Home Made For EPC Contractors Developers Construction Trades Electrical Contractor Mechanical Contractor Civil Contractor M&A
How It Works Insights About Pricing
Architecture

How your documents
become answers.

Axion is not a chatbot bolted onto a file server. It is a purpose-built intelligence layer that reads, classifies, connects, and cites every answer from your actual project documents. Here is how the system works, from upload to cited answer.

The Pipeline
Ingest
Upload documents
Classify
Parse and categorize
Graph
Map relationships
Index
Embed for search
Cite
Grounded answers
Ingest

Your documents go in. All of them.

Upload a 1,200-page bid package. Axion parses every page: OCR for scanned documents, text extraction for digital files, metadata identification for revision tracking. The system processes specifications, contracts, RFIs, submittals, geotechnical reports, environmental studies, change orders, and 149 other document types native to solar, BESS, and construction projects.

A typical bid package is fully ingested in under ten minutes. Supported formats include PDF, DOCX, XLSX, TXT, CSV, and other text-based files. Native drawing ingestion is on the roadmap.

Knowledge Graph

Every document connects to every other document.

Axion builds a knowledge graph from your documents. Instead of storing them as isolated files in folders, Axion pulls out the entities (equipment, specifications, parties, dates, requirements, locations) and maps how they relate to each other.

A change order references a spec section that references an equipment schedule that references a submittal. In a folder, those connections are invisible. In the knowledge graph, they are explicit and queryable.

The graph is structured around a domain-specific ontology built from nearly 20 years of utility-scale solar and BESS project operations: 27 document categories, 52 work packages, 156 document types. This is not a generic construction taxonomy adapted from commercial building. It was built for your projects.

Semantic Index

Your questions, in plain English.

Every passage in your documents is indexed by meaning, not just by keyword. When you ask "Does the Division 26 spec require arc-flash labels on every disconnect?" the index finds the passages that answer the question, even when the spec uses different words than you did.

The knowledge graph and the semantic index work together. The graph narrows the search to the right project, the right document set, the right revision. The index finds the best passages inside that narrowed set. Neither one alone is as accurate as both together.

Retrieval and Citation

Every answer grounded. Every claim cited.

When you ask Axion a question, three things happen in sequence. First, the knowledge graph identifies which documents, entities, and relationships are relevant to your query. Second, the semantic index retrieves the most semantically similar passages from that narrowed context. Third, a large language model generates a natural-language answer grounded entirely in the retrieved passages.

Every claim in the answer is cited to the source document it came from. If the answer is not in your documents, Axion says so. It does not fabricate contract terms, invent risk flags, or hallucinate equipment specifications.

1.4s
Cited answer returned on a live
utility-scale deployment
Data Isolation

Your data never touches another customer's.

Your documents, and everything Axion builds from them, are stored and retrieved separately from every other customer's. No question you ask can reach another company's data, and no question they ask can reach yours. That limit is applied when the answer is retrieved, not by filtering results afterward. Your data is encrypted in transit and at rest. It is never used to train, fine-tune, or improve any AI model, ours or our providers'.

We call this IP Fortress. It is a set of commitments written into our Terms of Service, not a setting that can be switched off. We will walk your security team through the architecture behind it under a mutual non-disclosure agreement.

Encrypted in transit and at rest

Your data is encrypted both in transit and at rest. Access to production systems is limited to authorized personnel under written agreement.

No model training, ever

Your documents do not train any AI model. Not ours, not our providers'. This is a contractual commitment in the Terms of Service.

Nothing is shared

Your data is stored and retrieved separately from every other customer's, and never enters another customer's answers.

Your data, your exit

Export your outputs and request deletion at any time, with certification. You built the knowledge base. You own it.

Clear Lines

What this is. What this is not.

What Axion Is
Purpose-built for construction, solar, and BESS projects
A knowledge layer on top of your documents
Grounded in your data, cited to the source document
Your data is never commingled with another customer's
Built by operators who run these projects
What Axion Is Not
A general-purpose AI adapted for construction
A document management system replacing Procore or SharePoint
A chatbot generating plausible answers from training data
A system where your data improves a model someone else uses
Built by researchers who study the industry from outside
See It Work

Bring your hardest
bid package.

The best way to evaluate Axion is with your own documents. Upload a real bid package, ask a real question, and see the cited answer. No demo data. No slides. Your documents, your questions, your evaluation.