Knowledge Base

Knowledge Base

Discover the documents and data that run an AEC project, and the workflows that depend on them. See how we turn this data into structured AI-ready knowledge, and how AI agents can automate domain-specific workflows on top.

AEC-native Data

The documents and models a project runs on, and what teams need to be able to ask of them.

As-built drawings and handover packs

The record set describing the building as constructed, together with the health and safety file and the information required for the golden thread.

Bills of quantities

The measured, itemised list of work and materials priced by tenderers, structured to NRM2 or a bespoke measurement rule set.

Change orders, variations and compensation events

Instructed or notified changes to scope, time or cost, and the notices, quotations and assessments that follow under the contract.

Construction contracts (NEC, JCT, FIDIC)

The conditions of contract, particulars, amendments and schedules that define obligations, risk allocation, notices and payment between the parties.

Construction drawings

The 2D graphical record of design intent: plans, sections, elevations, details, schedules and title blocks, issued as sheets with revisions.

Construction programmes

The logic-linked schedule of activities, durations, milestones and float, held in P6, Asta or MS Project and issued as baselines and updates.

Construction specifications

The written performance and prescriptive requirements for materials, workmanship and systems, organised by work section (NBS, CSI MasterFormat, Uniclass).

Drawing schedules (doors, windows, finishes, equipment)

Tabular schedules on drawings or in the model listing elements, their references, properties and locations, and the links between them and the plans.

Employer's requirements

The client's statement of scope, performance and quality requirements under a design and build contract, against which the contractor's proposals are measured.

Fire strategy documents

The fire strategy report and its supporting drawings and specifications, setting out compartmentation, escape, structural fire protection and systems.

IFC and BIM models

The federated 3D information model and its IFC exchange format: objects, properties, classifications, relationships and geometry.

Meeting minutes and decision records

Minutes of design team, progress and coordination meetings, holding the decisions, actions and agreed changes that rarely make it back into the drawings.

Method statements and RAMS

Risk assessments and method statements describing how a task will be carried out safely, submitted before work starts and reviewed by the principal contractor.

O&M manuals

The operation and maintenance documentation handed over at completion: asset registers, manufacturer data, commissioning records, warranties and maintenance schedules.

RFIs

Formal requests for information raised during construction to resolve ambiguities or conflicts in the drawings and specifications, with their responses.

Site diaries and daily reports

The daily record of labour, plant, weather, progress, deliveries, instructions and events on site, often the evidence base in disputes.

Submittals

Contractor-issued product data, shop drawings and samples submitted for review against the specification before procurement or installation.

Tender packs and ITT documents

The invitation to tender and its enclosures: employer's requirements, drawings, specifications, pricing documents, conditions and returnable schedules.

AEC Workflows

The reviews and checks those documents feed, and what changes when the knowledge underneath is structured.

AI submittal review

Checking each submittal against the relevant specification clauses and drawings, flagging omissions and deviations, and drafting the review response with the source of every finding.

Contract obligation extraction

Extracting obligations, notice periods, risk allocations and deliverables from the executed contract into a structured register the project team can act on.

Drawing coordination review

Checking architectural, structural and MEP sheets against each other for conflicts, missing references and inconsistent schedules before issue.

Fire strategy consistency check

Checking the fire strategy report against the drawings, specifications and schedules it depends on, and surfacing contradictions before they reach the regulator or site.

Gateway 2 readiness review

Checking a higher-risk building application for contradictions and gaps across the fire strategy, structural and design information before submission to the regulator.

Handover pack structuring

Turning the handover deliverables into a structured asset and information register, with every record linked to its source document and drawing.

Lessons learned and institutional knowledge capture

Capturing decisions, defects, precedents and outcomes from completed projects into structured knowledge the next project can reuse.

Project knowledge search

Asking questions across the whole project record, drawings, models, specs, contracts and correspondence, and getting answers that cite their source.

RFI drafting and precedent search

Finding whether a question has been answered before, on this or earlier projects, and drafting the RFI or its response from the governing drawings and clauses.

Specification to drawing consistency check

Reconciling what the specification requires with what the drawings and schedules show, item by item, with every mismatch traced to its clause and sheet.

Tender document review

Reading the full tender pack within the tender window to surface scope, risk, contradictions and qualifications before pricing is committed.

Variation and change impact review

Tracing a proposed change through the drawings, specification, programme and contract to identify what it touches and what it triggers.

Work With Us

See it on your data.

See it on your data.

Our engagements begin with a focused working session designed to identify where AI can create immediate business impact within your specific context.


No pitches. No generic frameworks. Just clarity on where AI works and where it fails, what’s worth building and what isn’t.