.

Where can I see whether ordering is available?

On the current product page. An order button appears only for a matching available offer from the current catalogue. This documentation and the machine-readable price source do not enable sales.

Existing documentation and sources

Back to the short version