Nomic is an AI agent platform for architecture, engineering, and construction firms. It grounds search, review, drafting, and compliance workflows in drawings, specifications, project data, and connected systems.
Nomic is a domain-specific AI agent platform for architecture, engineering, and construction (AEC) firms. It works over drawings, specifications, RFIs, submittals, codes, reports, BIM/IFC models, and project repositories to support information retrieval, document comparison, drafting, review, and compliance work.
The platform is intended to keep project data in its existing governed environments while giving teams a way to ask project questions and run repeatable workflows. Depending on the workflow, outputs can include grounded answers with source context, cited code findings, review comments, structured tables, drafted RFI responses, PDF markups, and submittal logs.
Nomic offers prebuilt workflows for drawing review, submittal review, code compliance, project research, detail search, and RFI responses. Its Agent API is aimed at internal AI teams that need drawing parsing, structured extraction, multimodal embeddings, and custom agents over AEC data.
Nomic Parse processes complex AEC material, including large drawing sets, specifications, scanned PDFs, tables, title blocks, and markups, turning visual and textual content into searchable, structured knowledge.
Teams can ask questions across drawings, specs, past RFIs, reports, standards, and project documents. Responses are presented with source context, while code-related checks can include specific references.
The Drawing Review workflow compares drawing sets or plan packages against firm QA/QC standards, flags missing information and inconsistencies, and produces cited findings and PDF markups. Validated findings can be sent to Autodesk Forma, Fieldwire, and Bentley ProjectWise as native issues.
Nomic checks drawings against applicable building codes, standards, and owner requirements. The site states that its workflows cover more than 380 codes and standards and return traceable findings.
Agents can draft summaries, comparisons, review comments, RFI responses, proposal sections, structured outputs, and starting submittal logs from project and historical firm data.
Internal AI teams can use APIs and models for drawing parsing, structured extraction, embeddings, multimodal file understanding, and custom agents over project repositories.
Engineers can search drawings, specifications, prior RFIs, codes, and project context to assemble a grounded draft response that they can verify before sending.
Design and project teams can run a first-pass comparison across sheets to identify missing tags, inconsistencies, and other potential quality issues, then use cited markups to focus manual review.
Teams can check drawings against applicable codes, standards, and owner requirements and use the resulting references to investigate issues during design or permitting.
Reviewers can cross-reference submittal packages against project drawings and specifications and generate an initial submittal log from the project manual before making approval decisions.
Designers can locate previously drawn details across firm repositories, while project teams can query IFC models for quantity takeoffs, coordination checks, data validation, and space schedules.
The platform lists drawing review, QA/QC, code compliance, submittal review, RFI responses, project research, firm-wide detail search, RFP response drafting, and work with BIM/IFC models.
Depending on the workflow, it can produce grounded answers with source context, cited code findings, review comments, PDF markups, drafted RFI responses, comparisons, structured outputs, and starting submittal logs.
No. The pricing page notes that its workflow time estimates assume human review and final approval. Nomic should be treated as a first-pass research, drafting, and coordination aid rather than the final authority.
The site identifies Autodesk Construction Cloud, Bentley ProjectWise, Trimble ProjectSight, SharePoint, Egnyte, and Box, and describes additional project systems and document repositories as supported. Pricing specifically lists Autodesk, Bentley, SharePoint, and more for Business and Enterprise.
Yes. The Agent API is available on Business and Enterprise plans and is intended for internal AI teams building custom agents with drawing parsing, structured extraction, embeddings, and multimodal file understanding.
unriddle.ai
Anaraは、文献・ウェブ検索、出典付き回答、文書分析を一元化するAIリサーチワークスペースです。
hoarder.app
AIタグ付け、全文検索、セルフホスティング対応のオープンソースブックマーク管理
leya.law
弁護士の調査・起案・レビューを効率化する協働AIプラットフォーム
ozbrain.com
OzBrain is a hosted shared knowledge base that AI agents and authorized teammates can read and write. It gives connected agents a structured source of truth for projects, decisions, research, rules, and other working knowledge.
goover.ai
情報探索と調査整理、レポート作成を支援するAIリサーチエージェント
filegpt.app
PDF、ドキュメント、音声、YouTube動画、Webページなどと自然言語で対話。
