The Construction Prompt Coach: Get What You Need from AI, Fast.

How to turn AI from generic answers into a practical construction tool — using a simple method that delivers clear, job-ready results fast.

You've heard the hype about AI. You've even tried using ChatGPT or a similar tool to help with your work. You ask it to write an email about a delay or summarize a safety issue, and what you get back is… generic. Vague. Unusable.

It feels like another overhyped tech toy that doesn't understand the grit and reality of the work.

Here's the truth: The problem isn't the AI. It's the instructions we give it. In the world of AI, these instructions are called "prompts." "Vague prompts get you vague results. It's the digital version of garbage in, garbage out"

As a subcontractor, your time is your most valuable asset. You don't have hours to go back and forth with an AI chatbot, rephrasing your request. You need the right document, the right email, or the right summary now.

Instead of guessing, let's use a playbook. By combining a simple framework with core strategies from OpenAI's own guide, you can turn a generic AI into a world-class project coordinator that truly understands how your business works.

Your Blueprint for Perfect Prompts: The CRAFT Framework

A great way to structure your requests is with the CRAFT framework. It's a simple model to ensure you cover all the key details. The CRAFT framework (Context, Role, Audience, Format, Task) was popularized by Lawton Solutions as a memorable and effective method for prompt engineering.

C for Context: The "Where, Why, and With What"

Never assume AI knows what you're talking about. Providing reference text is one of the best ways to get better results. Set the scene, provide the facts, and give the AI all the information it needs to do its job.

Vague Prompt: "Write an email about the problem with the ducts."

Prompt with Context: "We are the HVAC subcontractor on the 'Oak Valley Community Hospital' project. In the west wing, second floor, the recently installed plumbing pipes are clashing with our planned ductwork route shown on drawing M-201. This prevents us from installing the main supply trunk line. Use the foreman's daily log as reference: 'End of day, confirmed clash with P-301 piping run. Notified GC foreman on site.'"

R for Role: The "Who You Are"

This involves asking the model to adopt a persona. It's a magic key. By assigning a role, you tell the AI which experience database, vocabulary, and tone to use.

Vague Prompt: "Explain the ductwork problem."

Prompt with Role: "Act as a Senior Project Manager for an HVAC subcontractor with 20 years of experience. You are professional, firm, and solutions-oriented."

A for Audience: The "Who It's For"

Who are you writing to? An email to the GC's Superintendent requires a different tone and level of detail than a toolbox talk for your crew or a formal notice to the architect.

Vague Prompt: "Write about the clash."

Prompt with Audience: "The audience for this RFI is the General Contractor's Project Manager. They are focused on schedule and budget. We need to clearly explain the issue and the potential for a delay if not resolved quickly."

F for Format: The "What It Should Look Like"

Don't leave it up to the AI model to decide. It's important to clearly state the format you want for the response — whether that's a formal letter, a quick email, a bullet-point list, or just a short summary. Be specific.

Vague Prompt: "Give me the details."

Prompt with Format: "Format the response as a formal Request for Information (RFI). Use a clear subject line. The body must have three sections: 1. The Issue, 2. The Location and Drawing Reference, 3. The Requested Action."

T is for Task: The "What to Do"

Finally, give a clear, direct command. Use strong action verbs like "write," "summarize," "analyze," "compare," or "create a list."

Vague Prompt: "Help with this situation."

Prompt with Task: "Write a draft email to the GC to accompany the formal RFI. The email should briefly summarize the clash, state that the RFI has been submitted, and request a coordination meeting within 48 hours."

Go Deeper: Pro-Level Strategies from OpenAI's Playbook

Once you've mastered CRAFT, you can incorporate these advanced strategies directly from OpenAI's documentation to tackle more complex work.

1. Split Complex Tasks into Simpler Subtasks

Asking AI to do something complex in one shot is a recipe for a bad result. Guide it step-by-step. For instance, when creating a change order justification:

• Step 1: "Summarize the key differences between the originally specified 'Model A' light fixture and the new 'Model B' fixture based on these two spec sheets…"
• Step 2: "Based on that summary, create a bulleted list of the impacts on our electrical scope. Include material cost differences, additional labor hours, and schedule delays."
• Step 3: "Now, combine that information into a formal Change Order Request narrative."

2. Provide Examples to Steer the Output (Few-Shot Prompting)

If you need AI to follow a very specific style or format, give it an example. This is one of the most powerful techniques.

Prompt with an Example: "I need to write a daily safety observation summary. Always follow this format: Issue: [One-sentence description]. Location: [Specific area]. Action Taken: [What was done immediately]. Here is today's observation: 'A worker on the third floor wasn't tied off while working near the edge.' Now, generate the summary in the correct format."

3. Give AI "Thinking Time"

For complex reasoning tasks, ask the model to work out the solution for itself before giving you the final answer. This forces a more rigorous, logical process and reduces errors.

Prompt Without Thinking Time: "Does this contract clause expose us to risk? 'Subcontractor shall be responsible for all site cleanup.'" (This may give a simple yes/no).

Prompt WITH Thinking Time: "First, identify any ambiguous terms in this contract clause: 'Subcontractor shall be responsible for all site cleanup.' Second, list potential scenarios where this ambiguity could lead to a dispute with a General Contractor. Third, based on your analysis, explain the primary financial risk this clause presents for a subcontractor. Finally, answer whether this clause exposes us to significant risk."

The Pelles Philosophy: Computers should learn us, Not the Other Way Around

For decades, technology has forced us to adapt. We learn its quirks, menus, and language. The philosophy here is that this approach is backward. The future of truly useful AI is one where the system learns you.

The strategies above are how you manually coach an AI today. At Pelles, the mission is to build this coaching capability directly into their platform through a three-phase evolution, so you can trigger actions, not write a story about them.

Phase 1: The User Interface — Your Command Center

First, they provide tools to make giving instructions effortless. The Pelles interface is designed to systematize the CRAFT framework internally, removing the guesswork and busywork.

• Your Centralized Context Hub: Instead of copy-pasting, you can connect Pelles to your project documents or simply drag-and-drop a daily report, submittal, or drawing to give the AI the specific facts it needs.
• Structured Inputs/Outputs, Not Guesswork: The platform gives you the ability to define your Role, Audience, and create your desired Formats, to eliminate uncertainty.

Phase 2: AI-Assisted Collaboration — The System Gets Smarter

As you use the interface, Pelles learns. This is where they use AI-powered suggestions to better understand your needs for a seamless human-computer collaboration.

This collaborative loop is driven by continuous learning: each time you accept or refine a suggestion, you're actively guiding the system. It adapts to your projects, recognizes your key contacts, memorizes your communication style, and remembers your preferred document formats, gradually building a personalized understanding of how you work.

Phase 3: Agentic Intelligence — Your Automated Partner

Once the system has learned your recipes, it graduates from collaborator to an autonomous partner. The Pelles system becomes an "agent" that can act on your behalf, intelligently using your templates and data to execute complex tasks from simple commands.

The goal is to free you from prompt engineering, giving you an intelligent partner that understands your workflows and anticipates your needs.

Start Building Your Automated Partner Today

These professional strategies are the training methodology for the future of work. By using them, you're not just getting work done faster today; you are developing the precise communication habits that will power the automated systems of tomorrow.

This is the logic being built at Pelles — a system that listens, learns, and ultimately anticipates your needs. As subcontractors, we work in a world of specifics. It's time our tools did, too.

Build Smarter.