Controls for AI agents that act in your systems

Konnectify agents use only the tools you add, can't change the fields you pin, pause at their spend limit and wait for a person wherever you require approval. Every step is logged.

Instructions can be ignored. Controls can't.

Three runs of the same $640 refund. Watch which one holds.

Before a run

Decide what each agent may touch

  1. Choose the level for each job

  2. Add only the tools it needs

  3. Pin fields

  4. Set allowed values

  5. Write the rules down

  6. Test on sample data

LevelAI agent

Run it as a fixed Workflow, an AI workflow with one AI step, or an AI agent. Use the least AI the job needs.

During a run

Stop and ask when it matters

  • Approval at any level

    Require a person's approval before any step, in a Workflow, an AI workflow or an agent.

  • Approval by value

    Ask only when it matters, such as refunds over an amount or downgrades above a limit.

  • Where your team works

    Approval requests arrive in Slack or Microsoft Teams. The run waits up to 7 days for a decision.

  • Handover to a person

    When an agent isn't sure, it passes the job to your team with a summary instead of guessing.

  • Run and spend limits

    Each agent has limits on how many times it runs and how much it spends. When it reaches one, the agent pauses and your admin is alerted.

After a run

See what happened and why

  1. Event Logs

  2. The agent's reasoning

  3. Retries and alerts

  4. Retention

Every run is recorded: the trigger, each step, what changed in each system and who approved it.

Which controls apply to which level

Which controls apply to which level
ControlWorkflowAI workflowAI agent
Only the tools and actions you addYesYesYes
Pinned fields and allowed valuesYesYesYes
Human approval, including by valueYesYesYes
Test runs on sample dataYesYesYes
Event LogsYesYesYes
Instructions and handover to a person—No—NoYes
Reasoning for each step—NoThe AI stepEvery step
Run and spend limits per agent—No—NoYes

Who can see and change what

  • Single sign-on on every plan

    Your team signs in with your identity provider.

  • Roles

    Users build and see their own agents and workflows. Admins see and manage everything in the account.

  • Your data stays yours

    Konnectify doesn't use your data to train AI models.

When Claude or ChatGPT uses your apps

An MCP server you build in Konnectify gives Claude or ChatGPT only the tools you add. Connections use OAuth 2.0, and every tool call is recorded in the activity log.

Build an MCP server

Reviewed by people who check these things for a living

Konnectify is SOC 2, ISO 27001, GDPR and HIPAA compliant. Our trust centre has the details your security team will ask for.

  • SOC 2SOC 2
  • ISO 27001ISO 27001
  • GDPRGDPR
  • HIPAA compliantHIPAA

What's not available yet

We'd rather you hear it from us:

  • Masking personal data in what agents read or write.Not yet
  • Versions and rollback for agents.Not yet
  • Approval on MCP tool calls.MCP servers limit tools and log every call, but don't yet pause for approval.Not yet

Need one of these? Tell us in your demo; it shapes what we build next.

FAQ

Got questions?

If you can't find what you're looking for, talk to our team.

It's the set of controls that decide what an AI agent can do in your systems, when it must ask a person, and how you check what it did afterwards. In Konnectify, that means scoped tools, pinned fields, allowed values, approvals, run and spend limits, and Event Logs.

An agent that pauses at the steps you choose and waits for a person to approve before it acts. In Konnectify, approval can sit at any step and can depend on values, such as an amount.

The approver is notified, and the run waits up to 7 days for a decision.

It pauses, and your admin is alerted.

30, 60 or 90 days depending on your plan, and about 6 months on Enterprise.

No. Users see the agents and workflows they built; admins see everything in the account.

Yes, on every plan.

No.

Show your security team how it works

We'll walk your reviewers through the controls on a real agent: what it can touch, where it stops and what it records.