Construction and facilities In active development
A facility management platform that replaced spreadsheets and phone calls
Every request, inspection and cost for every building now lives in one place, with a clear owner and status.
Industries
Software and AI for law firms and legal teams
Lawyers read, compare and draft for a living. We build assistants that do the first pass quickly and show their sources, so lawyers can spend their time on judgment.
Common challenges
What slows this industry down
Law firms and in-house legal teams handle large volumes of text: contracts, precedents, policies, correspondence and case files. Much of the work is careful reading and comparison. Junior lawyers and paralegals spend hours finding clauses, checking terms against a playbook and pulling together documents from templates.
Large language models are good at this first pass. They can extract key terms, compare a contract with your standard positions, find relevant passages across thousands of documents and fill templates. They can also be wrong in confident language, so every answer must point to its source and a lawyer must check it.
We build contract review assistants, retrieval based knowledge search, intake forms and document automation for legal teams. Assistants work only from your documents, show the passage behind every answer and keep client data within the services your firm approves. Legal advice stays with lawyers.
Slow first review
Every contract needs a first read to find key terms, risks and deviations from your standards.
Hard-to-find knowledge
Precedents, clause banks and past advice sit in document systems that are hard to search.
Repetitive drafting
Standard documents are assembled by hand from templates, which invites small errors.
Client intake
New matters arrive by email and phone, and conflict checks and details are gathered by hand.
Confidentiality
Client information must stay protected and never be used to train outside models.
What we build
What we build for this industry
The services law firms and legal teams ask us for most often.
RAG knowledge assistants
Assistants that answer questions from your own documents and show where each answer came from.
Document automation
Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
AI copilots
AI helpers built into your product or internal tools that draft, summarize and suggest while people decide.
Customer portals
A secure place where your customers upload documents, check status, pay and message your team.
Solutions that fit
Problems we solve here most often
Contract review assistant
Highlight unusual clauses, missing terms and deviations from your standard positions, so reviewers focus where it matters.
Knowledge assistant (RAG)
Ask a question in plain words and get an answer from your own documents, with links to the sources.
AI document processing
Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
Email triage
Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
Similar work
Similar work from other industries
Finance and accounting In use
A payroll system that turned a monthly build into a monthly review
Payroll is calculated from recorded inputs, reviewed once and sent as payslips in a single batch, with every change logged.
SaaS and startups Design stage
Designing a goal tracker that measures effort, not streaks
A product design built around handwritten daily proof, locked plans and honest self-scoring. The build is in progress.
In practice
What it looks like in practice
An illustrative walk-through, not a client story.
An in-house legal team receives dozens of supplier contracts each month. A contract review assistant reads each new contract, extracts the parties, term, renewal, liability cap and governing law, and compares each clause with the team playbook. It produces a short summary with each deviation marked and linked to the exact clause.
A lawyer reads the summary, opens the flagged clauses and decides what to accept or negotiate. Standard contracts with no deviations move quickly, and the lawyer spends time on the few that need it. When someone asks how the company handled a similar clause last year, a search assistant finds the relevant past contracts and notes and shows the passages. It does not give a legal opinion.
The team measures time per contract before and after, and reviews a sample of results each month to keep the playbook current.
Where to start
Where most legal teams start
Most legal teams start with a contract review assistant built around their own playbook. It is focused, easy to measure and keeps lawyers in control.
The next step is often knowledge base search across precedents and past advice, built as a knowledge assistant. Firms with high volumes of standard documents add document automation, and firms that want clients to share files securely add a client portal. Each assistant is tested on real documents with your lawyers before it is used on live matters.
Models and tools
MCP servers and AI models that matter here
These connect AI to the tools this industry already uses. We pick per project and test on real data first.
- Google DriveGoogle's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
- BoxBox's official MCP server lets AI search and read files, ask questions across documents with Box AI, extract data and upload files.
- DropboxDropbox's own MCP server lets AI list, search and read files, convert them to markdown and create, move, share and delete files. In beta.
- Claude Opus 5.5Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
Keep exploring
More for legal
Related services
View all related services- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- Document automation Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
- AI copilots AI helpers built into your product or internal tools that draft, summarize and suggest while people decide.
- Customer portals A secure place where your customers upload documents, check status, pay and message your team.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
Solutions
View all solutions- Contract review assistant Highlight unusual clauses, missing terms and deviations from your standard positions, so reviewers focus where it matters.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- AI document processing Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
- Email triage Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- AI support agent An assistant that answers routine questions from your own content, checks orders and hands anything else to a person.
Industries
View all industries- Insurance Claims intake, document and photo processing, policy knowledge assistants and customer portals for brokers and insurers.
- Tax and compliance services Client portals, document checklists, case queues and deadline tracking for tax preparers and compliance firms.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
- Finance and accounting Client portals, document collection, invoice and receipt processing, and reporting for accounting firms and finance teams.
- Real estate Listing sites, lead handling, CRM automation and document workflows for agencies, brokers and developers.
- Property management Tenant portals, maintenance tracking, owner statements and inbox automation for property managers.
Guides and articles
View all guides and articles- What is RAG and when do you need it? How retrieval-augmented generation lets AI answer from your documents, when it fits and how to build it well.
- RAG vs fine-tuning Two ways to make AI work with your knowledge, compared by cost, accuracy and upkeep.
- How to choose an AI model for your business A step-by-step way to pick an AI model by testing candidates on your own tasks, data rules and budget.
- Prompt writing basics for business teams How to write prompts that get consistent, useful results from AI tools, with templates your team can reuse.
AI models
View all ai models- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- Claude Sonnet 5 Anthropic's balance of speed and intelligence: a strong everyday model for assistants, document work, tool calling and coding.
- Gemini 3.1 Pro Google's most advanced Gemini model for reasoning, software engineering and agent work, reading text, images, audio, video and PDFs. Available as a preview.
- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Gemini 3.5 Flash-Lite Google's lowest-cost current Gemini model for high-throughput work such as sub-agent tasks and document parsing.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
MCP servers
View all mcp servers- Google Drive Google's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
- Box Box's official MCP server lets AI search and read files, ask questions across documents with Box AI, extract data and upload files.
- Dropbox Dropbox's own MCP server lets AI list, search and read files, convert them to markdown and create, move, share and delete files. In beta.
- OneDrive Microsoft's OneDrive MCP server, part of its Work IQ preview, lets AI find, read, create, move, share and delete files in OneDrive.
- AWS S3 Amazon S3 is handled through the managed AWS MCP Server, which lets AI run scripted AWS actions, create presigned links and search AWS docs.
- Confluence Atlassian's official Rovo MCP server lets AI search and read Confluence spaces and pages, create and edit content and add comments and labels.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Context window A context window is the maximum amount of text, measured in tokens, that an AI model can consider at once, including the question, documents and its answer.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Token A token is a small piece of text, often part of a word, that AI models read and write, and that providers use to measure limits and pricing.
FAQ
Questions from legal teams
Have a question that is not here? Ask us directly.
It can extract terms and flag deviations quickly and consistently, and we test it on your own contracts before use. A lawyer checks every result. See contract review.
No. We use AI services under business terms that exclude training on your data, and we can keep documents in the storage your firm already approves.
Assistants answer only from your documents, cite the passage they used and say when they cannot find an answer. We also test for hallucination before launch.
Where it offers an API, yes. Many firms use Google Drive, Box, Dropbox or SharePoint, which we connect to directly. See API integration.