Skip to content
Implementa.

Building an AI agent · Guide 3 of 6

How to build an AI chatbot that isn't a chatbot wearing a hat

Building an AI chatbot in 2026 is no longer setting up a Q&A box. It's deciding whether you want a "marketing" chatbot (answers what you wrote), a "support" one (RAG over your knowledge base) or an "agent" (decides and executes actions). The three options have different architecture and price.

See it in production → 24/7 AI SupportBack to the pillar

The 3 types of chatbot and which one you need

TypeWhat it doesWhen to use it
Marketing / FAQReplies with answers you wrote in advanceSmall site, stable FAQs, low budget
Support (RAG)Pulls info from your KB and answers with contextSupport with a solid KB, >500 repetitive tickets/month
AgentDecides and executes actions (not just replies)Complex processes, system integration

RAG architecture step by step

  1. Structure your KB. Short blocks (200-400 words), self-contained, with metadata.
  2. Generate embeddings. Turn each block into a vector with a model (OpenAI ada or equivalent).
  3. Store in a vector database. Pinecone, Weaviate, pgvector depending on scale and budget.
  4. Configure retrieval. For every query: pull the top-k most similar blocks, re-rank, filter by metadata if relevant.
  5. Pass context to the LLM. The LLM gets the retrieved context + the user prompt + the system prompt.
  6. Return the answer with a source citation (optional but recommended).

When the chatbot should hand off to a human (criteria)

  • Low model confidence (answer probability below threshold).
  • Cases flagged as sensitive (complaints, escalations, discount requests).
  • Explicit user request ("I want to talk to a person").
  • Number of turns without resolution — after 5-6 messages with no progress, escalate.
  • Frustration detection — keywords like "this isn't working", "I'm fed up".

Measuring CSAT and deflection without lying to yourself

Same thing as in support: inflated deflection is the trap. Measure:

  • Tickets resolved without escalation with confirmed resolution.
  • Post-interaction CSAT (>4/5 is healthy).
  • Clean escalation rate (every escalation must carry context).
  • CSAT before vs. after the chatbot.

Recommended stacks (self-serve, mid, enterprise)

SizeStackMonthly cost
Self-serveImplementa Support AI, Intercom Fin, Chatbase$79-300/mo
Mid-marketZendesk + custom RAG + integration$1,500-5,000/mo
EnterpriseProprietary platform or Salesforce + custom agent$5,000-25,000/mo

Frequently asked questions

If you get under 100 visits/day, it probably doesn't earn back the setup effort (it takes you more time to configure than it saves). From 500-1,000 visits/day with qualified traffic, yes — a lot. The honest metric isn't "traffic" but "repetitive queries/month": more than 50, it pays.

Self-serve: €0 extra beyond the subscription (€79-149/mo at Implementa). Self-hosted with your KB: €0 license, ~€20-50/mo in LLM tokens for reasonable volume. The real fight is content updates — that takes a human 2-4 hours/month so it doesn't go stale. That's a hidden cost.

Yes, modern LLMs handle multi-language without extra effort. Caveat: your KB has to be in at least one well-written language (English or neutral Spanish best). If your source content is low quality, the problems replicate across every language — amplifies them, doesn't fix them.

Read it, or want it shipped?

The guide covers the what and the why. Getting it into production — that's what we charge for.

Book a conversationSee services
How to build an AI chatbot that isn't a chatbot wearing a hat · Implementa