In development

You are welcome to use it on real jobs. Feedback shapes what gets built next, and beta testers keep their pricing fixed for life.

In development · Beta pricing fixed for life

Tell us what you think

GX-11 · AI on the job

Useful AI, not a chatbot in the corner

Takeoff counts your drawings from their own geometry. Dave writes your RAMS, refines a proposal, turns a meeting into minutes and answers questions about live project data. And MCP lets your own Claude talk to a Graftix project directly.

Shot 04 · Hero

AI symbol takeoff mid-run, detections highlighted on the drawing

2400 × 1350

Symbol takeoff

Count the drawing, not the days

Quantifying a drawing set is one of the last genuinely manual jobs left in this industry. A highlighter, a clicker and a weekend. Takeoff works differently from most things sold as AI: the model reads the legend, you draw a box round one instance of a symbol, and the counting is done on the drawing's own vector geometry. Exact centroids, any rotation, and no confidence bands to argue with.

  • The model reads the drawing legend and hands you the symbol list to confirm
  • You draw a box round one instance, and every congruent cluster on the sheet is found
  • Counts are exact, because they come from the CAD geometry rather than a guess at pixels
  • It needs a CAD-exported PDF. Hand it a scan and it says so, rather than inventing a number

Shot AI1

Organisational symbol library

1600 × 1000

Shot 15

Dave answering a question about live project data

1600 × 1000

Dave

Ask about your own job

Dave is not a general-purpose assistant bolted onto the sidebar. He is connected to your live project data, and he turns up where the work already is — on a data card, in the RAMS editor, in a proposal, in the journal after a meeting, and in the summary at the top of a report.

  • Plain-English questions about your own projects, tasks, sites and costs
  • Writes a RAMS from a project intake, scoring likelihood and severity one to five
  • Refines a proposal section, drafts minutes from a meeting, writes a report summary
  • Bring your own Anthropic key if you would rather run it on your own account

Model Context Protocol · Bring your own key

Talk to your projects from outside the app

Graftix speaks MCP, the open standard Anthropic built for connecting AI assistants to real systems. Connect your own Claude with your own API key and it reads your live project data directly. No export, no report builder, no waiting for somebody to pull a spreadsheet together on a Friday afternoon.

Ask for a progress summary across every building on a campus job. Ask which tasks have been blocked longest and who owns them. Ask what material spend looks like against budget this month. You get a written answer, from live data, in the time it takes to type the question.

  • Reads projects, tasks, blockers, programme, materials, financials, attendance, RFIs and certificates
  • Controlled write access: update status, assign work, set dates, log blockers, raise an RFI
  • Runs on your own Anthropic key, billed to you, revocable at any time in Settings
  • Scoped to the organisations and roles your account already holds
  • Every change written back appears in the task audit history like any other edit
Ask about MCP access

"Give me a progress report across every building."

Rolls up completion by site, phase and trade, and flags which buildings are behind programme.

"What has been blocked longest, and who owns it?"

Every open blocker ordered by age, with its owner and the task it is holding up.

"How does material spend compare to budget?"

Cost codes, committed spend and contract value, per project or across the whole portfolio.

"Who is on site right now?"

Live check-ins straight from attendance, without anyone logging in to look.

"Reassign these twelve tasks to the second-fix team."

Controlled write access does the work, and every change lands in the audit history.

The honest bit

AI assists. It does not sign anything off.

Every output from symbol takeoff and from Dave is reviewable before it is used, because in this industry a wrong number ends up on a certificate with somebody's name on it. Dave is an assistant, not a competent person, and the platform is built to keep it that way.

  • You verify anything safety-critical, regulatory or requiring professional sign-off
  • No solely automated decisions with legal or similarly significant effect
  • Your data is never used to train AI models
  • Every organisation gets UK-resident inference via AWS Bedrock
Read the full AI policy

Shot AI2

Takeoff review screen before results are committed

1600 × 1200

In this module

Everything in the AI tools

11

AI symbol takeoff

Exact counts from the drawing's vector geometry, reviewed before anything is committed.

Organisational symbol library

Trained symbols saved for the business, so the next project starts ahead.

Dave AI assistant

Plain-English answers about your own live project data.

Bring your own key

Connect your own Anthropic API key if you would rather run Dave on your own account. Note that requests then go to Anthropic directly, under your own terms, so UK-resident inference is not guaranteed on that path.

Data residency

UK-resident inference via AWS Bedrock, for every organisation.

No model training

Your prompts and project data are never used to train AI models.

RAMS generation

A risk assessment and method statement from a project intake, with likelihood and severity scored one to five.

Proposal refinement

Rewrites a section of a tender proposal, grounded in the design, previewed before you accept it.

Meeting minutes

Turns a live meeting transcript into minutes, omitting a section rather than padding it out.

Report narrative

The executive summary at the top of a Highlight Report, written from the project's own numbers.

MCP access

Point your own Claude at a live project over the open standard, with a token you issue and revoke.

Get started

Give it a drawing and see.

Takeoff is the feature that makes people sit up. Upload a real sheet and run it on your own symbols.