HVAC Master Technician Copilot (sample)

This is an example of a technical copilot giving detailed answers to difficult technical questions about systems and devices. It is designed to address the needs of organizations broadly defined as in "the trades" where master level practitioners, trainers, and resources are rapidly retiring from the industry, and replacing them with a younger workforce is difficult. These organizations need to make their frontline workers more efficient and need to replace the more senior "oracles" of their industries who are leaving.

This copilot gives frontline workers answers to even the most difficult questions they may run into while in the field or on the phone with a customer. It is like having a master technician with instant access to every manual in their pocket via Slack, WhatsApp, text message, or a phone call.

📝 Instructions

You are HVAC-bot - an intelligent AI assistant built by Gooey.AI to help US based HVAC technicians answer technical questions about the heating and cooling units they work on. Try to give succinct answers to their questions (at a 8th grade level), taking note of their district and the particular model and manufacturer of heating or cooling unit they are attempting to repair.

- Politely refuse to answer questions beyond the subject of air conditioner, furnace, heat pump or other residential heating or cooling appliances. 
- Only if the user gives a salutation such as "Hi" or "Hello", introduce yourself before answering the user's query with the following text:
Welcome to HVAC-bot. I'm an AI 🤖 designed to help Heating and Cooling technicians. Send me a text or 🎙️voice note with any farming question and I'll give you an answer based on recommendations and best practices from Technical manuals developed by the manufacturers. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons.  Now, what would you like to know? 🔦 🪛  ℉ ℃

🧠 Language Model

📄 Knowledge

Add documents or links to give your copilot a knowledge base. When asked a question, we'll search them to generate an answer with citations.

Submit Links in Bulk

💪 Capabilities

🗣️ Text to Speech & Lipsync

🔠 Translation & Speech Recognition

🩻 Photo & Document Intelligence

🧩 Developer Tools and Functions

⚙️ Settings

📄 Knowledge Base

👩‍🏫 Search Instructions

How should the LLM interpret the results from your knowledge base?

Citation Style

🔗 Shorten Citation URLs

Create Synthetic Data

To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.

Advanced Settings

In general, you should not need to adjust these.

👁‍🗨 Conversation Summarization

These instructions run before the knowledge base is search and should reduce the conversation into a search query most relevant to the user's last message.

🔑 Keyword Extraction

Instructions to create a query for keyword/hybrid BM25 search. Runs after the Conversations Summarization above and can use its result via {{ final_search_query }}.

✏ Embeddings Model

Dense Embeddings Weightage

Weightage for dense vs sparse embeddings. 0 for sparse, 1 for dense, 0.5 for equal weight.
Generally speaking, dense embeddings excel at understanding the context of the query, whereas sparse vectors excel at keyword matches.

Max Citations

The maximum number of document search citations.

Max Snippet Words

After a document search, relevant snippets of your documents are returned as results.
This setting adjusts the maximum number of words in each snippet (tokens = words * 2).
A high snippet size allows the LLM to access more information from your document results, at the cost of being verbose and potentially exhausting input tokens (which can cause a failure of the copilot to respond).

Snippet Overlap Ratio

Your knowledge base documents are split into overlapping snippets.
This settings adjusts how much those snippets overlap (overlap tokens = snippet tokens / overlap ratio).
In general you shouldn't need to adjust this.

🔠 Language Model Settings

Avoid Repetition

Response Format

Max Output Tokens

The maximum number of tokens to generate in the completion. Increase to generate longer responses.

Creativity (aka Sampling Temperature)

Higher values allow the LLM to take more risks. Try values larger than 1 for more creative applications or 0 to ensure that LLM gives the same answer when given the same user input.

Answer Outputs

How many answers should the copilot generate? Additional answer outputs increase the cost of each run.

🛠️ Tools

Give your copilot superpowers by giving it access to tools. Powered by Function calling.

Save JSON as PDF

Run cost = 4 credits

Breakdown: 1 (GPT-4o (openai)) + 3/run

By submitting, you agree to Gooey.AI's terms & privacy policy.

Show Raw Output

Assistant

The electrical requirements for the model 4A7A3030N1000A1, which is similar to the 4A7A3030G, are as follows:

Power Supply: 208/230 volts, single-phase, 60 Hz
Minimum Circuit Ampacity (MCA): 17.0 amps
Maximum Fuse Size: 25 amps

These specifications should help ensure the unit operates safely and efficiently [†].

†. 4A7A3030H1000NA spec sheet.pdf, page 5 https://gooey.ai/2/d6k1

User
what are the electrical requirements of the 4A7A3030G

💁‍♀️ Sources

Generated in 6.0s on

...

ℹ️ Details

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord