Agents
Two agents over one audited core. Arin runs operations and escalates only the decisions that need your judgment; PECO turns plain-language requests into confirmed, repeatable automations. Every action lands on the same immutable record.
Two agents, one record
The idea
Agents run the routine work inside a policy envelope and surface only what needs a human - each escalation already reasoned through, each action confirmed and written to the same immutable record a person would use. Nothing runs off the books.
same authorization - same record - regardless of who acted.
In plain terms
Most AI in enterprise software stops at suggestion: it drafts, summarises and answers, then hands the work back to a person to re-enter somewhere else. The Splenta platform is built the other way round - the agent does the work in the real system, and the person handles what the agent should not decide alone.
It is software that runs day-to-day operational work autonomously inside a policy you set, rather than assisting a person who runs it manually. The agent reads the same records your team reads, takes the same actions through the same authorization, and stops at the boundary you draw. Arin, PECO and Semorel are three ways of applying that idea - continuous operation, in-app automation, and agent access to your own product.
A chatbot produces text and leaves the system unchanged; you still perform the action. These agents perform the action and write it to the record. The difference shows up in the failure case: a chatbot that is wrong wastes your time, whereas an agent that acts must be governed - which is why every action runs through scoped authorization and lands on an append-only ledger that shows who or what acted.
Arin is a single-tenant agent that runs a function continuously - it works procurement in the background, handles the routine within policy, and hands you only decisions that genuinely need judgment. PECO lives inside an application: a plain-language assistant plus a visual builder over one shared action model, so a request becomes a confirmed, repeatable automation. Semorel is a drop-in client-side SDK that lets a trusted agent read what is on screen in your own app and invoke its actions in-session.
Human and agent actions carry the same weight in the audit trail. There is no side channel where automation happens off the books and gets reconciled later. Every action is attributable, replayable and scoped by the same authorization model, which is what makes it defensible to an auditor rather than merely convenient to operations.
No. Autonomy is a setting, not a commitment. Agents run at the level you configure - observe only, propose, act with confirmation, or act within policy - and the boundary is enforced by scoped tokens rather than by prompt instructions. Teams typically start in observe mode on one workflow and widen the envelope as the escalation quality proves itself.
An agent can only be governed if the thing it acts on has a real record and a real permission model. Where that exists, the platform connects to it. Where it does not, the Agentic Enterprise modules provide it - which is why the systems of record and the agent layer are designed together rather than sold as unrelated products.
▷ agentescalate.review→NEEDS YOU
We're onboarding design partners putting agents on their real operations - where the routine work runs itself and only the exceptions reach a person. Tell us what your team does by hand today.
