Skip to content
Decision Engine/KnowledgeEngine

Six capabilities. One thing that a professional will sign.

The knowledge base is the floor — not the product. The KnowledgeEngine is the system built on top of it: six reusable capabilities that turn a governed corpus into a verdict with evidence, confidence, and an audit trail.

Living Canvas · voice
advisor
Overrides + recalculation
human-in-the-loop
Scoring + BEM-QA
evidence · confidence · deterministic
Multi-model orchestration
~60 agents, dependency-gated
Knowledge base
the floor — governed corpus
The distinction that matters

A knowledge base is where most “document AI” stops.

Index a corpus, bolt on a chatbot, add citations: you have a product that sounds right. For work that can be wrong with consequences — a LEED submittal, a supplier ESG audit, an IEP compliance review — that's not enough. The KnowledgeEngine is what turns the floor into a verdict you can defend.

Grounded

Every output is anchored in the knowledge base and traces to the exact rule it rests on. The engine cannot invent a regulation it isn't holding.

Cited sources · version-aware

Defensible

Verdict, evidence, and confidence on every requirement; deterministic math; an expert override that recalculates; a full audit trail. Built to show its work.

Confidence · override · audit trail

Correctable

Every value is overridable and the override propagates. The output is not a black box — it's a structured document an expert can interrogate and correct.

Dependency graph · recalculation

Why grounding matters

A knowledge base isn't a pile of documents in a chatbot.

The most common question we get: “can't I just upload our documents to an LLM?” You can — and for regulated work, that's exactly where it breaks. Here's the difference.

The usual approach

A pile of documents in an LLM

?
  • Everything weighs the same. A forum post and a federal regulation are retrieved as equals — the model can't tell authority from anecdote.
  • Frozen at upload. It knows whatever you pasted, whenever you pasted it. Codes change; the pile doesn't.
  • No version or jurisdiction sense. v4 vs v4.1, your state vs another — it can't keep them straight.
  • Retrieval by vibes. Similarity search grabs passages that sound related, then the model fills the gaps — confidently.
  • No precedence when sources conflict. When two documents disagree, nothing decides which one wins.
vs
The Pandotic way

A governed knowledge base

AuthorityLaws & binding regulationcited
StandardCodes, frameworks & rubricsversioned
PolicyYour org's rules & precedentscoped
ContextRecords, history & notesranked
  • Ranked by authority. Law outranks standard outranks policy outranks anecdote — every time.
  • Version & jurisdiction aware. The engine knows which edition and which region governs this case.
  • Cited to the source. Every claim traces back to the exact rule it rests on — checkable, auditable.
  • Current & maintained. As regulations change, the knowledge base updates — not a frozen snapshot.
  • Conflicts resolved by precedence. When sources disagree, the hierarchy decides which one controls.

A pile of documents can tell you what a paragraph says. A governed knowledge base can tell you what actually governs your decision — and prove it.

How the engine works

From your documents to something you can act on.

One pipeline, every product. Ground it in what's true, read the hard documents, and turn the evidence into the tool the job actually needs.

01 · the ground

Knowledge base

Everything the engine is allowed to treat as true — your world, plus the rules that govern it.

Internal
Your data, history & records
External
Laws · codes · regulations · rubrics
02 · the work

Document & complex-data extraction

The engine reads the artifacts your experts read — and turns them into structured, scored evidence.

  • Ingest complex docs, drawings, models & data
  • Structured evidence with confidence
  • Score every requirement against the framework
  • Deterministic checks where the numbers matter
03 · the value — what you get
The smartest chatbotA grounded advisor that cites its evidence — and can't make things up.
Decision enginesA verdict, with the evidence and confidence to defend it.
Certification toolsCredit-by-credit, submittal to certified — defensibly.
Regulation mappingEvery requirement tracked to the rule it answers to.
One engineMany productsEvery regulated field
The six capabilities

From floor to output. What each layer does.

Each capability builds on the one below it. Together they produce a structured output an expert will put their name on.

01

Knowledge base

The floor — not the ceiling

Every other capability rests on this. The knowledge base is not a pile of documents in a chatbot — it's a governed corpus, ranked by authority, version-aware, and jurisdiction-scoped. Laws outrank standards; standards outrank policy; policy outranks anecdote — every time.

Authority-rankedVersion-awareJurisdiction-scopedCited to source
02

Multi-model orchestration

~60 agents, dependency-gated

No single model does this work well. The engine deploys a coordinated set of specialized agents — some for extraction, some for scoring, some for deterministic verification — gated by dependency so each step waits for the evidence it needs. Model-agnostic: Claude, GPT, Gemini, or open-source; swapped as better ones ship.

~60 specialized agentsDependency-gatedModel-agnosticFrontier + open source
03

Structured scoring

Every requirement. Evidence and confidence.

Every framework requirement is scored against the evidence in the knowledge base — not summarized, not paraphrased. Each score carries the evidence that supports it and a confidence level that flags uncertainty rather than hiding it. A professional can check every call.

Requirement-level scoresEvidence attachedConfidence levelsFully auditable
04

Deterministic QA

BEM-QA — the numbers are code, not guesses

Where the job involves math — energy model arithmetic, submittal calculations, regulatory thresholds — the engine runs deterministic code, not a language model guess. BEM-QA validates building energy models against the engineering rules they're supposed to satisfy, producing an auditable calculation trail.

Deterministic codeAuditable mathNo model guessworkBEM-QA certified
05

Expert overrides

Human-in-the-loop with recalculation

The engine is designed to be corrected. Every scored value is expert-overridable — and an override propagates. Change one input and the dependency graph recalculates; the whole analysis stays consistent. This is what makes the output something a professional will sign: it's correctable in the way their own work is.

Any value overridableOverride propagatesDependency graphFull recalculation
06

Living Canvas + advisor

Plain-language explanation, voice interface

A verdict without explanation isn't useful to a practitioner who needs to act on it. Living Canvas is the advisor layer: a grounded conversational interface that explains the output in plain language, answers follow-up questions against the same evidence base, and is available by voice. It can't make things up — it's bounded to what the knowledge base holds.

Grounded advisorCites evidenceVoice interfaceCan't hallucinate
How it holds together

One consistent output. Correctable at every level.

01

The engine doesn't guess. It scores.

Each requirement in the framework gets a verdict — pass, fail, or flagged — against the evidence in the knowledge base. The evidence is cited. The confidence is explicit. If something is uncertain, it says so rather than smoothing it over.

02

The numbers are code, not LLM output.

Where the job involves arithmetic — energy model calculations, threshold checks, submittal quantities — the engine runs deterministic code. The math is auditable. Anyone can check it.

03

Expert corrections propagate.

When a practitioner overrides a value — because they know something the engine doesn't — that correction flows through the dependency graph. Related scores recalculate. The whole analysis stays consistent, not frozen at the moment of import.

04

The advisor is bounded to the evidence.

Living Canvas, the conversational layer, explains the output in plain language and answers follow-up questions — but it is bounded to what the knowledge base holds. It can't generate a citation it isn't holding. That's the difference between an advisor that helps and one that misleads.

Proof — in production

LEEDSmart is all six capabilities, running live.

Green-building submittals in. Credit-by-credit verdicts — with evidence and confidence — out. The energy model QA'd deterministically. Expert overrides that propagate. An advisor that explains the whole thing in plain language. Every one of the six capabilities, pointed at the LEED framework, in production.

One pass
every framework requirement scored, with evidence + confidence
Deterministic
energy-model math is auditable code, not model guesswork
Recalculates
expert overrides propagate through the dependency graph
Grounded advisor
Living Canvas explains every verdict, bounded to the evidence
Bring us a framework

Tell us the documents and the rules.
We'll build the engine around them.

A pilot proves a single framework fast — the shortest path from “could AI do this?” to a verdict your experts will sign.