the donkit platform

one prompt in.a production agent out.

Describe what you need in plain English. Donkit assembles the agent — tools, memory, knowledge, its own database, even the UI — then proves it works before anyone relies on it.

01 — how it works

from a sentence
to production.

Four steps, minutes not sprints. The builder does the engineering; you stay in plain English the whole way.

step · 01
01

describe.

Tell the builder what the agent should do, in plain English. No graphs to draw, no YAML, no framework to learn.

step · 02
02

donkit wires it.

The meta-agent assembles everything — which tools to call, what to remember, what knowledge to load, what data schema it needs — and generates a custom UI to match.

step · 03
03

validate.

Before launch, Donkit runs your agent against generated test cases — including interventional tests that probe how it behaves when things go wrong. Improvements promote only when the evals prove they're better.

step · 04
04

publish.

One click. Your agent gets a shareable app with its own interface, running on production infrastructure. No deploy pipeline to build.

02 — under the hood

what you can't
get anywhere else.

Not a wrapper on a chat box. Interventional evals, a generated UI, a real database and smart model routing per agent — the differentiators, plus the whole platform behind them.

the builder

Agents that build themselves

The builder is itself an agent. It interviews you, drafts the config, creates the schema, wires the tools, and iterates from your feedback — the way a senior engineer would, in minutes instead of sprints.

frontendgenerated

A real UI, per agent

Every agent ships with its own frontend — chat, dashboards, forms — generated from what it actually does. Not an embed widget: an app your users open and use.

chatdashboardformstables
routingdifferentiator

The right model, every request

Donkit routes each request to the model that fits its complexity, domain and cost — automatically.

simple lookup→ haiku$
hard reasoning→ opus$$$
evaluationdifferentiator

Interventional evaluation

Most teams test agents on happy-path demos. Donkit generates evaluation datasets, runs them automatically, and intervenes mid-trajectory to test failure behavior. Every config change is measured — regressions rejected, improvements promoted. Your agent gets better with use.

happy pathpass
tool timeoutpass
bad input injectcaught
escalation rulepass
datadifferentiator

Its own database

Not a spreadsheet bolted on: a real SQL database per agent, with a schema the builder designs and migrates for you. The agent reads and writes under a restricted role — every query logged.

tickets
iduuid pk
statusenum
resolved_attimestamp
memory

Memory that persists

Vector memory for facts and documents, episodic memory for what happened. Long conversations compress into durable summaries instead of truncating.

vectorfacts · docs
episodic7d → ∞
concurrency

Sub-agents for real work

Agents spawn scoped sub-agents — one per document, task or data slice — and run them in parallel. Big jobs decompose instead of overflowing one context window.

observabilitylive

See every token

Full tracing of every run — each model call, tool call and sub-agent step, down to the token. When an agent misbehaves, you see exactly where and why.

plan120ms
search340ms
reply210ms
integrations

Connect anything via MCP

Plug in any Model Context Protocol server — CRMs, ticketing, internal APIs. Credentials are encrypted at rest and never leave the runtime.

CRMticketinginternal APIany MCP server
knowledge

Knowledge built in

Upload documents and Donkit handles the whole retrieval pipeline — parsing, chunking, embeddings, vector search — as a managed background process with per-document status.

parsechunkembedsearch
deploy anywhere

Run on our cloud, or inside your own perimeter.

Deploy the entire platform inside your own infrastructure — same product, your network, your compliance boundary. Nothing leaves your walls.

donkit cloudon-premiseair-gappedVPC
learn about on-premise
ready · 03

your first agent
is one sentence
away.

start building agents