Skip to content
open·agent

Resources

Guides for teams shipping AI customer support

Practical, opinionated writing on bringing your own LLM, grounding your AI in your data, and getting humans out of the loop on the boring questions without losing the moments that matter.

Collaboration

Multiplayer AI: humans and the agent in one live chat

Shared presence, live typing, and summoning the AI for a draft you can edit or send as the AI. How collaborative handling beats the silent-bot handoff.

7 min readRead guide →
Architecture

Bring your own LLM, explained

Why hosted chat platforms mark up AI 8-15x, what BYO LLM actually means, and the cost math on a real ticket.

9 min readRead guide →
AI

How RAG works inside OpenAgent

From PDF upload to grounded answer: chunking, embeddings, vector search, citations. A diagram you can actually trust.

11 min readRead guide →
ROI

The ROI of AI agents vs humans (with HITL)

Per-conversation math, when to escalate to a person, and why the right answer is almost never 100 percent AI or 100 percent human.

12 min readRead guide →
Setup

From signup to live chat in 10 minutes

The exact ten-minute path: provision a workspace, plug in your model key, upload a knowledge doc, paste the embed snippet. Screenshots included.

7 min readRead guide →
Brand

Branding your chat widget that visitors actually trust

Logo, color, voice, consent text, privacy URL: the brand surface visitors evaluate before they type the first message.

8 min readRead guide →
Foundational

What is RAG? Plain-English explanation

Retrieval-Augmented Generation explained without jargon. What it is, what problem it solves, what teams confuse it with.

5 min readRead guide →
Foundational

What is an AI customer support agent?

Different from a chatbot. Uses tools, remembers context, escalates when out of its depth. Eight questions to ask any vendor.

6 min readRead guide →
Foundational

How MCP (Model Context Protocol) works

The open standard AI vendors converged on for tool use. What it is, what changes for buyers, what the moving parts do, and where OpenAgent slots in.

6 min readRead guide →
MCP

MCP interop: Claude Code + OpenAgent, one server, two clients

Register the same MCP server in both Claude Code (the CLI) and OpenAgent (the SaaS). Concrete config side by side, the differences worth knowing, troubleshooting matrix.

8 min readRead guide →
Provider

Using OpenAI for customer support

GPT-4o-mini for the default 80%, GPT-4o for the high-stakes 20%, skip the o-series. Per-ticket cost benchmarks and the Azure OpenAI variant.

7 min readRead guide →
Provider

Using Google Gemini for customer support

The cost-leader. Gemini 2.5 Flash at ~$0.0011/ticket plus first-party embeddings. Why it's the OpenAgent default.

7 min readRead guide →
Provider

Using Anthropic Claude for customer support

Tone and refusal-style leader for brand-sensitive workspaces. When the premium is worth it and when it isn't.

6 min readRead guide →
Strategy

How to reduce customer support ticket volume

Seven moves to cut inbound volume by 30-60% without tanking CSAT. AI deflection, product fixes, the order that compounds.

9 min readRead guide →

Tools & reference

Interactive calculators and reference material. Free, no signup.

Comparisons

Honest side-by-sides against the platforms teams shopping us actually evaluate. Real pricing, real feature gaps, real reasons to pick the other guy where it makes sense.