MRC · In development

Microsoft Copilot Studio: Enabling makers to require human approval for tool calls

Copilot Studio now let’s makers require human approval before an agent runs specific tools. With a per-tool, per-agent toggle, any gated tool call pauses and shows an approval request describing what the agent intends to do, so a person can approve, approve for the session, or de

Microsoft Copilot Studio 03 Horizon04 Security05 GRC09 Work & Skills

DIGITAL SKILL WORKS LTD / 12 PANES

What it is

Microsoft Copilot Studio: Enabling makers to require human approval for tool calls is a Microsoft 365 roadmap item published via Microsoft Release Communications. Current status: In development.

What it does

Copilot Studio now let’s makers require human approval before an agent runs specific tools. With a per-tool, per-agent toggle, any gated tool call pauses and shows an approval request describing what the agent intends to do, so a person can approve, approve for the session, or deny before the action runs. This gives organizations a deterministic guardrail for high-stakes or sensitive operations like sending emails, closing tickets, or processing payments, independent of the agent's instructions. Approval requests appear inline in the channel where the agent is deployed, including Microsoft Teams and Microsoft 365 Copilot.

Why you should care

  • Board: Agents change operating risk. Ask for registry coverage and owner accountability first.
  • CISO: Treat agents as privileged actors: least privilege, owner, lifecycle, and audit before scale.
  • CFO: Map licence or consumption impact to the frozen value case; avoid seat spray.
  • Adoption: Pilot with a named cohort and measure changed work, not vanity clicks.

Suggested action

Wave 0 first: Security → GRC → Cost & Value → Licence → Adoption. Put this on the agent register with a named owner. Do not enable broadly until permissions, DLP, and reclaim rules exist.

12 Panes: 03 Horizon · 04 Security · 05 GRC · 09 Work & Skills

Communication needed

  • Security: Assess exposure, Conditional Access, and agent/tool permissions.
  • GRC: Update AI/agent register and evidence path; confirm DPIA triggers if personal data is in scope.
  • FinOps: Forecast seat or credit impact; align to frozen value case.
  • Adoption: Plan cohort messaging, clinics, and success measures.
  • Comms: One story for board and staff — what changes, what does not, who owns risk.

Benefits

  • May improve productivity on a specific Microsoft 365 surface when permissions and data quality allow.
  • Roadmap visibility helps Horizon planning without guessing dates.
  • Agents can automate multi-step work inside existing Microsoft 365 permissions.

Risks

  • Status and dates change; treat MRC as directional, not a contract.
  • Enabling without Steady controls can amplify overshare or cost leakage.
  • Agents act; over-privilege and ownerless agents create lasting exposure.
  • Preview or rolling features can change behaviour; fence exploration on Pane 12 Frontier.

Source

  • MRC id: 570434
  • Status: In development
  • Products: Microsoft Copilot Studio
  • GA / disclosure: September CY2026
  • Preview: —
  • Platforms: Web
  • Cloud instances: Worldwide (Standard Multi-Tenant)
  • moreInfoUrls: —
  • Open on Microsoft 365 Roadmap

Microsoft Release Communications / Microsoft 365 Roadmap (AI at Work). Content is subject to Microsoft API Terms of Use. Dates and status change; verify in the official roadmap before acting.

Back to roadmap intel