ERP that already did the thinking.
Eleven engines, and not one of them allowed to overstate what it found.
Eleven reasoning engines and eleven platform services, native to every ERP object, permission and workflow you already run. Not one model asked to do everything — eleven, each with one job and one boundary, composed by a runtime that will not let any of them overstate what it found.
Eleven engines, because the guarantees are different.
One general-purpose model asked to do all of this would give you the same shrug for an arithmetic question and a causal one. Cobalt ERP separates them, because what you are entitled to trust differs: arithmetic is reproducible, a mined pattern is an association, a forecast carries an interval, and an optimiser has to tell you whether a plan is merely feasible or provably best.
Eleven engines, each with one job
Not one model asked to do everything. Each engine has a single responsibility and a single kind of output, and the runtime composes them — they never call each other.
Reasoning engine
Deterministic and policy intelligence
Arithmetic, tax rules, eligibility, hard constraints
Finding
Analytical and data-mining intelligence
Cohorts, associations, outliers, change points
Mining insight
Predictive machine learning
Forecasts, probabilities, calibrated intervals
Prediction
Process and task intelligence
Discovery, conformance, bottlenecks, rework
Process insight
Computational intelligence and optimisation
Constraint solving, scheduling, multi-objective choice
Optimisation proposal
Simulation and scenario intelligence
Monte Carlo, discrete-event, sensitivity, stress
Simulation result
Knowledge graph and semantic intelligence
Typed relationships, lineage, dependency traversal
Graph traversal
Retrieval and enterprise memory
Permission-aware lexical, vector and prior-case search
Retrieval evidence
Document and multimodal intelligence
Text recognition, layout, tables, extraction, comparison
Extraction candidate
Language and conversational intelligence
Intent, clarification, grounded explanation
Explanation
Decision, recommendation and causal intelligence
Safe-candidate ranking, arbitration, uplift, causal analysis
Recommendation
Eleven pages, one per engine.
How each one works, what it emits, the boundary it holds, and the questions it answers.
What each one is not allowed to claim.
Every engine ships with a boundary as well as a job. The boundaries are the reason the output is usable on a ledger.
- Deterministic and policy is the only engine that may block or permit a transition, and only through rules that already exist in the domain.
- Data mining reports association. It is never rendered as causation — and no language model is permitted to reword it into one.
- Predictive machine learning is advisory derived data. It never carries permission, ledger, tax or approval authority.
- Process mining observes what happened. Observed practice does not redefine the permitted process.
- Optimisation must distinguish feasible, best-known and proven optimal, and may never quietly relax a hard constraint into a soft penalty.
- Simulation produces a scenario. A scenario is not a forecast, a commitment or an authorisation.
- Knowledge graph is derived and rebuildable — never the authority for a transaction. Inferred links stay separate from asserted ones.
- Retrieval returns evidence, and permissions are re-checked after reranking, not before.
- Document intelligence produces candidates. They stay candidates until validated or accepted by a person.
- Language may not write database queries of its own, write to the database, invent a calculation, or state a claim it cannot support.
- Decision and causal ranks only what deterministic filtering has already declared safe. A score is not permission, and a causal claim needs a defensible identification strategy.
Engines never call each other. The runtime composes them.
A compiled recipe decides which engines run, in what order, and what happens when one abstains. That indirection is what keeps each engine's guarantee intact all the way to the screen.
How Cobalt Intelligence thinks
Every question is answered by the combination of engines that can actually answer it. This is which ones each of eight real questions calls, which one leads, and what it hands to next.
| Question asked on a live record | Intelligence engines used | Lead engine & chain | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Question | Deterministic | Data Mining | Machine Learning | Process Mining | Optimisation | Simulation | Knowledge Graph | Retrieval | Document | Language | Causal Inference | Lead engine |
| Can we promise this order by Friday?Quote to cash · Sales order | Deterministic: primary engine | Data Mining: not used | Machine Learning: primary engine | Process Mining: not used | Optimisation: primary engine | Simulation: supporting engine | Knowledge Graph: supporting engine | Retrieval: primary engine | Document: not used | Language: not used | Causal Inference: supporting engine | DeterministicDeterministic → Causal7 / 11 |
| Why did this quote lose margin?Quote to cash · Pricing | Deterministic: primary engine | Data Mining: primary engine | Machine Learning: supporting engine | Process Mining: not used | Optimisation: not used | Simulation: not used | Knowledge Graph: primary engine | Retrieval: not used | Document: not used | Language: supporting engine | Causal Inference: supporting engine | Data MiningData Mining → Deterministic6 / 11 |
| Which supplier should we buy this from?Procure to pay · Sourcing | Deterministic: primary engine | Data Mining: supporting engine | Machine Learning: primary engine | Process Mining: not used | Optimisation: primary engine | Simulation: supporting engine | Knowledge Graph: primary engine | Retrieval: not used | Document: not used | Language: supporting engine | Causal Inference: supporting engine | OptimisationOptimisation → Deterministic8 / 11 |
| Where does our order process actually stall?Procure to pay · Process | Deterministic: supporting engine | Data Mining: primary engine | Machine Learning: not used | Process Mining: primary engine | Optimisation: not used | Simulation: not used | Knowledge Graph: not used | Retrieval: supporting engine | Document: not used | Language: supporting engine | Causal Inference: not used | Process MiningProcess Mining → Language5 / 11 |
| What happens to cash if Redlands slips two weeks?Finance · Scenario | Deterministic: primary engine | Data Mining: not used | Machine Learning: supporting engine | Process Mining: supporting engine | Optimisation: not used | Simulation: primary engine | Knowledge Graph: primary engine | Retrieval: not used | Document: not used | Language: supporting engine | Causal Inference: supporting engine | SimulationSimulation → Causal7 / 11 |
| Pull the totals off this supplier PDFProcure to pay · Bill inbox | Deterministic: primary engine | Data Mining: not used | Machine Learning: not used | Process Mining: not used | Optimisation: not used | Simulation: not used | Knowledge Graph: supporting engine | Retrieval: supporting engine | Document: primary engine | Language: supporting engine | Causal Inference: not used | DocumentDocument → Deterministic5 / 11 |
| What does our returns policy say about this?Service desk · Policy | Deterministic: supporting engine | Data Mining: not used | Machine Learning: not used | Process Mining: not used | Optimisation: not used | Simulation: not used | Knowledge Graph: supporting engine | Retrieval: primary engine | Document: not used | Language: primary engine | Causal Inference: not used | RetrievalRetrieval → Language4 / 11 |
| Which customers are about to churn?Subscriptions · Revenue | Deterministic: not used | Data Mining: primary engine | Machine Learning: primary engine | Process Mining: supporting engine | Optimisation: not used | Simulation: supporting engine | Knowledge Graph: supporting engine | Retrieval: supporting engine | Document: not used | Language: supporting engine | Causal Inference: primary engine | Machine LearningMachine Learning → Causal8 / 11 |
Cobalt Intelligence selects and orchestrates the combination of engines that can answer the question in front of it — a compiled recipe, not a routing guess, and never a ranking before the deterministic safety filter has run.
What each engine gives the others.
The value is in the composition, not the list. A forecast without graph context is guessing about the wrong entity; an optimiser without the forecast's uncertainty plans for a number that will not hold; a recommendation without deterministic filtering is a liability.
- Deterministic supplies the hard constraints, validators and safe candidates every other engine works inside — and mined exceptions can propose new rules, but only for a person to ratify.
- Knowledge graph supplies relationship context and prunes candidates, so prediction and optimisation start from the right entities.
- Process mining supplies actual flow state, variants and where the delay really is — which is what optimisation needs for capacity.
- Predictive machine learning supplies probabilities and intervals; simulation takes those distributions and stress-tests the plan built on them.
- Retrieval supplies the cited policy and the prior case; document intelligence supplies candidate facts that deterministic validation confirms.
- Language is last, not first — it presents what the others established, using typed tools and their evidence.
- Decision and causal arbitrates between objectives, and records exposure so the effect of its own recommendations can be measured later.
One core, every module, the same eleven engines.
A module does not fork the intelligence core — it plugs into it, contributing what a subject is and what counts as an observed outcome. Everything else, from drift monitoring to the accuracy report, derives automatically from one registration.
Every module runs on the same eleven engines
A module does not fork the core or bring its own model. It plugs into the same eleven engines every other module uses, and the recipe for its questions decides which of them run.
| Business area | Engines it runs on | Engines | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Business area | Deterministic | Data mining | Machine learning | Process mining | Optimisation | Simulation | Knowledge graph | Retrieval | Document | Language | Causal | Count |
| Finance & accountingClose, controls, reporting | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Customer relationshipsOpportunities, accounts, activity | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Quote to cashPricing, promise, fulfilment | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Subscriptions & revenueRenewal, churn, recovery | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Procure to paySourcing, matching, contracts | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Inventory & planningDemand, safety stock, transfers | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: not used | 10 of 11engines composed |
| WarehouseWaves, slotting, workload | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: not used | 10 of 11engines composed |
| Distribution & fleetRoutes, arrival time, cost to serve | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: not used | 10 of 11engines composed |
| ManufacturingShortage, sequence, yield | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Field serviceScheduling, first-time fix | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Service deskClassification, service level, resolution | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| People and payrollPolicy help, intake, checks | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
| Master data managementDuplicates, resolution, gaps | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 10 of 11engines composed |
| Fixed assetsLifecycle, revaluation | Deterministic: used | Data mining: used | Machine learning: used | Process mining: used | Optimisation: used | Simulation: used | Knowledge graph: used | Retrieval: used | Document: used | Language: used | Causal: used | 11 of 11engines composed |
The chain behind each module's headline capability.
- Quote to cash — conversion, margin leakage, promise confidence and fulfilment alternatives, from mining and prediction through graph, then simulation and optimisation, filtered deterministically and ranked.
- Procure to pay — supplier lead time, sourcing comparison, contract leakage, order consolidation and the expedite trade-off.
- Inventory — demand class, safety stock, obsolescence, transfers and a service-level what-if, ending in a draft transfer or requisition.
- Finance — close readiness, control breaks, anomaly evidence and run-rate scenarios, with the ledger untouched by any of it.
- Manufacturing — material shortage, sequence, yield and work-in-progress variance, as a planner proposal validated against hard constraints.
- Distribution — arrival-time risk, route and load plans, failed-delivery patterns and cost to serve, as a feasible dispatch proposal.
- Service desk — classification, service-level risk, repeat clusters and a cited resolution drawn from prior cases.
- Master data — duplicates, entity resolution, configuration gaps and change-impact analysis, into a maker-checker merge proposal.
A bounded run, and a gate no step crosses on its own.
An agent in Cobalt ERP is not a model with tools and a long leash. It is a task with a budget, a plan compiled from registered skills, and a verifier that is not allowed to be the thing that did the work.
A bounded run, and the gate in the middle of it
Nine steps, and nothing crosses the middle of them on its own. The planner cannot reach a tool, the verifier is not allowed to be the thing that did the work, and between staging and applying everything is resolved again from scratch.
- 1
Bounded task
one goal, one budget
- 2
Live context
actor, permission, entity resolved
- 3
Plan compiled
from registered skills only
- 4
Reads execute
typed results checkpointed
- 5
Proposal staged
preview and fingerprint
- 6
Human approves
or a named automation policy
- 7
Re-resolved
permission, duties, fingerprint again
- 8
Domain service
the same one a person would use
- 9
Verified
independently, against the success question
Granted per skill, per tenant, one level at a time.
Eight levels, granted per skill and per tenant
Autonomy is not a switch. It is eight rungs, admitted one skill at a time for one workspace at a time, and the top three need a named policy or a person before anything is applied.
From here a person or a named policy is required
Eleven services that make the engines governable.
An engine nobody measures is not an asset. These carry the contracts, the context, the evidence, the evaluation and the kill switches — and every capability registers once, so nothing can be scored while quietly escaping drift monitoring.
Eleven platform services, which is what makes them governable
An engine on its own is a library. These are the services that give it a contract, a scope, an audit trail and somewhere to be switched off.
Platform service
Contracts and schema registry
Versioned artifact schemas and adapters
Versioned schemas
Capability catalogue and domain kit
Manifests, registration, reachability checks
Capability manifests
Context, semantics and scope
Tenant, actor, entity, book, period, permission
Permission scope
Fact, event and dataset plane
Point-in-time facts, events, frozen datasets
Frozen datasets
Composition and decision runtime
Recipe compilation, arbitration, abstention
Compiled recipes
Job, worker and serving runtime
Ledger, scheduled work, batch scoring
Job ledger
Artifact, model and knowledge registries
Models, datasets, ontologies, playbooks, indexes
Versioned artifacts
Outcomes, evaluation and lifecycle
Drift, promotion, demotion, retirement
Drift and promotion
Evidence, provenance and explainability
Sources, lineage, citations, receipts
Lineage and citations
Security, privacy, egress and actions
Isolation, egress, duties, consent, kill switches
Kill switches
Native experience, feedback and operations
Panels, queues, alerts, cost, operations
Panels and queues
The cheapest layer that meets the bar.
The conversational surface has its own discipline on top of all this: a request walks a cascade and stops at the first layer that resolves it. Deterministic routing first, an on-device classifier next, a replay of something this tenant has asked before, and only then a paid model.
A request stops at the first layer that can answer it
Most questions never reach a model. They resolve on a deterministic router or an on-device classifier running on your own server, at no credit cost, and a model is asked only when the layers below it cannot answer.
Regex, slot-fill and conversation focus. No model involved.
62% freeA bag-of-words language model, trained at boot, running on your own server.
20% freeA phrase this tenant has asked before, replayed and re-validated live.
9% freeClaude or OpenAI, answering into a strict JSON contract.
7% 1 creditOn-device text recognition first; a model only on documents that need it.
2% N creditsEvery figure says what kind of thing it is.
The one thing that makes intelligence usable on a ledger is knowing which claims are arithmetic and which are inference.
Calculated by Cobalt ERP
Arithmetic over your own records. Reproducible, and the same every time you ask.
Rule-based
A deterministic rule fired. The explainer names which one and what it read.
Extracted from a document
Read off a PDF or an image, with a confidence score and the source page attached.
AI-generated
A model wrote it. Marked as such, every time, with no exception for convenience.
Related pages.
Frequently asked questions.
Why eleven engines rather than one model?
Because what you are entitled to trust differs by method. Arithmetic is reproducible; a mined pattern is an association and never a cause; a forecast carries a calibrated interval; an optimiser must tell you whether a plan is feasible, best-known or provably optimal. One model asked to do all of it gives you the same confident tone for every one of them.
Do the engines call each other?
No. A compiled recipe composes them, and the compiler rejects anything unsafe — cycles, a missing input, ranking placed before the deterministic safety filter, more than one side effect, or a user-visible output with no evidence and no expiry.
Which engines does my module use?
All fourteen modules run on the same eleven; what differs is which do the primary work. Manufacturing, procure-to-pay and field service use all eleven. Master data barely needs simulation. HR is deliberately restricted.
What is restricted for HR?
Prediction, optimisation, simulation and causal methods are limited to privacy-thresholded aggregate planning and administrative quality. They must not rank individuals or drive an employment decision, and task mining uses application events only — no screen recording, no keystroke capture, no productivity ranking.
What can an agent actually do on its own?
Whatever level you have admitted for that one skill on your tenant, and nothing beyond it. There is no blanket autonomy switch. Above attended apply, an action needs either a person or a named automation policy with its own caps.
What can an agent never do?
Post or reverse a journal, approve a controlled transaction, release a payment, change bank details, determine or submit tax, close or reopen a period, override a credit hold, dispatch regulated goods, release a quality hold, raise its own permissions, delete evidence, or make any hiring, firing, pay or disciplinary decision. That boundary is permanent.
How do I know an answer is right?
Every output carries its provenance — calculated, rule-based, extracted or generated — along with the records it read, the version of the rule or model that produced it, and an expiry. The evidence and decision graph keeps the lineage from source fact through to your decision.
Is a model allowed to instruct the system?
No. Model output is untrusted data with the same standing as a message from a stranger. It enters only by validating against a schema that cannot express an action, entity identity is re-resolved against your database, and permissions are checked live rather than taken from anything the model supplied.
See the whole chain on your own records.
Join the waitlist and put a real question to it. Every answer names the engines it used, the records they read and the rule or model version behind each figure.
Join waitlist