How it works

Learn the client's SAP, then resolve it safely.

It starts with an assessment that maps how that client's SAP actually works into a knowledge graph. The agents reason over that graph, and every action they propose is gated by policy before anything happens. Tessera federates across your systems rather than replacing them.

Learning loop · resolved outcomes compound the per-client memory SOURCES SAPS/4HANA · BW/4 · BTP ServiceNowITSM · incidents IdentityIdP · roles · SoD Ticket historythe agents' learning input Policies & controlschange mgmt · SoD · runbooks FEDERATION Connect IDoc OData RFC/BAPI CPI · BTP queried in place residency controls KNOWLEDGE CORE Semantic graph46 entities · 50+ relations Resolution memoryper-client · compounding Retrieval + groundingevidence for every claim NEURO-SYMBOLIC ENGINE Neural · agent reasoning reads the ticket + graph context proposes a specific action confidence score + cited evidence proposes re-reason Symbolic · policy engine allowlist · segregation of duties environment · confidence threshold deterministic verdict by risk tier not overridable by model output ACTION & SURFACES Auto-resolve Act & log Human approval Block & escalate Surfaces Command center Copilot Reports · audit UI GOVERNANCE & AUDIT · spans every stage Immutable audit · RBAC / ABAC + segregation of duties · Per-client data isolation · Shadow mode before execution · Rollback & kill switches
01 · Integration

Connectors to SAP (S/4, BW/4, CPI and BTP, IDoc, OData, RFC and BAPI), ServiceNow, and identity. Data is queried where it lives; copied only when necessary, within residency controls.

02 · Knowledge

A SAP-AMS knowledge graph and semantic layer, per-client resolution memory, and retrieval indexes that ground every recommendation in your own history.

03 · Agent runtime

Config-driven agents orchestrated through supervisor and graph patterns, with a risk-tiered action model and human-in-the-loop approval queues.

04 · Experience & control

Command center, copilot surfaces, assessment reports, governance and audit dashboards, and cost attribution.

Knowledge graph

A ticket carries its full context.

Incidents, IDocs, orders, configuration, partners, plants, error signatures, and business KPIs live in one semantic model. So when a delivery block arrives, an agent already knows the order, the partner, the interface, the recurring signature, and the KPI it threatens, instead of rediscovering it.

Built during the assessment: 46 entity types and 50+ relationships, plus per-client resolution memory that compounds with every fix.

ErrorSigVKM block Incident IDoc Order Partner Plant KPIDSO Playbookcandidate
representative graph fragment · O2C credit-block signature
Neuro-symbolic governance

An agent proposes. Policy decides.

A language model is good at reading a messy ticket and reasoning toward a fix. It is the wrong thing to trust with a production change on its own. So every action an agent proposes passes through a deterministic policy engine before anything happens.

Reason

Agent proposes

The agent reads the ticket and graph context and proposes a specific action with a confidence score and cited evidence.

Evaluate

Policy engine

Deterministic rules check it:

  • action on the allowlist
  • segregation of duties
  • environment permitted
  • confidence above threshold
Gate

Decision

Auto-resolve, require human approval, or block and escalate, by risk tier. Every decision is recorded with its inputs and the rules applied.

The policy engine is deterministic and is not overridable by model output or prompt content.

Governance

Safe to put in your client's production.

Action is gated by risk. Higher risk means more oversight, never less. This is what lets an SI put agents near production SAP at all.

RiskWhat the agent doesExamples
LowAuto-resolve within allowlistPassword reset, known IDoc reprocess
MediumAct and logJob restart, queue clear
HighRequire human approvalRole change, credit release
CriticalBlock and escalateProduction config, security grants
  • Human-in-the-loop approval queues, with shadow mode before any execution
  • Role- and attribute-based access, with segregation of duties enforced
  • Source attribution and confidence on every recommendation
  • Immutable audit of every agent decision and human approval
  • Per-agent and global rollback and kill switches
  • Per-client data isolation; one client's knowledge is never shared with another
The runtime

What makes agents safe to deploy.

Swipe to explore
Connectivity

Reaches your systems

Federated access to SAP (S/4, CPI and BTP, IDoc, OData, RFC, BAPI), ServiceNow, and identity, querying data where it lives.

Memory

Knowledge that stays

Every validated resolution becomes reusable, versioned, and attributable, isolated to each client tenant.

Execution

Acts within limits

Calls SAP via APIs, BAPI, and OData, with RPA only where no interface exists, never beyond the allowlist.

Deployment

Where you need it

SaaS, private cloud, or fully isolated for regulated estates, one control surface everywhere.