Tokoaido
Book an X-Ray

Agent Builder

Build agents. Or let the platform build them for you.

Tokoaido is not a black box that either does everything or nothing. Author your own agents with a no-code blueprint, run the built-in fleet out of the box, and let the platform recommend and build new agents from what it discovers. Every one draws on a governed tool library, and the agents you build start advisory and earn their autonomy.

Three ways agents get built

Bring your expertise, or borrow ours.

You author them

Describe an agent as a blueprint — a signal to watch, a finding to flag, a governed action to propose. No code. It compiles to a real, sandboxed agent on the same governed surface the platform uses.

The platform ships a fleet

A five-tier fleet runs out of the box. Sensing agents watch the streams, diagnostic agents find root cause, optimizers propose actions, the governed executor carries them out, and an orchestrator resolves trade-offs across the fleet.

The platform proposes them

It discovers your real processes, recommends automations ranked by ROI and risk, generates connectors from an OpenAPI spec, and improves its own agents over time from measured outcomes.

Build your own, no code

From a signal to a governed agent in minutes.

A domain expert — a reliability engineer, an ops lead — describes an agent as a blueprint. No prompts to wrangle, no pipeline to wire. It compiles to a real, sandboxed agent that runs on exactly the same governed surface as the platform's own.

  1. 01
    Choose a signal
    A machine tag or a system event to watch — a pump's vibration, an SLA field on a ticket, a spend threshold on a PO.
  2. 02
    Set the condition
    Rises above, falls below, or trends — with a threshold or a window. Plain choices, no query language.
  3. 03
    Describe the finding
    What it means, in plain language, with live values filled in — so a human reviewer immediately understands.
  4. 04
    Define a governed action
    A write to an IT system through a connector, or an OT change routed through MES/SCADA. The Safety Instrumented System and direct-PLC targets aren't even expressible.
  5. 05
    Dry-run, then publish
    Test the agent against telemetry before it goes anywhere. Publish it at advisory, where it earns autonomy from its track record.
Work order · Coolant Pump 03Awaiting approval
Action
Raise maintenance work order
Risk
Medium · €1,840 est.
Signer
Reliability lead
Approved by Reliability leadwhy: defect confirmed on spectrumrisk Medium
Work order proposedMaintenance Plannerrisk Medium
Diagnosis, score 0.86Root-Cause Analystouter-race defect
Finding, zone CReliability Sentinel4.0 mm/s RMS
✓Recorded: who signed, why, risk
Example

Why ours is different

A builder that can't build something dangerous.

A raw agent builder lets you write a prompt and hope. Ours makes governance the substrate — so the agents you build are the ones you can actually put into production.

Autonomy is earned

Agents you build start advisory and are promoted only by a measured track record of approved, effective actions.

Human-in-the-loop

Actions wait for a person while the agent is advisory or when the risk is high; nothing high-risk executes silently.

Safety by construction

A direct PLC write or any Safety Instrumented System interaction is blocked in the architecture — unexpressible, not just discouraged.

Checked & attributable

Changes to an agent are shadow-tested and blocked if they regress, and every consequential action is written to the audit log with who, what, risk and why.

The tool library

An agent is only as capable as its tools.

A tool is any governed capability an agent calls to gather, reason, and act: read a PDF, run a three-way match, query a system of record, adjust a setpoint through MES. The library ships with 168 tools across 11 categories, and it keeps growing.

74 run with nothing connected94 light up as you connect systems46 governed writes, each proposed and risk-checked
Documents & content22
Data & transformation7
Web & APIs7
Files & storage17
Email & messaging12
Enterprise systems28
Manufacturing & OT35
AI & reasoning5
Logic & control14
Finance & accounting17
Compliance & governance4
Document intelligence

Template-free extraction, OCR, and grounded answers with a citation behind every claim, provided by a separate document-intelligence service.

Mint a tool from a spec

Give the generator an API's OpenAPI spec and it produces a governed connector.

Any REST or OAuth API

The live HTTP and OAuth connector turns a web API into a tool an agent can use.

Bring outside agents

External agents can be registered and run under the same governance. MCP tool servers are supported as a client.

The point: a system you connect becomes a tool, and the platform equips the agents it builds from exactly this library, always within the governance and the hard safety boundary.

Operations X-Ray

Build your first agent with us.

Ask for a guided walkthrough: author a governed agent, dry-run it against telemetry, and publish it at advisory.

Book an X-Ray →Sign in