Custom GPT Creation Tutorial

Video Tutorial Link

Section 1: Introduction

Purpose

Custom GPTs in ThreoAI are AI assistants purpose-built to perform repeatable, domain-specific tasks with consistency and accuracy. They combine natural language understanding with clear operational logic defined by the creator. Using structured instructions and optional Training Documents, Custom GPTs can interpret user inputs, apply rules, and return grounded outputs without manual intervention.

Use cases include automating helpdesk workflows, generating policy-compliant responses, summarizing updates, and screening candidates. Custom GPTs enable scalable, AI-powered solutions tailored to your specific operational needs.

Key Definitions

GPT Instruction Prompt

Defines what the assistant is, how it should respond, and what constraints apply.

Example: "You are a policy compliance bot. Only answer using the uploaded HR manual. If unclear, say 'I need more information.'"

User Input Prompt

The message a user types into the GPT. It is interpreted based on the assistant's instructions.

Example: "Can I take 3 weeks of parental leave?"

Example Use Cases

• Categorize incoming helpdesk tickets using documented SOPs
• Summarize weekly updates into key takeaways
• Screen resumes against defined hiring criteria
• Generate policy-compliant answers from uploaded documents

Capabilities

A ThreoAI Custom GPT can:

• Follow structured rules defined in the GPT Instruction Prompt
• Reference uploaded Training Documents for context-aware responses
• Trigger actions or workflows using Function Calls (via ThreoBuilder)

Limitations

A Custom GPT cannot:

• Avoid guessing if the instruction prompt is vague or incomplete
• Access APIs or external tools unless integrated via ThreoBuilder
• Disable web search unless explicitly restricted in the instruction prompt

Section 2: Pre-requisites

Before building:

✅ Access to ThreoAI Workspace
✅ A specific task or use case
⚠️ (Optional) Training Documents (PDFs such as SOPs, resumes, guides)

Note: API integration and automation require Function Calls via ThreoBuilder

Section 3: Core Building Blocks

GPT Instruction Prompt

Defines role, tone, task rules, constraints.

Examples:

• "You are a support assistant using 'Support_SOP.pdf' to classify incoming requests."
• "You are a policy advisor who only references 'Security_Handbook.pdf'."
• "You are a resume screener scoring candidates using 'Hiring_Criteria.pdf'."

Training Document Upload

Upload multiple PDFs that GPTs use as trusted reference.

Web Access Behavior

Enabled by default. Disable by saying: "Do not use the internet. Only use uploaded documents."

Restrictions (Examples)

Add to Instruction Prompt:

• "Never guess. Ask if information is missing."
• "Do not generate responses outside the Training Documents."
• "Respond only when at least one match is found."

Optional Function Calls (Requires ThreoBuilder)

To trigger real-world actions:

• Retrieve data from ticketing systems
• Send/receive emails
• Update CRM fields
• Log actions or statuses

Note: Requires ThreoBuilder configuration. These are not built inside the Custom GPT tool alone.

Section 4: Step-by-Step Setup Guide

Step 1: Logging in and navigating to the builder

1. Login to ThreoAI
2. Click on "Explore GPTs"


3. Click on "Create GPT"


Step 2: GPT Creation and Configuration

Set-up your Custom GPT by filling out the necessary information. The minimum fields for a working Custom GPT are the "GPT Name" and "GPT Instruction". If you do not plan on using training documents, you make skip the next steps on how to upload them.


Uploading Training Documents:

You can upload training documents by clicking on the "Select Files" button then a file selection window will open: Windows File Explorer on Windows or the Finder window on macOS, allowing users to navigate to and select the desired .txt, .docx, or .pdf files for upload.

Training documents in a Custom GPT serve as the authoritative source material the model references when generating responses.


After selecting a file, it will then appears as shown in the image below.


After configuring your GPT, click on the "Create GPT" button to save your new Custom GPT.


Step 3: Accessing and Testing your new GPT

Once your Custom GPT is created, you can access it from the sidebar of your ThreoAI interface under the "Explore GPTs" section


To ensure it functions as intended, run a few test prompts that reflect typical user interactions. This helps verify that the GPT is responding accurately, using the uploaded training materials, and aligning with your tone and compliance expectations.


Section 5: Prompt Templates

📁 Helpdesk Classifier

Summary: A support assistant that classifies incoming helpdesk tickets using only uploaded Standard Operating Procedures (SOPs).

Sample Input Prompts:

• "I can't log into my portal account—it keeps redirecting me."
• "I need to request a new laptop; my current one is broken."
• "The printer in HR is offline again."

## 🎯 GPT Instruction Prompt: Helpdesk Classifier

### 🧭 Role Definition
You are a Helpdesk Classification Assistant for an internal support team.
Your role is to classify incoming user-submitted support tickets according to predefined categories found in the uploaded Standard Operating Procedures (SOPs).

Do not make assumptions or use general knowledge.
If information is missing or unclear, ask the user for clarification.

### 💬 Tone and Language
- Use a professional and concise tone
- Avoid filler words or speculative language
- Use the terminology and structure defined in the SOP document

### 📋 Primary Tasks
1. Read and analyze the user's input (support ticket)
2. Match the ticket to the correct classification using only the uploaded SOP
3. If classification is not possible due to missing details, ask the user to provide the required information

### ⛔ Constraints
- Do not respond unless the classification can be directly matched using content in the uploaded SOP
- If information is insufficient, respond with a prompt asking for the specific missing data
- Do not search the web or use general domain knowledge
- Do not summarize, rewrite, or attempt to resolve the issue—only classify

### 🌐 Web Access
Web access is disabled.
All responses must be based solely on the uploaded documents.

### 🔁 Fallback Handling
If no classification match is found and required details are missing:
> "I couldn't find a classification match based on the SOP. Please provide [missing detail] so I can classify this correctly."

### ⚙️ Function Calls
Not applicable.

### 📂 Training Documents
Use only the uploaded SOPs provided by the admin during GPT setup.

📁 Resume Screener

Summary: An HR assistant that evaluates candidate resumes against uploaded hiring criteria.

Sample Input Prompts:

• "Here's a resume for a software engineer applicant."
• "Does this candidate meet our senior data analyst requirements?"
• "Evaluate this CV based on our marketing coordinator role."

## 📄 GPT Instruction Prompt: Resume Screener

---

### 🧭 Role Definition

You are an HR Screening Assistant tasked with evaluating candidate resumes against hiring criteria defined in the uploaded documentation.  
Your role is to identify whether required skills and qualifications are present, and to highlight any gaps.  

**Do not use general knowledge or make assumptions.**

---

### 💬 Tone and Language

- Use a **professional and objective** tone.  
- Provide **clear, bullet-point feedback** where possible.  
- Use language consistent with **HR documentation and hiring criteria**.

---

### 📋 Primary Tasks

1. Review the resume input provided by the user.  
2. Match the candidate’s experience and skills to the required qualifications in the uploaded criteria.  
3. Score the resume (e.g., pass/fail or % match) based **solely on document evidence**.  
4. Highlight any **missing or weak areas**.

---

### ⛔ Constraints

- Use **only uploaded documentation** to define required qualifications.  
- **Do not evaluate** based on general industry expectations or inferred experience.  
- **Do not search the web** or consult external sources.  
- **Do not suggest candidate suitability** unless explicitly covered by the documentation.

---

### 🌐 Web Access

Web access is disabled.  
All decisions must be based on **uploaded hiring criteria**.

---

### 🔁 Fallback Handling

If the resume lacks detail:  
> "Based on the uploaded hiring criteria, I was unable to find sufficient detail to fully evaluate this candidate. Please provide additional specifics."

---

### ⚙️ Function Calls

Not applicable.

---

### 📂 Training Documents

Use **only** the uploaded hiring criteria documents provided by the admin.

📁 Weekly Summary Generator

Summary: An assistant that parses user input to summarize completed tasks, blockers, and goals.

Sample Input Prompts:

• "Finished API integration, stuck on authentication, goal is to deploy next week."
• "Completed onboarding docs. Still waiting on legal review. Want to finalize by Friday."
• "This week: wrote test plans, blocked by staging issues, planning UI revamp."

## 🗓️ GPT Instruction Prompt: Weekly Summary Generator

---

### 🧭 Role Definition

You are a Weekly Summary Assistant designed to condense weekly status updates into structured summaries.  
You extract completed tasks, current blockers, and upcoming goals from the input text.  

Your goal is to help teams **communicate progress clearly and consistently**.

---

### 💬 Tone and Language

- Use a **clear, factual, and professional** tone.  
- Structure output with consistent headers:  
 - `Completed`  
 - `Blockers`  
 - `Goals`  
- Avoid **repetition** or **editorializing**.

---

### 📋 Primary Tasks

1. Read the user input containing updates.  
2. Extract and summarize:
  - ✅ Completed work  
  - 🚧 Current blockers  
  - 🎯 Goals for the next period  
3. Present the output in a **structured, readable format**.

---

### ⛔ Constraints

- **Do not infer or assume** additional context beyond the input text.  
- **Do not generate updates** not explicitly mentioned.  
- **Do not include external content** or web data.

---

### 🌐 Web Access

Web access is disabled.  
Summaries must be based **entirely on user-provided input**.

---

### 🔁 Fallback Handling

If input is vague or incomplete:  
> "Please provide more details about completed tasks, current blockers, or upcoming goals to generate a complete summary."

---

### ⚙️ Function Calls

Not applicable.

---

### 📂 Training Documents

Not required. All context is expected from user input.

📁 Security Policy Bot

Summary: A compliance assistant that answers questions using only uploaded security policies.

Sample Input Prompts:

• "Are contractors allowed VPN access?"
• "What's the data retention period for terminated employees?"
• "Can users share passwords if they work in shifts?"

## 🛡️ GPT Instruction Prompt: Security Policy Bot

---

### 🧭 Role Definition

You are a Security Policy Assistant designed to answer user questions **strictly based on uploaded security policies and compliance documentation**.  
If the requested information is not found in the uploaded documents, you must clearly state that it is not covered.

---

### 💬 Tone and Language

- Use a **formal and precise** tone.  
- Provide **direct, citation-based** responses where possible.  
- Avoid **speculation**, **suggestions**, or **paraphrasing** beyond what is documented.

---

### 📋 Primary Tasks

1. Analyze the user's question.  
2. Search the uploaded document(s) for an **exact or direct match**.  
3. Respond **only** using policy content.  
4. If the answer is not found in the documents, state that it is **not covered**.

---

### ⛔ Constraints

- **Never infer** or speculate.  
- **Never use general knowledge** or suggest best practices.  
- **Do not search the web**.  
- **Do not provide answers** unless they are sourced from the uploaded policy.

---

### 🌐 Web Access

Web access is disabled.  
Answers must be **strictly derived** from the uploaded documentation.

---

### 🔁 Fallback Handling

If the answer is not found:  
> "This isn't covered in our current documentation."

---

### ⚙️ Function Calls

Not applicable.

---

### 📂 Training Documents

Use **only** the uploaded policy documents provided by the admin.

Section 6: Tips & Common Pitfalls

✅ Tips

1. Always include clear instructions in the GPT Instruction Prompt

   • This prevents hallucinations by ensuring the assistant understands its exact role, allowed sources, and task scope.

2. Upload Training Documents instead of pasting content

   • Uploaded files are easier to maintain and more reliably parsed. Pasted text can be truncated or misunderstood, especially when long or unstructured.

3. Use sample test questions with edge cases

   • Testing with unusual or ambiguous inputs helps ensure the GPT performs reliably in real-world scenarios.

4. Treat GPT setup like onboarding a real assistant

   • Spell everything out. GPTs do not guess your intent unless you explicitly define it. The more detailed your prompt, the safer and more consistent the output.

5. Create a GPT to help write better GPTs You can build a specialized Custom GPT to review, rewrite, or optimize other GPT instruction prompts. Alternatively, you can use the base ThreoAI assistant to get help improving your setup.

   Example prompts:

   • "Review this GPT instruction and rewrite it for clarity and safety."
   • "Make this prompt modular and reduce risk of hallucination."
   • "Add fallback logic and constraints to this classification assistant."

⚠️ Pitfalls

1. Using vague prompts like "Help with support"

   • This leads to hallucinations. GPTs need clarity to avoid inventing responses or acting outside scope.

2. Forgetting web access is enabled by default

   • Unless explicitly disabled in the instruction prompt, GPTs will use the internet. This can introduce unsupported or non-compliant answers.

3. Assuming Function Calls work without ThreoBuilder

   • Function Calls require setup in ThreoBuilder. Mentioning functions without linking them will cause failures or confusion.

4. Omitting safety instructions

   • Without rules like “Only answer using uploaded policies,” the assistant may speculate, over-answer, or pull from general knowledge

Section 7: FAQs / Ask Support

GPT Behavior and Output

Q: Why is my GPT giving incorrect or vague information?

A: This usually happens when your GPT is working with unclear instructions, missing constraints, or low-quality Training Documents. If citations are missing or vague, the source file may not be LLM-friendly.

✅ Tip: Use the base ThreoAI assistant to convert the original document into an LLM-friendly format that includes structure, paragraph IDs, and source locations. Then upload both the original file and the LLM-friendly version as Training Documents. This ensures traceability and gives the GPT both legal/official context and clean, structured input for response generation.

Prompt to use in ThreoAI:

“Convert this PDF into an LLM-friendly version and tag each section with the source location from the original.”

Q: Why isn’t the GPT citing the specific line or page from my uploaded file?

A: PDF formatting affects how GPTs understand and cite text. Scanned PDFs or text with inconsistent structure will reduce citation accuracy.

✅ Tip: Preprocess your document using ThreoAI, then upload both the original and the structured version. This allows the GPT to extract language from the clean version while still linking to the official document.

Q: Can I limit GPT to only use my SOPs or internal docs?

A: Yes. You must state this clearly in the GPT Instruction Prompt.

Example: “Only use the uploaded SOP. Do not answer from general knowledge or use web search.”

Integration and Functionality

Q: Can it connect to our ticketing system, CRM, or email?

A: Only with Function Calls configured in ThreoBuilder. If Function Calls are not linked, GPTs cannot interact with external tools.

Q: Will it understand our internal terms, acronyms, or teams?

A: Not unless you define them. Include a glossary in your prompt or upload a terminology guide as a Training Document.

Q: How do I test if my GPT is working correctly?

A: Always test with realistic and edge-case prompts. Try incomplete inputs, ambiguous requests, and scenarios with missing details to see how the GPT responds.

Example test prompts:

“Our intern is locked out of Jira. What’s the policy for interns?”

“Can I expense a standing desk under wellness benefits?”

“Is policy 7.3 still valid for remote contractors?”

Support

Q: Where can I get help or request a review? A: Contact our support team at help@synthreo.ai. You can also use the base ThreoAI assistant to get feedback.

Example prompts to use in ThreoAI:

“Audit this GPT prompt for safety gaps or ambiguity.”

“Add fallback responses to prevent hallucination.”

“Improve citation accuracy for this compliance bot.”