PlatformSolutionsAcceleratorsCustomersDevelopersStart for FreeBook a demo
The Rainbird platform

From your knowledge to proven decisions

Rainbird turns your policies and expertise into knowledge graphs, reasons over them deterministically, and proves every outcome with evidence.

Book a demoExplore the accelerators
Mortgage underwriting & affordabilityGraph V2.4

Regulation · Policy · Expertise

MCOB 11.6Consumer DutyFPC LTI limitLender policyExpert judgement

The knowledge graph

assessed incomestressed paymentmonthly surplusadverse credit tierloan to valueretirement affordabilityunderwriting decision

Hundreds of rules · 11 reasoning layers · Every threshold a policy fact

The decision

ApproveApprove with conditionsReferDecline
Named reasons · Conditions · Customer explanationAudit rationale
How it works

Codify, reason, prove

One chain of custody from your policy to the decision your regulator reads.

  1. 1Codify

    Captures expert knowledge as structured rules

    Rainbird StudioThe no-code environment where policy owners author, test and approve Rainbird knowledge graphs.
    RAKEThe Rainbird Agentic Knowledge Engineer workbench that turns written policy into deterministic, auditable decision agents.New
    Rainbird Claude SkillUses Claude to research, build and live-test Rainbird knowledge graphs straight from Claude Code.New
    Rainbird FoundryThe Rainbird enterprise programme that encodes your whole policy estate, resolving conflicts, overlaps and gaps.

    Regulations, policies and expert interviews become a versioned Rainbird knowledge graph.

  2. 2Reason

    Applies logic to reach verifiable conclusions

    Rainbird Reasoning EngineReasons over your knowledge graphs to ensure that identical facts produce identical decisions, each with a computed certainty and audit trail.

    Backward chainingA reasoning strategy that starts from the desired conclusion and works back to find only the data needed to prove it. asks only for the data it needs, then reasons symbolicallyUsing explicit, human-readable rules and logic rather than a statistical approximation. to an outcome.

  3. 3Prove

    Delivers evidence for every decision made

    The Evidence TreeThe Rainbird 'receipt' for every decision including the rules, facts and certainty that produced it.

    Every outcome ships with its rules, evidence and certainty, in natural language and JSONA plain-text data format, so the decision and its evidence can be read by any system without a special viewer..

Codify · Rainbird Studio

Author, test and govern your own knowledge graphs

You own the knowledge graphs: human-readable, versioned and portable. Run in our cloud, a private cloud or on your own infrastructure.

Start from a use case accelerator

Open an accelerator in the Rainbird Studio, review every rule it ships with, and adapt it to your sovereign policy: authoring becomes editing.

Agentic knowledge engineering

For new greenfield projects, translate regulations, policies and expert knowledge into a structured Rainbird knowledge graph, with AI drafting such as the Rainbird Claude skill plus human review.

Simulation and testing

Run test cases against knowledge graphs before deployment. Validate edge cases and regulatory changes instantly.

Versioned like code

Every graph is versioned in Studio, and every graph is code: export it, hold it in your own repository, diff releases, and run it through your own CI/CD with its test suite.

< 1 hour

Agentic knowledge engineering turns an existing documented procedure into a working knowledge graph, ready for your experts to review.

No-code

The people who own the policy author and amend the graph themselves, with no developers in the loop.

MCP-native

Every knowledge graph published is available to your applications over the REST API and to your AI agents over MCP.

Reason · Rainbird Reasoning Engine

Deterministic reasoning at machine speed

Same case in, same answer out, every time, with the working shown.

Backward chaining

Asks only for the data it needs

Rainbird doesn't evaluate every rule for every case. It starts from the question, works backwards to identify exactly which data is needed, and requests only that, minimising data exposure and processing overhead.

Symbolic core

Judgement itself is always symbolic

The Reasoning Engine is a pure symbolic reasoner. It never approximates. Given the same inputs it always reaches the same conclusion, deterministic by construction, not by averaging across outputs.

Incomplete data

Handles uncertainty without hiding it

Real-world decisions rarely have complete data. Rainbird reasons to the highest-confidence outcome supportable by available evidence, quantifies residual uncertainty, and flags what would change the result.

Certainty algebra

Confidence is calculated, never guessed

Every rule and every fact carries a certainty factor, and the engine combines them with a documented algebra. Each conclusion arrives with a computed confidence.

Data arrives by connection to your systems, by inference within the graph, or by asking a person. The reasoning itself is symbolic end to end: no LLM in the decision loop, so decisions run at zero token cost

Prove · The evidence tree

Every decision ships with its evidence tree

Every decision comes with an evidence tree which acts as its regulator-ready receipt. Each arrives with the full chain of rules, evidence and the certainty values that produced it, in natural language and JSON. Inspectable by humans, parseable by machines.

Evidence tree · APP-3003 · Mortgage underwritingReads right to left · Graph V2.4 · 380 ms

The checks

Reasoned · 100% certain

All seven assessments completed.

Because

  • Income assessed and evidenced
  • Expenditure assessed
  • Affordability holds at the stressed rate
  • Security and valuation assessed
  • Credit history assessed: clean
  • Deposit and source of funds assessed
  • Term and retirement assessed
7 of 7

Policy fact

Acme lending policy requires all seven assessments to complete before any approval.

Required: 7

The record

Reasoned · 100% certain

The assessment record is complete.

Because

  • Seven assessments were required by policy
  • All seven have completed.

The candidates

Reasoned · 100% certain

Approve is a candidate decision.

Because

  • The record is complete
  • No policy rule is breached
  • Nothing needs underwriter judgement
  • No conditions are outstanding.

Policy fact

A decline outranks a referral, a referral outranks a conditional approval, and a clean approval ranks last: the strictest outcome always wins.

Precedence ladder

The decision

Reasoned · 100% certain

APP-3003 is approved.

Because

  • Approve is the candidate at the strongest precedence
  • Every check completed and none dissented.
Decision: Approve100% certain

351 rules · 37 relationships traversed · 4 data calls · 1 question asked · 0 LLM calls

How it fits

Where Rainbird sits in your stack

Rainbird sits between your AI agents and your systems of record: the layer where judgement happens.

  • Your agent needs a judgement it must not guess. It delegates.
  • Rainbird reasons deterministically over your encoded policy.
  • The decision returns: certainty attached, evidence tree included.
Your agents, apps & workflows
PROBABILISTIC · DELEGATES THE DECISION
ONE CALL · MCP OR RESTTHE GOAL + YOUR FACTS
DECISION · CERTAINTYEVIDENCE TREE
Rainbird decision layer
DETERMINISTIC · YOUR POLICY AS A KNOWLEDGE GRAPH
ZERO LLM
REASONINGSAME FACTS
SAME DECISION
Asks only for what it's missing, then decides
FETCHES FACTS,LIVE AT RUNTIME
FACTS RETURNED,WITH SOURCE
Your systems of record
CORE SYSTEMS · SCREENING · REGISTRIES · DOCUMENTS
Ownership
Your sovereign IP

Portable knowledge graphs

You own the knowledge graphs: human-readable, versioned, portable. Run in our cloud, a private cloud or your infrastructure.

Invocation
Agent-ready

Published as an MCP tool

Publish any knowledge graph as an MCP tool. Agents invoke it by name and get the decision back with its evidence tree.

Computable Policy

Make the enterprise policy estate computable with Rainbird Foundry

Delivered as a programme with the Rainbird team.

Rainbird Foundry scales the same deterministic knowledge graph architecture across the whole enterprise. It encodes regulation and policy estate-wide, resolving conflicts, overlaps and gaps. This knowledge layer is available to AI agents to ensure that all decisions are bound by regulation and policy.

MetaGraph
Policy
Policy
Policy
Policy
Policy
Policy
···
Learn more about computable policy →
Enterprise ready

Built for regulated industries

We carry high levels of certification and support multiple deployment options.

Security & compliance

  • ISO 27001 · Certified
  • HIPAA · Compliant
  • SOC 2 Type II · In progress

Deployment

  • SaaS (multi-tenant)
  • Private cloud
  • Self-hosted

Integration

  • REST API
  • MCP, AI agent native
  • Pre-built connectors
See it live

See Rainbird reason through your decision

Bring us a decision your organisation must get right. We will build a live Rainbird knowledge graph and run it for you in the room, on your data.

Book a demoExplore the accelerators