Platform
What our products are built on
You could buy software that does any one thing on this page. What is harder to assemble is the combination.
Why it is hard to copy
Three things that only work together
A model of what an organisation is
Governing decisions without one gives you policy you cannot target.
A record of how it decided
Modelling a business without recording decisions gives you a diagram nobody opens again.
An honest measure of whether it worked
Measuring outcomes without the other two gives you a number with no explanation attached.
The engines
Nine engines
Choose one to see what it does, how it works and what it measures.
Which product uses what
One platform, applied in different places
| Engine | Enterprise Decision Intelligence | Alpha Engine | Enterprise Solution Architecture | Enterprise Ontology Management | Enterprise Culture Evolution |
|---|---|---|---|---|---|
| Ontology engine | No | No | |||
| Decision intelligence engine | No | ||||
| Capture layer | No | No | No | No | |
| Control dials | No | No | No | ||
| Presence | No | No | |||
| Solution packs | No | No | No | ||
| Attribution | No | No | No | ||
| Decision learning | |||||
| Collective intelligence | No | No |
This shows what each product is designed on, not what is running today, as our products are at different stages. Enterprise Culture Evolution also uses dedicated culture analysis, culture evolution and coaching engines.
Every measure named on this page is one the product records from a customer's own data against a baseline taken before anything changes. We publish no benchmark we cannot reproduce from a live engagement.
Ontology engine
What the business actually is
Few organisations of consequence are a single enterprise. A government is a federation of legally distinct departments, authorities and funds; a corporate group is a set of subsidiaries. Each describes itself in its own vocabulary, so group-level questions go unanswered. The ontology engine gives a federated group one place to discover, capture, check and maintain a model of every entity it runs, partners with or measures itself against — described by what each one is responsible for, rather than by what it calls things.
How it works and what gets measured
One essence, many implementations
A unit of work is defined once and used by any number of entities without being copied. Each entity separately links it to the capabilities, processes and applications that deliver it, and keeps its own architecture landscape with baseline, transition and target states.
Provenance before authority before a person
Every fact is an assertion carrying evidence that names its source and its exact location — file, sheet and row, or section and page, or URL. Anything extracted by AI enters as inferred and rises to confirmed only when a named owner confirms it, with who and when on the record.
Conflicts escalate rather than resolve quietly
Where two sources disagree and one outranks the other, the order is applied and the rule cited. Where they carry equal authority the engine does not choose: it opens a decision record for the board that owns it.
Intake needs two reviewers
Submissions are validated, scored for completeness and confidence, and reviewed by the entity's architect and a group architect before anything becomes an assertion. Nobody approves their own answers.
Analysis is computed, never stored
Every cross-entity view is derived at the moment it is asked for. Rebuilding from the same data reproduces every figure exactly. Overlap totals count only human-confirmed matches; unconfirmed ones are shown separately as potential.
What gets measured
Overlap count and confirmed duplicated contract value, per overlap and in total. Completeness per entity and whether it is going up. The share of governance decisions carrying an impact estimate before approval. Any figure on an executive screen traces to its source rows in no more than four clicks.
Decision intelligence engine
The system of record for judgement
Every large organisation has a system of record for money, people, customers and stock. None has one for judgement. This is that missing system: one canonical, append-only entry per decision — whoever or whatever made it — holding what was decided, between which options, on what reasoning, under which version of which rule, and what happened afterwards.
How it works and what gets measured
A register is not a log
A log records that a user changed a field to a value at a time. A register records that a named person or agent chose this option over those three, for this stated reason, with this much at stake, under the policy in force that morning — and later, whether it worked.
Append-only, and policy as of the time
Actions add events; nothing rewrites them. The policy version attached is the one in force when the decision was made, not the one in force when somebody later goes looking. Both are easy to skip at the start and impossible to retrofit afterwards.
People and agents on equal footing
A human decision and an agent decision are the same kind of object: same entry, same fields, same evaluation, same register. That is what lets one set of rules govern both.
The unit is the decision class, not the department
A recurring consequential decision — pricing exceptions, capital approvals, supplier awards — described once, with an accountable owner and a target time. A class is something a person, an application and an agent can each do, which is why one register serves all three.
Reasoning recorded at the time
The decider's own words, captured while the decision is being made. Reasoning supplied once the outcome is known is not reasoning; it is explanation.
What gets measured
Risk and audit can reconstruct any decision with the policy of the day attached. Finance and operations can see where authority actually sits, class by class, against where it was supposed to sit. Agent decisions sit in the same register as human ones, so autonomy can be argued from evidence rather than asserted. Legal gets the decision and its evidence rather than somebody's mailbox.
Capture layer
Decisions that never reach a system
A consequential decision leaves behind a transaction, a thread, or nothing at all. The capture layer arrives where decisions are actually taken — in the meeting, the mail thread, the application, the agent's own code path — and turns each one into the same normalised record. It is built on a single assumption: people will not come to a new screen to record a decision they have already made.
How it works and what gets measured
Six routes in, one record out
Meetings and calls; a managed decision inbox; business applications read at the transaction that carries the decision; a custom connector for anything with an API; portal and mobile; and an endpoint an AI agent calls before it acts. Nothing downstream needs to know which door a decision came through.
Intent, not aftermath, for agents
The agent API registers and evaluates the decision at the moment of intent, rather than reconstructing it from logs afterwards. An agent that acts and reports later is being observed, not governed.
Detection proposes, it never files
A decision spotted in conversation or email is put to its owner, who confirms, reassigns or dismisses it. Nothing enters the register without the named decider confirming, and dismissing takes one tap and needs no reason.
One decision, three channels, one record
A decision routinely appears on a call, again in chat and again in the ERP. Identity resolution recognises the same person or agent across all three and merges the appearances into a single record with several sources attached.
The decision, not the conversation
Consent recorded before anything is taken from a recorded channel. Personal data redacted and non-decision content discarded rather than stored. Every record tagged at ingest with its residency boundary and retention class.
What gets measured
Two measures, both baselined before anything is switched on: the share of decisions in a governed class that reach the register, and the time between a decision being taken and it being captured. Coverage, not cleverness, sets the ceiling on every other engine.
Control dials
Discretion as a range, not a switch
A rule about risk and a judgement about a team are not the same setting, and delegation matrices jam them into one line. Policy sets the hard boundary — what may never happen. The trust dial sets how much room a given decider has inside it. Widening the room a good team has no longer requires anyone to reopen the risk appetite, and tightening the risk appetite no longer requires anyone to re-argue whether the team is any good.
How it works and what gets measured
Policy as code, not prose
Versioned, owned by a named person, and applied to people, applications and agents alike. Each policy states what it tests and what happens when the test fails — notify, require approval, or block until it clears — and its version is recorded on every decision it touched.
A dial per decider, in five bands
From no discretion, through recommend and supervised, to delegated and autonomous. It is a setting rather than a rule, owned by the person accountable, and it can be moved without rewriting anything about risk.
Nothing is committed without a projection
Moving the control changes nothing. A proposed setting is replayed against the decisions already in that organisation's register, showing today's mix beside the mix the change would produce. Only then can it be committed, with a recorded reason.
Tightening is frictionless; loosening is not
Narrowing discretion takes effect on the author's own action. Anything that widens autonomy needs a second person to activate it.
Agent authority, one class at a time
Every agent has an identity, an accountable human owner, a defined scope and an off switch one person can reach. Its decisions can run in shadow — recorded, compared against the human's, never executed — and autonomy is extended class by class on that evidence. An agent can sit at the top band on one class, near the bottom on another and be blocked entirely on a third.
What gets measured
Delegation becomes reversible — a setting with a projection, not a restructure. Risk appetite stops standing in for trust. Leadership attention is rationed deliberately rather than by whoever shouts. And agents become adoptable, because authority is extended on evidence and can be withdrawn the same way.
Presence
Is anybody actually behind the gate?
Routing decides who should decide. Presence decides whether they are there, and what happens when they are not. It establishes whether a decider is reachable now, moves authority to a nominated cover in a recorded way when they are not, delivers the notification by a ladder matched to the urgency, records whether a human actually saw it, and escalates tier by tier against a time budget.
How it works and what gets measured
Presence is consumed, not owned
Derived from declared status, calendar, working hours, time zone, device and on-call rota — each assertion carrying the time it was established. Declaring absence has to be easier than not declaring it, so the calendar is read by default and the declaration is the exception.
A stale signal cannot quietly divert authority
Past the staleness limit, presence resolves to unknown — which routes to the holder and notifies the cover, rather than guessing.
Three named ways authority moves
Standing delegation lives in the rights model. Temporary delegation is declared by the holder for a bounded period and may be narrower than their own authority but never wider. Automatic cover routes work when the holder is unavailable, bounded by that unavailability, and is reviewed one band tighter for the duration. Every decision names both parties and which mechanism applied.
Notification is a ladder, not a channel
Quiet channels first, interruptive ones at defined intervals. A notification moves from sent to delivered to acknowledged to decided, and acknowledgement is recorded only on an explicit action — one tap, never inferred from a page view. That state, not the decision, is what escalation watches.
Escalation ends somewhere, by configuration
Tiers per class with a time budget each, typically holder, cover, owner, then the accountable director. A ladder with no bound and no default is refused at configuration.
What gets measured
The analysis separates time spent waiting because nobody was there from time spent waiting because somebody was thinking — which is the split a class owner needs before changing either the ladder or the dial. It leads with the class and never the person: a view that answers who is absent will be read as attendance monitoring, and will end the deployment.
Solution packs
The playbook, written down
A solution pack writes one playbook down in a form the product can use: what it changes in an organisation, which gaps it addresses, which measures it expects to move, how long it takes and what it costs. Because it is structured against a model of how an organisation actually operates, it can be matched to one before a decision is taken, applied afterwards, and measured.
How it works and what gets measured
Three ways into the library
Authored in the portal; imported as a document with its structure proposed by extraction for the author to correct; or requested from Red Bear by a brief. Every pack is versioned and starts as a draft.
Nobody approves their own
Every new pack and every new version goes to a senior reviewer who approves, rejects or returns it with questions, with a recorded rationale. Until it is approved it appears in no evaluation, no match and no application.
Ask it questions, get citations or nothing
Each pack carries a question interface whose answers are drawn from the pack's own content with a citation. Where the content does not support an answer, the answer is “not found”.
Evaluation commits nothing
An approved pack evaluated against an organisation returns a proposal: where it applies, the gaps it addresses, an estimated uplift with its interval, the confidence, and what is not known.
An application is measurable from day one
Applying a pack records its version, a baseline proposed from connected data with the source and date of each figure, a start date and duration, a named owner, a named sponsor, and the predicted uplift — retained unaltered for later comparison. A baseline figure with no connected data stays a gap; it is never guessed.
What gets measured
A playbook that outlives its author, held by the organisation in a reviewed form rather than by one person. A match made before the commitment rather than after it. And an answer to whether it worked — predicted against realised over the same period, using the prediction as recorded at the time.
Attribution
What you did, apart from what the market did
Records the three facts that make attribution possible and that most organisations never write down: which intervention was actually implemented, when and at what cost, and what followed. Then compares the uplift predicted at the outset against the outcome measured later, and estimates how much of the observed change the intervention actually caused rather than the market, the sector or sheer scale — always as a range.
How it works and what gets measured
The prediction is frozen before the work starts
The plan inherits the predicted uplift from the original case and retains it unaltered. Revisions keep every prior version, so the comparison is against what was actually believed at the time rather than against a later, wiser number.
What was planned and what was done are separate records
Actual implementation date, actual investment and an assessment of implementation quality, held apart from the plan. Partial or abandoned implementation is recordable, because pretending otherwise corrupts every figure downstream.
Measured during, not at the end
Revenue, margin, cash conversion and plan adherence captured periodically, each measurement carrying its period and source. Waiting until the end means the loop never closes.
The split is always an estimate with an interval
The share attributable to the intervention is separated from sector and market movement, and both halves are labelled estimates. A point figure here would be a fiction.
Confidence decides what is shown
Below a confidence threshold the product declines to attribute at all, and says why — other things moved in the same window, so this movement cannot be laid at this decision's door.
What gets measured
A defensible answer to what the work was actually worth, with the working shown. A library scored by outcome rather than by reputation. And reporting that carries real attribution rather than a number nobody can source.
Decision learning
Finding out whether the decision was any good
Outcomes measured back against the expectation recorded at the time, with the quality of the reasoning scored separately from the quality of the result — so a well-reasoned decision that got unlucky is not treated as a bad one, and a careless decision that got lucky is not treated as a good one.
How it works and what gets measured
Process and outcome never combine into one score
They are held on two axes and read as a shape. Four quadrants: deserved success, bad luck, lucky escape and deserved failure. The lucky escapes are the dangerous ones, because the organisation is about to repeat the method.
Learning has to change something
What is learned must alter a person's discretion, a rule, or a standard. If it changes none of the three, it has not been learned — it has been noted.
The expectation must predate the outcome
Only works if what was expected was written down beforehand, which is why the discipline sits in the capture step months earlier rather than in the review.
Honest about its own stage
It begins as reasoning over a small number of cases with the uncertainty stated, and becomes quantitative only when the volume supports it. Saying so, rather than presenting a model trained on nine examples, is the part most products get wrong.
Ordered by confidence, not by size
Where impact is shown, the findings are ordered by how confidently they can be attributed rather than by how large the movement was. Ordering by movement would be judging by outcome, in the layout.
What gets measured
Decisions can be reviewed on how they were made rather than on how they turned out, which is the only version of the exercise that changes behaviour. Rules that are constantly overridden surface as rules to fix rather than as people to discipline.
Collective intelligence
The pattern, never the data
What is learned across customers — which playbooks work in which conditions, which mappings recur, which signals tend to precede trouble — held centrally and reachable through an interface, so each engagement can start further forward than the last.
How it works and what gets measured
The data never leaves its tenant
What accumulates centrally is the pattern, not the records it was derived from. Customer data stays in the customer's own boundary.
Queried, never copied
Customers query the shared intelligence through an interface. They do not hold a copy of it, which is what makes it possible to share at all.
Protected three ways
Commercially in the agreements, architecturally by keeping it in Red Bear's own tenant separated from customer tenants, and operationally by watching for query patterns that look like somebody trying to extract the whole thing.
Residency without surrender
Where a customer requires the intelligence in their own region, a regional replica is a paid option. It remains Red Bear's data rather than becoming theirs.
What gets measured
Designed to compound: each engagement should make the next one cheaper to deliver and more likely to work, so the business does not slowly turn into a consultancy.
Tell us which one you need first
Most conversations start with one engine and one problem: a decision nobody can reconstruct, an estate nobody can compare, or a playbook that left with the person who wrote it.