POLR AI Getting Started Series · 5 of 5

Getting started with Claude Code, ship one useful tool.

A hands-on course for technical leaders and dev-curious operators at AEC firms. Set up Claude Code, work on a real internal tool (an Excel macro, a Bluebeam script, a Procore data export, a small Power Automate flow), and walk away with one shipped script your team uses next week.

About 110 minutes, self paced. Narrower audience than the other four resources. CTOs, IT leads, operations engineers, BIM managers, and the rare PM who learned a little Python. Aimed at the operator deciding if this is a real lever or hype.

Start the walkthrough Have us build the tool with you

Reading time · ~110 minBuilt for AEC technical leadersPOLR AI Getting Started Series · 5 of 5

What you will cover

01What Code isAgentic coding versus copy-paste-into-chat. Why the build economics for small internal tools just changed.02Install and authenticateDesktop and CLI. Permissions and what Claude Code can touch on your machine.03Your first useful sessionClean up a Bluebeam or Excel script end-to-end on a small, real artifact.04Plan-then-ExecuteThe pattern that keeps the agent honest on a multi-step task. Worked on a Procore data export.05Hand off and decideVersion control basics for non-developers. Build versus hire versus contract.

Module 01 · Foundation

What Claude Code is, and what it is not.

Claude Code is agentic coding. It reads a codebase, plans changes, makes edits across files, runs commands, and reports back. The shift from copy-paste-into-chat is bigger than it sounds.

Agentic coding in plain English

In Chat, you ask, Claude answers, you paste the answer somewhere. In Code, Claude works inside your project. It reads files, edits files, runs the tests, fixes what it broke, and tells you what changed. You review. You approve. You ship.

For an AEC firm, that means the small internal tools that used to need a developer no longer do. The Excel macro the estimator has been meaning to clean up. The Bluebeam script that almost works. The data export from Procore that a Power Automate flow could clean up if anyone had two days. Claude Code can ship those in an afternoon.

Claude Code does not turn an operator into a developer. It turns an operator into someone who can ship a useful internal tool without hiring a developer for the small stuff. Know the difference.

POLR observation

When Code is the right surface

The work touches real files, real code, or a real script. Not a memo, not a brief.
The change spans more than one file or more than one step.
You want a working artifact at the end, not advice.

When it is the wrong surfaceIf the answer is a paragraph, use Chat. If the work is reading and writing documents, use Cowork. Code is for the day the documents are not enough.

Module 02 · Setup

Install and authenticate.

Ten minutes from zero to your first session. Two surfaces (desktop and CLI), one account.

The install

install.sh

01Install the Claude desktop app from claude.com/download.
02For the CLI, install via npm i -g @anthropic-ai/claude-code.
03Run claude in any project folder.
       Authenticate with the same account you use on the desktop app.
 
# If your firm has not approved an Anthropic plan yet, this is the
# conversation to have with the owner before you go further.

What Claude Code can touch

Files in the folder you launched it in. Nothing outside.
Commands in your shell, with your permission. Each one shown before it runs the first time.
Network calls only when you tell it to. Claude Code is local-first.

Module 03 · First session

Clean up a Bluebeam or Excel script.

Twenty minutes end-to-end on a small, real artifact. Bring a script you have been meaning to clean up. The point is to feel the loop.

The opening prompt

first-session.txt

you ▸Read every file in this folder. Tell me what this
       script does in plain English. Then tell me three things that are
       fragile, three things that are unclear, and one thing that is wrong.
 
       RULESDo not change anything yet. I want to read your
       assessment first. Then we decide what to fix.

Why this opening mattersClaude Code will happily start editing if you let it. Asking for an assessment first slows the loop down to your speed. You stay in charge.

The edit loop

Once the assessment is in front of you, pick the smallest change that makes the script better. Have Claude Code make it. Run the script. Confirm. Commit. Repeat. Two hours later you have a cleaner version of the artifact and a five-line changelog you can hand to the next person.

Module 04 · Pattern

Plan-then-Execute on a real pipeline.

The single pattern that keeps an agent honest on multi-step work. Twenty minutes worked on a Procore data-export pipeline.

The pattern

plan-then-execute.txt

PLANRead the inputs. Write a numbered plan, smallest possible
        steps, no code. Stop. Wait for me to approve.
 
EXECUTETake the approved plan. Implement step 1.
        Show me the diff. Wait for me to approve before step 2.
 
REPORTAfter every step, tell me what you changed,
        what you ran, and what surprised you.
 
# The plan is the contract. If the plan is wrong, fix the plan
# before any code gets written. Cheap to redo on paper.

Worked: a Procore data-export pipeline

The firm exports Procore data into a CSV every Monday. Half the columns are wrong, dates are in two formats, and three subs are spelled three different ways. Plan-then-Execute walks Claude Code through the cleanup once. After that, the script runs every Monday on a schedule.

Plan: identify the columns, the date formats, the alias problem. Stop.
Execute step 1: a normalizer for dates. Show diff. Run on last week's CSV. Confirm.
Execute step 2: a sub-name alias map. Show diff. Confirm.
Execute step 3: the wrap-up script that runs the pipeline end to end on Monday morning.

Three AEC use cases

The patterns where Claude Code pays back fastest at an AEC firm.

Takeoff sanity-check against historical job-cost data.

Claude Code reads the takeoff export and the firm's job-cost history out of the accounting system, flags line items that fall outside the firm's own historical range, and writes a short note explaining why. The estimator runs it before every bid review instead of eyeballing the spreadsheet.

Clash-detection triage against the spec section index.

Claude Code reads the clash report and the spec index together, groups clashes by responsible trade and spec section, and drafts the RFIs the team would otherwise file late. The BIM coordinator reviews and sends, instead of transcribing.

Weekly job-cost variance narrative for the principal.

Claude Code pulls the variance export from the accounting system, reconciles it against the project management notes, and drafts a one-page Friday narrative in the firm's voice. The recurring admin task that used to absorb a chunk of every Friday now runs on a schedule and lands ready to edit.

Module 05 · Hand off

Hand off. Decide what is next.

The fifteen minutes that decide whether your firm should adopt Claude Code, hire someone who can, or contract the work out. Honest about all three.

Version control basics for non-developers

Initialize a git repo in the folder. Even on your laptop, even if nobody else touches it. git init.
Commit after every working change. git add . && git commit -m "what changed".
Roll back with git checkout -- . when an experiment broke everything.

Build, hire, or contract

Build it yourself when the tool is small, the firm has the time, and the tool is the firm's own process (nobody else can describe it as well). Hire someone when you have three or more tools like this in the next year. Contract it out when you want it shipped in four to six weeks with a fixed scope and you do not want the maintenance debt on the team.

POLR's Development service line is the third option. We pair with your team or do it standalone.

Have a small internal tool that has been on the list for a year? Let us ship it.

POLR's Development service line builds custom internal tools for AEC firms. 4 to 6 weeks. Productized scope. We pair with your team or do it standalone.

Book a Development discovery call See our services

Part of the POLR AI Getting Started Series. POLR AI is an independent partner. We are not affiliated with Anthropic.