Company Docs Q&A Pack

Name: Company Docs Q&A Pack
Brand: @ai

by @ai

Workflow pack by @aiKnowledge & support

An internal assistant that answers from your own documents with a source link for every answer, and says so when the documents don't cover it.

What’s good

Answers only from your own documents, with a source link per fact
Says "I couldn't find that" instead of guessing
Stays in sync: edits, new and deleted files, skips unchanged ones

Heads-up

Needs n8n, OpenAI and Supabase accounts and about an hour to set up
One shared chat login; no per-person document permissions

What you end up with

A login-protected chat page (and optional Slack bot) where staff ask questions and get short answers taken only from your company documents, each with a link to its source, or an honest "I couldn't find that in the documents".

How it works

Put your policies, handbook and guides in one Google Drive folder
Create a free Supabase project and run the included SQL script
Import the two workflows into n8n and connect Google Drive, Supabase and OpenAI
Paste your folder link into Settings and run the indexing workflow once
Add your company name and who to contact for unanswered questions
Publish, then share the chat link and login with your team
Optional: let staff ask in Slack, or re-index within the hour when files change

What you need

The pack is a one-time purchase. These services are billed by their own companies.

n8n
Cloud Starter or free self-hosted
Cloud Starter is $20/mo billed yearly (2,500 executions a month, 14-day free trial); each question is one execution, the daily sync another. Community Edition self-hosted is free.
$20/mo
OpenAI API
Pay as you go (prepaid credits from $5)
Embeddings (text-embedding-3-small) to index the documents and gpt-5-mini to answer; cost depends on use: about 135,000 tokens to index ~200 pages once, about 3,200 input tokens for a first question.
Depends on use
Supabase
Free plan
Stores and searches the document passages (pgvector). Free projects pause after a week without activity; the daily sync normally keeps it active.
Free
Google Drive
Free personal account
One folder holds the documents the assistant may use.
Free
Slack
Free plan (optional)
Only needed if staff should ask by @mentioning a bot.
Free

Running cost

From $20/moplus usage-based costs

About $0.004 to $0.02 in AI costs per question, depending on the model

How that’s worked out

Per question: about $0.004 with Gemini 3.8 Flash or $0.02 with Claude Opus 5.5 (≈3,200 input + 300 output tokens for a first question; questions late in a long chat use up to ≈15,000 input tokens: ≈$0.012 / ≈$0.066). With the default gpt-5-mini the cost depends on use (no verified price). Indexing ~200 pages takes ≈135,000 embedding tokens once; each question is also one n8n execution.

Setup

Runs on: n8n 2.x, cloud or self-hosted
Difficulty: Medium
Setup time: About 60 minutes

Example

In

A staff member asks in the chat: "Can a customer return a blender they already opened?" (sample documents: a fictional employee handbook, a 3-page refund-policy PDF and an IT setup guide in Word).

Out

"Small kitchen appliances and electronics (for example blenders, kettles, coffee makers and lamps with smart features): 14 days. [refund-policy.pdf, p. 1]" with a link to the PDF. For "Can I bring my dog to the office?" it replied "I couldn't find that in the documents. Please ask your manager or HR …". Retrieval and citations came from the real workflow; the answer wording came from our rule-based test stand-in, not a real AI model.

What’s in the pack

2 n8n workflow files (index the documents, ask the docs)
Supabase setup SQL (table, search function, indexed-files view)
Step-by-step setup guide
All prompts with tuning tips
3 fictional sample documents (Markdown, PDF, Word) and test questions with expected answers
Test report

Support: Setup guide, sample data and a test checklist are included; email questions to support@atai.market.
License: Original @ai pack. Use it in your own business; don't resell or republish it.

How I tested it

Run end to end in n8n 2.41.6 with local stand-ins for OpenAI, Google Drive and Slack and a real PostgreSQL + pgvector database: indexing, skip/re-index/remove, five failure cases and 7 chat questions behaved as designed; real AI answer quality was not tested.

The full test report comes with the pack. Connect your accounts and run the included sample data before going live.

Free templates that do part of this

n8n community template library Free 12,895 free community templates (Oct 2026). You adapt, connect and test them yourself; quality and upkeep vary.

Compare workflow packs

	Lead Follow-Up Pack	Long Video to Clips Pack	Invoice Intake Pack	Company Docs Q&A Pack
Price	$49One-time price; the services it runs on are billed separately	$49One-time price; the services it runs on are billed separately	$49One-time price; the services it runs on are billed separately	$49One-time price; the services it runs on are billed separately
Runs on	n8n 2.x, cloud or self-hosted	n8n 2.x, cloud or self-hosted	n8n 2.x, cloud or self-hosted	n8n 2.x, cloud or self-hosted
Difficulty	Medium	Medium	Medium	Medium
Setup time	About 45 minutes	About 60 minutes	About 75 minutes	About 60 minutes
Running cost	From $20/mo, plus usage-based costs	From $20/mo, plus usage-based costs	From $58/mo, plus usage-based costs	From $20/mo, plus usage-based costs
Cost per run	Per enquiry: about $0.004 with Gemini 3.8 Flash or $0.02 with Claude Opus 5.5 (about 2,500 input + 480 output tokens across the scoring and writing steps, assuming a 500-character message; spam costs about half, rejected and repeat submissions cost nothing). With the default gpt-5-mini the cost depends on use (no verified price). Each enquiry is also one n8n execution.	Per 60-minute video: about $0.18 with AssemblyAI Universal-2 ($0.15) and Gemini 3.8 Flash (about $0.03), up to about $0.35 with Universal-3.5 Pro ($0.21) and Claude Opus 5.5 (about $0.14). Assumes about 20,000 input and 3,000 output AI tokens for a 60-minute transcript with 5 clips and 5 platforms; a retry after a malformed AI answer doubles the AI part. With the default gpt-5-mini the AI part depends on use (no verified price). Each video is also 2 n8n executions; Google Drive and Gmail are free.	Per invoice: about $0.003 (text PDF) or $0.005 (scan or photo) with Gemini 3.8 Flash, or about $0.016 / $0.028 with Claude Opus 5.5. Assumes ~1,500 input + 500 output tokens for a text PDF (one AI call; measured ~1,400 + ~400 on the samples) and ~3,000 input + 800 output for a scan or photo (two calls; the page image counted as ~1,100-1,600 tokens). With the default gpt-5-mini the cost depends on use (no verified price). Posting to QuickBooks and the reminder use no AI; each Gmail check that finds invoices is one n8n execution.	Per question: about $0.004 with Gemini 3.8 Flash or $0.02 with Claude Opus 5.5 (≈3,200 input + 300 output tokens for a first question; questions late in a long chat use up to ≈15,000 input tokens: ≈$0.012 / ≈$0.066). With the default gpt-5-mini the cost depends on use (no verified price). Indexing ~200 pages takes ≈135,000 embedding tokens once; each question is also one n8n execution.
Support	Setup guide, sample data, test checklist; email support	Setup guide, sample data, test checklist; email support	Setup guide, sample data, test checklist; email support	Setup guide, sample data, test checklist; email support
Best for	Small businesses that get enquiries through a website form	Podcasters and creators who post short clips from long recordings	Small businesses that pay supplier invoices in QuickBooks Online	Teams with handbooks, policies and SOPs in Google Drive
Skill level	Any level	Any level	Any level	Any level
	Notify me	Notify me	Notify me	Notify me

Customer reviews

No reviews yet.

Review this product

Share what worked and what didn’t. Reviews from buyers get a Verified Purchase badge.

Write a customer review

Also in Workflow packs

See the full ranking

Notify me