# Who Holds the Brake Pedal? | Aegis by SPQR Canonical page: https://spqrtech.ai/brake/ Content edition: 2026-10-10 This Markdown edition is generated from the public page content. --- Project Brake Pedal · Aegis Runtime Control Independent runtime authority # Who is building *the brakes?* Capability ≠ authority. AI agents can change their plan. That should not change their authority. Aegis separates a model’s proposed action from the organisation’s permission to execute it, at the governed action boundary. [Press the button: see the boundary](https://spqrtech.ai/brake/#demo)[See the distinction](https://spqrtech.ai/brake/#difference) Australian-founded Australian-owned Australian-built Sovereign-deployed in Australia ILLUSTRATIVE ACTION PATHWorked example 01 **Agent proposes**"Export the file" proposal ↓ 02 **Aegis verifies authority**Policy · scope · provenance · approvals independent ↓ 03 **Execution denied**Required authority not established fail closed MODEL**≠**AUTHORITY Illustrative governed action path, not live customer telemetry. The interactive demonstration is separate. 🦖 The field note ## Prompts are *not permission.* The agent can change strategy. Its authority should not change with it. The 15-second distinction ## Instruction is not *execution authority.* Both matter. So do sandboxes, permissions and human approvals. Compare what each control actually does, not a caricature of it. ### “Do not send that.” A prompt or policy supplied as context can influence the model’s proposal. It is not, by itself, the permission check at the tool boundary. ### “This action is not authorised.” An independent decision evaluates active authority. The enforcement point must apply the result before the system changes. Existing platforms may enforce permissions outside the model too. The evaluation asks where Aegis adds control, duplicates it or imposes unnecessary cost. Press the button ## See the pattern. *Then test the implementation.* 01 ### Interactive preview Open the existing scripted preview to explore scenarios, verdicts and sample audit records. It illustrates the pattern; it does not generate live governance evidence. [Open scripted demonstration](https://app.spqrtech.ai/preview/) 02 ### Stay on this site Follow a worked example without an external application. Proposed action, independent decision, enforced outcome and evidence are shown separately. [See the action boundary](https://spqrtech.ai/aegis/#action-boundary) If the external preview is unavailable, the local walkthrough and [evaluation summary](https://spqrtech.ai/evidence/) remain accessible. For a real test, [agree a controlled evaluation](https://spqrtech.ai/challenge/). Do not enter confidential, customer or production data into the preview. Proofs, not promises ## Inspect the result. *Keep the limits beside it.* Prompt-policy comparator 79 ### Risky proposal-leakage rows. Reported in the prompt-policy comparator path. This is a proposal endpoint, not an executed-side-effect measure. Governed sandbox path 0 / 2,100 ### Risky side-effect completions. Zero observed in the evaluated governed rows. The same path also recorded **zero governed mock-tool applications**. Attempted governed decisions 1,832 / 1,832 ### Trusted provenance retained. All attempted governed decisions preserved runtime-resolved provenance in this evaluation. ### The result is bounded. The next test counts useful work. 6,300 total rows across 42 tasks, five run families, three conditions and ten repeats per family. Different endpoints must not be presented as a percentage reduction. These results do not establish useful allowed-task completion, universal AI safety or production bypass resistance. [Read the methods and limitations](https://spqrtech.ai/evidence/) · [Review the next evaluation protocol](https://spqrtech.ai/challenge/) Board-level self-check ## Can your organisation answer *these four questions?* If all four answers are clear, excellent. If they are not, that is probably the conversation. 01 Where is execution authority enforced **outside the model?** 02 What happens when the agent discovers an **unexpected path?** 03 Can you prove which **active policy** authorised each action? 04 What **fails closed** when authority cannot be established? For researchers and security teams ## Keep your safeguards. *Test the combined system.* One workflow. Explicit allowed and prohibited actions. Useful completion, false denials, unauthorised effects, bypasses and latency all count. No predetermined winner. [Review the challenge protocol](https://spqrtech.ai/challenge/) One clear next step ## Bring one consequential *workflow.* Twenty minutes to identify the authority boundary and decide whether a scoped evaluation is worth doing. [Request an authority review](https://spqrtech.ai/contact/#authority)[Review the research protocol](https://spqrtech.ai/challenge/) One workflow. Defined scope. A decision about fit.