ChatBot

Questions-answer to be put as context

 

✅ Small Group – Chatbot Context (Founder Version)

1️⃣ Who we are (identity + positioning)

  1. In one sentence, what does Small Group do?

  2. Are we best described as:

    • Software agency

    • AI automation agency

    • Or a hybrid (explain in one line)?

  3. Who are we best suited for?

  4. Who should not work with us?

  5. How big is the team and what roles exist?

  6. Where do we primarily operate (geo + timezone)?

  7. How long have we been building software?

  8. How long have we been working with AI/automation?

  9. What’s the core belief behind Small Group (how we think about tech solving problems)?

2️⃣ What we actually build (capabilities, not buzzwords)

  1. What types of software do we commonly build?

  2. What types of AI automations do we commonly build?

  3. Where do AI + automation fit into your projects vs traditional software?

  4. Do we build MVPs, full products, or both?

  5. Do we integrate with existing tools and systems?

  6. What kinds of problems are we very good at solving?

  7. What kinds of projects do we avoid or say no to?

3️⃣ Proof & trust anchors (critical for the bot)

  1. What proof can we show early? (case studies, demos, internal tools, founder credibility)

  2. Have we built systems similar to what most prospects ask for?

  3. Do we sign NDAs and who owns the code?

  4. What’s one honest reason clients trust us after working with us?

  5. What’s one limitation or boundary we openly admit?

4️⃣ How work actually happens (process + control)

  1. How does a project typically start?

  2. How do we understand a client’s problem before building?

  3. How often do clients see progress?

  4. Do clients talk directly to builders?

  5. How do we handle scope changes?

  6. What happens after launch?

5️⃣ Pricing logic (not numbers, logic)

  1. How do we usually price projects (fixed, hybrid, phased)?

  2. What factors influence cost the most?

  3. When does AI automation make projects cheaper vs more expensive?

  4. What budget misunderstandings do clients often have?

  5. When are we not a good financial fit?

6️⃣ Risk, safety & responsibility (especially for AI)

  1. How do we handle data privacy and sensitive systems?

  2. How do we prevent AI systems from doing the wrong thing?

  3. When do we keep humans in the loop?

  4. What guarantees do we explicitly not give?

7️⃣ Lead qualification & handoff (bot → human)

  1. What information must be captured before human follow-up?

  2. What information is optional?

  3. What signals indicate a serious problem vs curiosity?

  4. What is the ideal moment for the bot to suggest human contact?


Implementation Strategy

 

1️⃣ Overall Architecture (Simple, Robust)

Components

Flow

User message
 → Intent detection
 → RAG retrieval (Small Group knowledge)
 → LLM response (grounded)
 → State update
 → (Optional) booking CTA

Important

2️⃣ RAG Strategy (This is the heart)

2.1 What goes into RAG (ONLY this)

Create one single knowledge base called:

small_group_core_knowledge

Documents to store (MANDATORY)

  1. Company identity & positioning

  2. Services (software + AI automation)

  3. Process & onboarding

  4. Pricing philosophy (not numbers)

  5. Trust & risk handling

  6. Case summaries (even anonymized)

  7. What we say no to

  8. Booking & next steps

⚠️ Do NOT store:

2.2 Chunking Strategy (important)

Chunk size

Example chunk titles

Add metadata:

{
  "category": "services",
  "confidence": "high",
  "last_updated": "2026-01"
}

2.3 Retrieval Strategy

When to retrieve

How many chunks

Hard rule

If no relevant chunk is found, the model must say
“I don’t have enough context to answer that accurately.”

No hallucination allowed.

3️⃣ PROMPTS (This is the gold)

3.1 SYSTEM PROMPT (Non-negotiable)

You are Tushar, the AI assistant for Small Group, an AI automation and software agency.

Your primary goals:
1. Answer questions accurately using ONLY the provided context.
2. Build trust through clarity and honesty.
3. Understand the user’s problem before proposing solutions.
4. Gently guide serious users toward booking a call.

Rules:
- Never invent facts about Small Group.
- If information is not in context, say you don’t have that information.
- Do not ask for contact details until the user shows problem intent.
- Do not repeat booking prompts.
- Be calm, confident, and conversational — not salesy.
- You are allowed to say “we may not be the right fit.”

Tone:
- Professional, human, thoughtful.
- No hype, no buzzwords.

3.2 DEVELOPER PROMPT (Controls behavior)

Conversation policy:
- Early stage: answer trust and capability questions freely.
- Mid stage: ask open-ended questions to understand the problem.
- Late stage: summarize the problem and suggest booking a call.

Problem discovery order:
1. What they are trying to build or fix
2. Why it matters (pain)
3. Who it affects
4. Constraints or past attempts

Booking call is suggested ONLY IF:
- The user describes a real problem
- OR asks for estimates, timelines, or next steps

If user asks unrelated general questions, politely redirect.

3.3 RAG INJECTION PROMPT (Hidden)

This is appended automatically after retrieval:

Use the following Small Group context to answer the user.
If the answer cannot be found here, say so clearly.

<context>
{{retrieved_chunks}}
</context>

3.4 RESPONSE PROMPT (Per message)

User message:
{{user_input}}

Respond by:
1. Directly answering the question using context
2. If appropriate, asking ONE thoughtful follow-up
3. Keeping responses concise and grounded

4️⃣ Booking-Call Goal Logic (Very Important)

4.1 When the model should suggest a call

Trigger ONLY if at least one is true:

4.2 Exact Booking CTA Prompt

This is the ONLY phrasing allowed:

If helpful, someone from our team can review this with you and suggest next steps.
Would you like to book a short call?

Then offer:

No email begging. No pressure.

4.3 After booking intent

Once user says yes:

5️⃣ Safety & Anti-Hallucination Guards

Add these explicit instructions:

If a question involves:
- Legal guarantees
- AI accuracy promises
- Exact pricing
- Regulatory claims

Respond conservatively and recommend a human conversation.

 

N8N implementation

 

1. High-level architecture (mental model)

Chatbot = 4 brains working together

  1. LLM (reasoning + conversation)

  2. RAG (facts about Small Group)

  3. Conversation State (what we know about user)

  4. Conversion Logic (when to push booking)

n8n orchestrates all 4.

2. Knowledge you will store (RAG collections)

Create 4 small, sharp knowledge bases (don’t overdo it).

KB-1: Company & Trust

KB-2: AI Automation

KB-3: Software Development

KB-4: Process & Next Steps

Each doc chunk should answer one question, not paragraphs.

3. Core system prompt (passed to LLM)

This is non-negotiable. This is what makes it feel human and focused.

You are the AI assistant for Small Group, a team that does BOTH:
1) AI automation (agents, workflows, ops automation)
2) Custom software development (MVPs, internal tools, SaaS)

Your goals, in priority order:
1) Clearly understand the user’s problem
2) Answer trust and capability questions honestly
3) Decide whether AI automation, custom software, or a mix is appropriate
4) Move qualified users toward booking a call

Rules:
- Never oversell
- If something is unclear, ask ONE sharp clarifying question
- If the problem is real and non-trivial, suggest a call
- Do not push booking too early
- Sound like a smart founder, not sales copy
- Use retrieved knowledge as ground truth
- If info is missing, say so transparently

4. Conversation control prompt (dynamic, injected)

This is updated on every message:

Known user info:
- Problem summary: {{problem_summary}}
- Industry: {{industry}}
- Company size: {{company_size}}
- Urgency level: {{urgency}}
- Budget signal: {{budget_signal}}
- Trust level: {{trust_level}}

Your task:
- Either deepen problem understanding
- Or answer a trust/capability question
- Or move toward booking a call if criteria are met

5. Qualification logic (VERY important)

Only push for a call if 2 of 3 are true:

This logic lives in n8n, not the LLM alone.

6. n8n workflow (node-by-node)

1. Webhook / Chat Trigger

2. Session Memory (Redis / DB)

3. Intent Classifier (LLM – cheap model)

Classify message into:

Store result.

4. RAG Retriever

Based on intent:

Use:

5. Main LLM Response Node

Inputs:

Outputs:

6. Problem Extractor (LLM or rules)

Extract and update:

Update session memory.

7. Qualification Scorer (IF + Function node)

Increment score if:

8. Call Suggestion Gate

IF:

→ allow booking CTA

Else:

9. Booking CTA Generator

Soft, founder-style CTA:

Examples:

Attach:

10. Human Handoff (optional)

If user explicitly asks:

→ notify Slack / email with:

7. What NOT to do (hard advice)

8. Why this works (founder logic)