LiveAI agent foundation

AI supplies the judgement; LiveBPM guarantees reliable execution. Eight layers of capability add understanding, extraction and judgement to every step of a process, while every change of business state is still made by the deterministic engine under human authorisation.

Key points
  • LiveAI is our enterprise agent foundation; all eight layers L1–L8 are shipped
  • AI never changes business state; it produces evidence-backed recommendations and confirmation items
  • Four authorisation levels L0–L3, widened or tightened by measured data
  • Three levels of degradation; on-premise or masked-API data modes
Design principle

AI never changes business state

What it changes is the information a person has when they decide.

The system is cut in two. Anything that changes state, records an amount, writes an approval or moves a document is executed by the process engine. Anything that judges whether something is reasonable, how risky it is, or which policy applies is handled by an agent, which returns a recommendation with its evidence, attached to the process instance as structured data.

Even if an agent hallucinates, is manipulated by prompt injection, or drifts after a model upgrade, the worst it can do is produce a wrong recommendation that a person rejects. It cannot change the amount on an order.

What a recommendation looks like

Conclusion: this quotation is 7.8% above the cost pass-through baseline, outside the 5% tolerance. Review suggested.

Evidence: (1) raw material index up 3.1% quarter on quarter, external data, two days old. (2) comparable quotations from other suppliers up 2.4% over the same period. (3) this supplier's twelve-month delivery rating: A.

Applicable policy: Procurement Management Rules, clause 6.3, price anomaly review.

Suggested actions: request a cost breakdown; compare with the second bidder; or keep the price and record the reason.

Confidence 0.86, with the numeric part computed deterministically. Authorisation L2, explicit confirmation.

Eight layers

LiveAI L1–L8

All eight layers are shipped and carry production scenarios. New capabilities follow the same rule: validated in a sandbox first, then admitted to delivery scope.

L1Shipped

Model access and routing

OpenAI-compatible protocol, routing by data classification; sensitive data to a dedicated instance, general traffic to a public API.

L2Shipped

Data ingestion and classification

Connects internal systems and external sources, tagging sensitivity field by field to drive masking and routing.

L3Shipped

Anti-hallucination grounding

Full RAG pipeline. Anything uncertain is marked as unstated rather than invented, and every conclusion traces back to source text.

L4Shipped

Information extraction

Multi-format documents into structured data with field-level confidence; low-confidence results routed to human review.

L5Shipped

Rule engine

Hard rules implemented as code rather than prompts: no hallucination, reproducible, auditable.

L6Shipped

Tool wrapping and agents

System operations wrapped as tools, natural-language querying across databases, multi-step task orchestration.

L7Shipped

Human-machine collaboration

Review routing, approval records and write-back, connected directly to LiveBPM work items and approvals.

L8Shipped

Governance and observability

Sensitivity tagging, PII detection, lineage auditing, fabrication guards, cost quotas and compliance boundaries.

Continuing above the eight layers: multi-agent orchestration and task decomposition, an industry template library, and appliance-style on-premise packaging. Time-series forecasting, computer vision and classical machine learning sit outside L1–L8 and are scoped separately.

Four delivery patterns

Ten scenarios, without a new line of foundation code

All of them assembled from the eight layers by configuration. Business logic lives in configuration; the foundation stays generic.

Extraction · unstructured to structured

Field-level extraction from contracts, supplier documents, invoices and forms, with confidence scores and source positions.

Question answering · querying and explaining across systems

Natural-language questions across databases, with an explicit refusal when the data is insufficient rather than an invented answer.

Scoring · grading and normalising by rule

Classification, definition alignment and valuation recomputation. Calculation runs deterministically and can be reproduced.

Review · clause-by-clause comparison

Contract alignment, policy comparison and applicability checks, answering what matters about this specific document.

Human on the loop

Four levels of authorisation

Graded by consequence and confidence, each level mapping to a different process engine configuration. Most agents sit at L1 or L2; L0 is used only where no money is involved.

LevelNameRelationshipTypical useEngine configuration
L0AutomaticAI acts; reviewable afterwardsDue-date reminders, document generation, OCR pre-fill, scheduled exception listsSystem step, logged only
L1Silent recommendationAccepted by default, reversible at any timeRanking, suggestions, field mapping, first-pass classificationAutomatic step plus record, one-click revert
L2Explicit confirmationA person must confirm the judgementException interception, variance alerts, tolerance breaches, clause deviationsCreates a work item; overriding requires a reason
L3Human-ledAI supplies material onlySupplier removal, major contract award, budget exceptionsMulti-level countersign; AI output is an attachment

Autonomy is earned

The system records acceptance rate, revision rate, override rate with reasons, and post-hoc accuracy for every class of judgement. Three consecutive months above the threshold with no serious error can move a judgement from L2 to L1; a rising override rate escalates it automatically and triggers a knowledge review.

Every interaction is training data

When an agent proposes and a person overrides with a reason, that record is at once a negative example, a piece of tacit organisational knowledge and a candidate rule. Keeping it structured turns judgement into an asset that survives staff turnover.

Governance

We answer the AI-specific risks up front

RiskWhat it looks likeHow it is controlled
Data sovereigntyWhether business data, policies and customer information leave the companyFully on-premise deployment supported; in API mode a model gateway enforces masking under a data processing agreement. The customer chooses.
HallucinationConclusions that read well but are wrongEvidence chain and sources mandatory; numeric conclusions computed deterministically; critical judgements cross-checked by two models; L2 and above require human confirmation.
Prompt injectionMalicious instructions embedded in external textExternal input filtered; prompt templates strictly separated from user data; agents hold no write access to master data, so manipulation causes no material loss.
Behaviour driftJudgement changes after a model upgradeModel versions under configuration management, with a golden test set of real historical cases regressed automatically on every upgrade.
Runaway costCall volume spikesQuotas and budget alerts per agent and per organisation; batch work off-peak; simple tasks on small models, complex judgement routed to larger ones.
ExplainabilityBeing unable to explain a decision to an auditorEvery call recorded: input snapshot, retrieved knowledge, model version, conclusion, confidence and the human outcome. Fully replayable.
FAQ

LiveAI questions

What is LiveAI?

LiveAI is our enterprise agent foundation. It has eight layers: model access and routing, data ingestion and classification, anti-hallucination grounding, information extraction, a rule engine, tool wrapping and agents, human-machine collaboration, and governance and observability. It adds extraction, review, scoring and question-answering to each step of a process.

Can the AI change business data or approve on its own?

No. LiveAI never changes business state. It can read process context, write a recommendation with its evidence, and create a work item for a person to confirm. In L0 authorisation it may trigger reminder-type helper flows. State changes, amounts and approval records are always executed by the LiveBPM engine under human authorisation.

What happens when the AI is wrong or hallucinates?

Every judgement carries an evidence chain and its data sources. Numeric conclusions are computed deterministically rather than generated by a model. Critical judgements can be cross-checked by two models. Anything at L2 or above requires explicit human confirmation. In our ten-scenario validation, confidence-based routing and the rule engine together intercepted 75% of the error cases before they reached a user.

Does the business stop if the AI service is unavailable?

No. The intelligence layer and the business layer are physically decoupled, with three levels of graceful degradation: a single failing agent simply hides its recommendation; if the model service is down the system falls back to pure rules; if an external data source is down the most recent cache is used and clearly marked as stale. Process integrity is guaranteed by the engine, not by the AI.

Does our data leave the company or train public models?

Fully on-premise deployment is supported, in which case no data leaves your environment. In API mode traffic passes through a model gateway that enforces masking, under a data processing agreement. The model layer speaks the OpenAI-compatible protocol, so sensitive data can be routed to a dedicated instance. Customer data is not used to train public models.

What is the four-level authorisation model?

AI actions are graded by consequence and confidence: L0 automatic execution, L1 silent recommendation, L2 explicit confirmation, L3 human-led. Most agents sit at L1 or L2. The level is widened or tightened based on measured acceptance rate, override rate and post-hoc accuracy, not on opinion.

See all FAQs and the glossary →

Want to know what AI can and cannot do in your processes?

Send us your policy documents and a few sample documents. We will tell you which judgements suit an agent and which must stay with a person.