SenangAI — your data, your infrastructure, your control
Home · Use cases
Sovereign AI · the agentic team

Teamspaces for the work, not the org chart.

A teamspace can be a department, a project that closes when the work does, or a standing group that cuts across several functions. People collaborate inside the one that matches what they are actually doing — and each space runs as many agents as it needs, all under the same scope, approval and audit.

ATProject AtlasPROJECTLegal + finance + engineering+ agents as neededMKMarketingDEPARTMENTClaims checked against source+ agents as neededENEngineeringDEPARTMENTRunbooks, incidents, decisions+ agents as neededESCustomer escalationsSTANDINGSupport, delivery and legal+ agents as neededRCRisk & complianceDEPARTMENTEvidence produced as work runs+ agents as neededVMVendor migrationPROJECTCloses when the cutover does+ agents as neededFIFinanceDEPARTMENTFigures traced to their source+ agents as neededLGLegalDEPARTMENTClauses, playbook, obligations+ agents as neededSenangAIOne governed platformPersonal · teamspace · organisationCompany knowledge + agent orchestration
  • Project AtlasProjectLegal + finance + engineering — 6 agents today, more whenever the work needs them.
  • MarketingDepartmentClaims checked against source — 3 agents today, more whenever the work needs them.
  • EngineeringDepartmentRunbooks, incidents, decisions — 5 agents today, more whenever the work needs them.
  • Customer escalationsStandingSupport, delivery and legal — 4 agents today, more whenever the work needs them.
  • Risk & complianceDepartmentEvidence produced as work runs — 4 agents today, more whenever the work needs them.
  • Vendor migrationProjectCloses when the cutover does — 2 agents today, more whenever the work needs them.
  • FinanceDepartmentFigures traced to their source — 5 agents today, more whenever the work needs them.
  • LegalDepartmentClauses, playbook, obligations — 4 agents today, more whenever the work needs them.
Everyone starts with oneEach person arrives with a personal agent in their own private scope.
Teamspaces run as many as they needAdd an agent per workflow, per matter, per client. There is no cap and no per-agent fee.
All of them inherit the same controlsWhether there are three agents or three hundred, every one is scoped, approved and audited alike.
How teams are organised

A teamspace is whatever the work is.

Most tools make you collaborate along the org chart, which is rarely where the work happens. A teamspace is drawn around a piece of work instead, so the people who need the same knowledge share the same boundary — whether that lasts a decade or a quarter.

Department

The permanent kind. Legal, finance, engineering, risk — a stable group with material that stays theirs, and agents that mature over years rather than weeks.

Lasts as long as the function does.

Project

Temporary and deliberately cross-functional. A migration, an acquisition, a product launch — legal, finance and engineering working from one shared boundary, which closes when the work does.

Archived or deleted at the end, with its agents.

Standing group

Permanent but cross-functional. Customer escalations, vendor review, incident response — a recurring problem that never belonged to a single department in the first place.

Outlives any one project.

People belong to as many teamspaces as their work requires, and see only what each one permits. Joining a project does not widen what someone can read elsewhere, and leaving it closes that access cleanly.

Finance & procurement

Every number traceable to the thing it came from.

Finance questions are rarely about the number. They are about which entries moved it, which of those were approved, and whether anyone should have noticed sooner. This is a reconciliation problem across ledgers, invoices, contracts and email, and it is exactly the shape of question a knowledge graph resolves and a search index does not.

Reconcile a figure to source documents
Route invoice checks through an approval step
Enforce a spend budget on the AI itself
Month-end narrative drafted, then reviewed
Finance & procurementGoverned
“Why did this cost centre move 18% this quarter?”
GL export · Q3Vendor invoice #4471Change approval
IT & engineering

Institutional memory that survives the people who left.

The answer usually exists — in a two-year-old incident review, a decision record nobody indexed, or the head of an engineer who has since moved on. Connecting runbooks, incident history and architecture decisions turns that into something answerable at three in the morning, without granting an external tool access to production.

Answer from runbooks and incident history
Architecture decision records stay linked to systems
On-premises deployment keeps sources internal
Agents scoped per team, never global
IT & engineeringGoverned
“Has this failure mode happened before?”
Incident #2291ADR-014Runbook · failover
Risk & compliance

Evidence on demand, not evidence assembled in a panic.

Most AI governance conversations end with a promise to produce records later. Ours starts with them. Every event is recorded as it happens and linked in the graph to the person, the scope, the sources and the model involved — so “show me everything about this decision” is one question, not a week of log correlation. Denied attempts are captured too, and they are usually the records an auditor most wants to see.

Denied attempts recorded, not silently dropped
Approval decisions carry the approver and rationale
Model routing and cost logged per request
Records exportable for review
Risk & complianceGoverned
“Show me every denied access attempt this month.”
Audit event · deniedScope policyApprover log
People & operations

The current policy, not the version saved in 2023.

HR questions are high volume, low complexity and unusually sensitive — the wrong answer is a grievance and the wrong retrieval is a confidentiality breach. The graph links each policy to its versions, effective dates and regional addenda, so the answer cites the version in force on the date that matters. Personal scope keeps individual cases private while organisation scope answers the policy question.

Answers cite the handbook version in force
Personal scope keeps individual cases private
Region-specific policy resolved correctly
No retrieval from restricted case files
People & operationsGoverned
“What is our parental leave policy in this region?”
Handbook v9 · §4Regional addendumEffective date
Sales & customer teams

What was promised, by whom, and whether it shipped.

Account context is scattered across the CRM, the contract, delivery tickets and a year of email. Before a renewal call, the useful version of that is one paragraph with citations, scoped to the account team, assembled without exposing other customers. That is a permissions problem as much as a retrieval one.

Account history assembled and cited
Scoped to the account team, not the company
Commitments matched against delivery state
Brief generated ahead of the call
Sales & customer teamsGoverned
“What have we promised this customer already?”
MSA · Schedule BDelivery ticket #88Renewal notes
Underneath

Five patterns, every function.

The teamspaces differ — some permanent, some closing next quarter. The shape of the problem does not, which is why one governed platform serves all of them, and why adding your tenth or hundredth agent needs no new security review.

RetrieveFind the passage that settles it, from sources this person is permitted to read, with the citation attached.
ConnectLink documents, people, decisions and obligations into one graph, so the entities relate rather than merely co-exist.
ReasonFollow those connections to answer “why”, “who decided” and “what depends on this” — questions no single document contains.
ActDo the next thing — draft, file, notify, generate — behind an approval step a person controls.
ProveProduce the record afterwards: what was asked, retrieved, approved, which model ran, what it cost.
Getting started

Start with one. Add the rest freely.

The best first agent answers a question your organisation argues about regularly, where the sources exist but nobody can assemble them quickly. Once that one is trusted, the next twenty cost you nothing but the time to build them.

Start with one governed use case

Bring the question your organisation keeps arguing about.

Thirty minutes. We will map one use case, demonstrate scope isolation, and show the audit evidence the platform produces — or tell you plainly that you do not need us yet.