AI Integration Platform

2kw.ai Documentation

Define an agent once (model, instructions, tools, knowledge and approvals) and 2kw.ai runs it: through an OpenAI-compatible API, inside your own product, or in the chat app. Gateway, traces and evals sit under every agent.

Quick Start

1

Install the CLI and set your key

Create a key on the API keys page, then:

npm install -g @2kw/ai
export AI_2KW_API_KEY=sk_your_api_key
2

Create an agent

backbone agents create --name first-agent --model gpt-5.1 \
  --instructions "You are a concise assistant. Answer in two sentences at most."
3

Talk to it

backbone agents run first-agent "What can you help me with?"

The full guide adds the API call, conversations and the chat app: Quickstart: your first agent.

Managed agents

Agents inside your product

Drop a managed agent into your own app. Your UI and brand. 2kw.ai runs the rest.

Read more

Your team, your agents

Talk to your organization's published agents in the chat app, with attachments, citations and tool approvals.

Read more

Fully managed

Gateway, traces and evals under every agent.

Read more

Resources

Quickstart: First Agent

From signup to a first agent conversation in about ten minutes.

Agents

Versioned assistants with server-side tools, knowledge search, citations and human approval, run through the Responses API.

Agent Tools

Built-in tools, your own webhooks, client-executed tools, knowledge search with citations and files in a turn.

Agent Connectors

Give an agent the tools of an MCP server, with sign-in, approved hosts and images and files in results.

Agent Approvals

Decide which tool calls run on their own and which wait for a person, and set the conversation mode.

Skills

Versioned SKILL.md bundles an agent loads on demand, pinned per run.

Knowledge

Upload documents and get hybrid semantic and keyword search with durable citations.

Microsoft 365

Let agents read and write Outlook mail and calendar and read contacts, each member signed in with their own Microsoft account.

Chat App

Talk to your published agents at chat.2kw.ai, with attachments, citations and tool approvals.

Scheduled tasks

Have an agent run on a schedule, such as a daily digest, and find each result in a new chat.

Embeddable Surface

Put an agent into your own web application as a chat panel with one script tag.

AI Gateway

One API, any provider. Use the OpenAI SDK you already know — 2kw.ai routes to the right backend.

Providers & BYOK

Connect your own OpenAI, Azure OpenAI, Anthropic, xAI, Mistral or Ollama account and call it through the gateway.

Prompts

Version-controlled prompt templates with variables, labels, and built-in testing.

Transcription

Turn audio into text, JSON, SRT or VTT through an OpenAI-compatible endpoint.

Data Extraction

Define a JSON schema, feed in any text or document, and get back validated structured output.

Extraction Schemas

Create, version, label, validate and test the JSON Schemas that drive an extraction.

Quality and Rules

Read grounding and confidence scores, and check output with business rules.

Large Documents

How long inputs are split, extracted and merged, and what to expect from the result.

Document Conversion

Turn PDFs, Word docs, emails, and images into clean text ready for extraction.

Files

Upload files once through the OpenAI-compatible Files API and attach them to an agent turn.

CLI

Manage agents, schemas, prompts and extractions from the terminal.

MCP Server

Give Claude Code, Cursor, Codex and other MCP clients direct access to the platform.

n8n

Run extractions, prompts, conversions and agents from n8n workflows with the 2kw community node.

n8n workflows as tools

Let an agent run the workflows of your own n8n, and choose per agent which ones.

API Keys

Create and manage authentication tokens for the API.

Errors

Every status and code, what it means and what to do next.

Usage & Rate Card

What 1x, 5x and 10x cover, worked examples per model, and the price of every token, page and minute.

Datasets

Versioned test data you run experiments against, so past results stay reproducible.

Evaluators

Turn experiment outputs into comparable scores per item and per variant.

Queues

Route traces, spans and experiment results to human reviewers and record their scores against your own rubrics.

Experiments

Compare models, prompts, schemas and parameters against the same test data before you ship.

Observability

Send OpenTelemetry traces and see your own spans next to every 2kw.ai call.

Changelog

What each release added and changed, newest first, from the agents platform on.

Was this page helpful?