Skip to content

Control plane for agentic AI

Agents change every quarter. Your controls shouldn't.

Your agents send the email, move the money, change the record. Fyder gates the effect itself, so swapping models and frameworks never moves the boundary.

Governed surface
ToolReachesGate
source controlC3Named human
payments apiC3Named human
issue trackerC2Named human
outbound emailC2Named human
workspace filesC1None
doc searchC0None
Reaches = highest class the tool can produce.
Its C0 calls still pass unattended — the gate is on the effect.
Routing ·Routing rotates automatically across supported model providers; the tool and gate above hold regardless of which model is active.

The trust gap

You don't have a technology problem. You have a trust problem.

Hand AI to your workforce with no boundaries and no record, and you've handed out power without accountability. That's the gap between what AI can do and what you can trust it to do.

Smarter models won't close it. Boundaries, scope, and a record around every action will. Not policies. Not guidelines. Guarantees.

Effect boundary
Fyder system schematicAgent surfaces feed the Fyder control plane, which enforces an effect boundary before your systems.
Fig. 1 — where the controls sit. Full autonomy up to the boundary; a named human beyond it.
  1. Any surface. Any model.

    Chat, CLI, remote tasks, standing agents — and whatever models and frameworks your people reach for next.

  2. Class and scope resolve here.

    Every tool is registered with the classes of effect it can produce. An agent cannot raise its own class.

  3. One boundary, enforced.

    Autonomy inside. Approval at the effect boundary. A named human beyond it.

  4. What crossing means.

    A write to a system of record, a transmission outward, a disclosure to a third party, or spend. There is no fifth.

  5. The trail holds the context.

    Sources consulted, tools invoked, content retrieved at the moment of the decision.

What the control plane holds

The controls don't live in the agent. They live in the path it has to take.

A control that lives inside a model is a request. A control that sits on the path between the agent and the system is a guarantee. One column below is expected to churn; the other does not move when it does.

Changes without warning

What you swap

  • models and inference providers
  • agent frameworks and harnesses
  • tools, MCP servers, internal APIs
  • the people running any of it
  • whatever ships next quarter

Stays where you put it

What holds

  • the action classes and what each one means
  • which classes require a named human
  • the scope an identity is entitled to
  • the promotion path from user to team to org
  • one record across all of it

Action classes

Four classes. The two that leave the sandbox stop at a person.

Classes sort on one question: has the effect left the agent's own workspace? Reading, drafting and iterating inside it run unattended. Anything that lands in a system other people depend on is a named human's decision. Gates attach to the class, never to the tool — an agent cannot escalate by finding another route to the same outcome, and approval is asked once per effect rather than once per tool call.

C0
Read
Retrieves. Changes nothing.
search · retrieve · summarize · inspect
No gate — full autonomy
Nothing to undo
C1
Draft
Works freely in its sandbox. No effect on systems of record.
draft · scratch analysis · workspace branch · dry run
No gate — full autonomy
Sandbox only — nothing left it
C2
Promote
Crosses into production or shared systems.
edit a ticket · push to main · staging deploy · send email
Named human
Undo is the receiving system's to give
C3
Irreversible
Cannot be undone.
move funds · delete records · production deploy
Named human
No undo path

What compounds

Discoveries stop dying in one person's terminal.

A flow that worked is captured as a skill and promoted upward under the same approval model as everything else. Knowledge outlives the model that produced it and the person who found it.

Skill promotionVersioned · rollback enabled
Userdrafted and run in one workspace · no promotion yetone person
Teampromoted after a team lead reviews the run historythe team
Orgpromoted again after an org owner signs offthe org
Version controlled. Rollback to any prior version. Promotion widens who can run the skill, not what it is allowed to touch.

Next

Bring the tools your people already use.

A briefing walks through how a handful of your real tools would register, the action classes they reach, and where the gates would land across every surface you run.