Fixed quote after a free call

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.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Question asked

    A team member asks a question in Teams, Slack or the web page.

  2. 02 Automated

    Documents searched

    The assistant searches only that project's documents.

  3. 03 Automated

    Answer with sources

    It answers with page and clause references, or says it does not know.

  4. 04 PM or estimator review

    PM checks

    The project manager checks drafts such as RFIs before they are issued.

  5. 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 each person sees and what runs in the background, including what happens when something goes wrong.

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.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Project team Teams, Slack, web Assistant service Permissions check Document index Specs, RFIs, terms Language model Claude, Gemini, GPT Answer or draft With page refs Project manager Checks, issues
  • Input
  • Logic and services
  • Data
  • AI step
  • Output
  • People

How it flows

  1. 1 A team member asks a question in Teams, Slack or the web page, and permissions are checked.
  2. 2 The service searches the project's document index for the relevant pages and clauses.
  3. 3 The model answers only from those pages, with references, or says it does not know.
  4. 4 Drafts such as RFIs go to the project manager to check and issue.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI project assistant for specs, drawings & RFIs project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Document sources, permissions, common questions and where the team wants to ask them.

  2. 02

    Indexing

    About 1 week

    Connect document storage, set up per-project indexes and permissions.

  3. 03

    Build

    About 2 weeks

    Assistant service, Teams or Slack app, RFI and submittal drafting, admin view.

  4. 04

    Test

    1 to 2 weeks

    A test set of real questions with known answers; the team signs off accuracy.

  5. 05

    Launch

    2 to 3 days

    Roll out to one project team, then widen.

  6. 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

Claude, Gemini or OpenAI models Laravel or n8n AI Agent node SharePoint, Google Drive, Procore or ACC documents A vector index (pgvector or similar) Microsoft Teams or Slack app Single sign-on through Microsoft or Google

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • 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
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

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.eu

UK: 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.uk

EU 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.eu

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 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. 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. 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. 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

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

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

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 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.

Book a free 20-minute call