A construction AI assistant that answers from your own project documents
Project teams lose hours hunting through specifications, contracts and old RFIs for one answer. We build a private AI assistant, in Teams, Slack or a web page, that searches your project documents, answers with page and clause references, drafts RFIs and submittal notes and shows its sources every time. It never decides scope, design or safety questions. Projects typically cost $2,500 to $7,500 and take five to eight weeks.
The problem
Why project teams lose hours searching documents
A mid-sized project can carry thousands of pages: specifications, drawings, the contract, addenda, RFI responses and submittals. When a site manager asks which fire-stopping product is specified or what the contract says about weekend working, someone has to find the page.
General chatbots are no help here: they do not have your documents and they will confidently invent an answer. A construction AI assistant must answer only from the project's own files, show exactly where the answer came from and say when it does not know.
What we build
What our construction AI assistant includes
Private document search
Specifications, contracts, addenda, RFIs and submittals indexed per project, with access matching your permissions.
Answers with references
Every answer cites the document, page and clause, with a link to open it.
RFI drafting
Draft RFIs from a site question, with the relevant clauses and drawings referenced, for the PM to edit and issue.
Submittal notes
A checklist of specification requirements for a submittal, for the reviewer to check against.
Where you already work
Available in Microsoft Teams, Slack or a simple web page on phones.
Admits uncertainty
If the documents do not answer the question, it says so and suggests who to ask.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Question asked
A team member asks a question in Teams, Slack or the web page.
-
02
Automated
Documents searched
The assistant searches only that project's documents.
-
03
Automated
Answer with sources
It answers with page and clause references, or says it does not know.
-
04
PM or estimator review
PM checks
The project manager checks drafts such as RFIs before they are issued.
-
05
Site manager or director decides
Design and scope
Design intent, scope and safety questions are decided by the designer, PM or competent person.
How it behaves
How the project AI assistant behaves
What the project team sees
- Answers in Teams, Slack or on a phone
- Page and clause references with every answer
- A clear "not found" when the documents do not say
What the project manager sees
- Draft RFIs and submittal checklists to edit
- Questions the assistant could not answer
- Access limited to each project team
What the automation does
- Searches only the project's documents
- Answers with references or declines
- Never decides design, scope or safety
Edge cases and fallbacks
- Conflicting clauses in two documents
- Both are shown with references, and the question goes to the PM.
- Superseded document
- Answers come from the current revision; older revisions are labelled.
- User without access to a project
- The assistant does not search that project.
- AI provider outage
- Users are told the assistant is unavailable and can search the document store directly.
Architecture
An AI assistant for project documents at a glance.
- Input
- Logic and services
- Data
- AI step
- Output
- People
How it flows
- 1 A team member asks a question in Teams, Slack or the web page, and permissions are checked.
- 2 The service searches the project's document index for the relevant pages and clauses.
- 3 The model answers only from those pages, with references, or says it does not know.
- 4 Drafts such as RFIs go to the project manager to check and issue.
Project planner
How the project runs, phase by phase.
AI project assistant for specs, drawings & RFIs project plan
Typical time to launch: about 6 weeks, then support
-
01
Discovery
About 1 week
Document sources, permissions, common questions and where the team wants to ask them.
-
02
Indexing
About 1 week
Connect document storage, set up per-project indexes and permissions.
-
03
Build
About 2 weeks
Assistant service, Teams or Slack app, RFI and submittal drafting, admin view.
-
04
Test
1 to 2 weeks
A test set of real questions with known answers; the team signs off accuracy.
-
05
Launch
2 to 3 days
Roll out to one project team, then widen.
-
06
Support
Ongoing
New projects indexed, answer quality reviewed monthly.
What it runs on
Real products only, connected through the access each vendor provides. See all integrations
Cost estimate
What it costs, line by line.
-
Discovery and test set
Sources, permissions and real questions with known answers.
$500 – $1,200
-
Build
Assistant service, indexing, Teams or Slack app and drafting actions.
$1,200 – $4,000
-
Integrations
Document storage, project system and single sign-on.
$300 – $1,000
-
Testing and evaluation
Accuracy testing against the test set before launch.
$300 – $900
-
Launch and training
Pilot team roll-out and walkthrough.
$200 – $400
-
Total project estimate
$2,500 – $7,500
Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Model usage, hosting and any vector database are billed to your accounts directly. Scanned drawings without text need extra processing.
Monthly running costs you pay directly
Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.
- AI model usage: Billed by the provider per use; large document sets cost more to index once.
- Hosting and index: Your server or cloud plan, including the vector index.
What pushes cost up
- Systems without an API, or with integration access that must be requested from the vendor
- Writing data back into your core system rather than only reading from it
- Several locations, brands or very different processes to support
- Custom apps, dashboards or a voice line on top of the workflows
What keeps cost down
- One location and one clear process to start with
- Cloud software with a documented API
- Using tools you already pay for instead of adding new ones
- Approved wording and sample data ready at the start
Privacy and consent
Rules we design for, with the sources.
EU: AI transparency
Article 50 of the EU AI Act sets transparency duties for AI systems that interact with people, from 2 August 2026. The assistant is clearly labelled as AI in every channel.
Source: artificialintelligenceact.euUK: competent people decide safety
Under CDM 2015, duty holders plan, manage and monitor health and safety; the assistant can find a method statement clause but never judges whether work is safe.
Source: www.hse.gov.ukEU and UK: confidential documents
Project documents can contain personal and confidential data, so they stay in your storage and with model providers under contract, with access by project.
Source: gdpr-info.euFree tools
Try these first, free.
Guides to read first
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
- 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
- 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
- 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.
How scope stays under control
- Product backlog
- Every feature, fix and question in one prioritised list you can see at any time.
- Acceptance criteria
- Plain-language conditions for "done" on each item, agreed before work starts.
- Change requests
- New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
- User acceptance testing (UAT)
- Before launch your team tests the real workflow against the acceptance criteria and signs off.
Tools we use
Project manager / Scrum master
Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.
Business analyst
Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.
Automation engineer
Builds the n8n workflows, integrations, AI steps and error handling.
Backend developer
Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.
Frontend / mobile developer
Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.
QA engineer
Tests every workflow against the acceptance criteria, including edge cases and failure paths.
DevOps engineer
Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.
Who does what at each phase
- Free call
- Project manager, business analyst
- Understand the problem, check it is worth automating and outline a rough range.
- Discovery
- Business analyst, automation engineer
- Map the current process, systems and data, and agree success measures.
- Design
- Business analyst, automation engineer, backend developer
- Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
- Sprints
- Automation engineer, developers, QA
- Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
- UAT and launch
- QA, DevOps, project manager
- Your team tests and signs off, we switch on, monitor closely and train the team.
- Support
- Automation engineer, DevOps
- Stabilisation window, then optional monthly care with monitoring and changes.
A point of contact
One person who can answer questions and approve decisions, with about an hour a week during the project.
Access
Admin or API access to the systems involved, created as separate accounts with the least access needed.
Sample data
Real but non-sensitive records (or de-identified ones) so we can design and test against reality.
Approved wording
Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.
Vendor agreements
Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.
Time for testing
A few hours from the people who will use the system, for the demos and user acceptance testing.
Working system
Workflows, integrations and any apps running in your accounts, under your keys.
Documentation
Workflow specification, data-flow map, run book and exported workflow files.
Training
A walkthrough for the team and a short recorded video for new starters.
Handover
All access, credentials and code handed over; you can keep us or take it in-house.
Stabilisation window
Fixes for anything that does not meet the agreed acceptance criteria after launch.
Support options after launch
No plan
You run it yourselves after the stabilisation window and contact us when you need a change.
Monthly care
Monitoring, error alerts, small changes and updates each month, with an agreed response time.
Priority care
Faster response times for business-critical workflows and a monthly review call.
How a project moves through our team
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
FAQ
Construction AI assistant questions questions, answered.
Questions whose answers are in your documents: specified products, contract clauses, past RFI responses, submittal requirements and dates. It shows the page every time.
It is built to answer only from retrieved pages and to say when it cannot find an answer. It can still misread a page, so references are always shown and important answers should be checked.
It can read text on drawings and title blocks when the PDFs contain text. It does not interpret design intent from geometry; those questions go to the designer.
It is a focused assistant with a few actions, such as drafting RFIs and submittal checklists. We keep actions narrow so a person stays in control of anything issued.
We use providers and settings where your data is not used for training, keep documents in your storage and limit access by project.
Before launch we test it on real questions with known answers. After launch we track questions asked, answers with references and questions it could not answer.
Free 20-minute call
Want this for your construction firm?
Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.
More for construction firms
All servicesConstruction CRM & opportunity pipeline automation
Track every enquiry, invitation to bid and repeat client in one construction CRM, with follow-ups after each bid, reminders for estimators and a report on where profitable work comes from.
From $1,000 · About 4 weeks Details
Bid & tender management automation
Read new bid packages into a summary, send invitations to the right subcontractors and suppliers, chase quotes before the deadline and line up returns for the estimator to compare.
From $1,000 · About 4 to 5 weeks Details
Subcontractor compliance & COI tracking
Collect and track subcontractor insurance certificates, licences, safety documents and tax checks, chase anything expiring and stop unapproved firms reaching site.
From $1,000 · About 4 weeks Details