Pressure-test the function
Pressure-test the function.
Pick the function. Hermes Agent runs the maturity read: posture for the unit, not a skills quiz for one person.
Pick a function and its maturity check loads below: two ladders, joined by the gate. Open to run, and nothing is stored.
Aligned with the Cloud Security Alliance maturity model and controls matrix; not a certification or STAR listing.
First look instead? The ten-minute Quick Mythos Vulnerability Assessment→
Personal read instead? Build the defender’s skills →
Manual: The human is the safety net. Low autonomy asks little of your controls.
Live assess
Run it, don’t just read it.
The unit’s armour: function posture on two ladders, joined by the gate. Pick a function above, then start on screen. Open to run, and nothing is stored.
Selected function
Identity Security
8 questions · 2 categories
Standards lenses · one spine
Assess once on the AI Controls Matrix. ISO, NIST, and AI-CAIQ are lenses on those answers — not a second questionnaire.
Compatible-standard reports are lenses on AI Controls Matrix (AICM) answers from the function diagnostic — the AI Consensus Assessments Initiative Questionnaire (AI-CAIQ) is the attestation view of that spine, shown as a sample. Not certification.
Sample reports
See a finished report before you start.
One finished function read per fictional organisation. Full board, mastery, and standards lenses live in Reports.
Self-assessed sample data, never client results. All reports →
Exhibits · the living standards map
Assess once. Read against every standard.
Open the living standards map
A navigation map, not a conformance attestation: assess once on the AI Controls Matrix and read every standard as a lens on that one run. Privacy regimes arrive from skill tags in the panel below.
AI Security Maturity Model: The maturity read. The lit standards cover the same governance ground.
The depth behind this map lives one level down: every standards lens as a finished sample → and, for members, the full control spine and crosswalk →
The method
How a function climbs, and where SkillGuard fits.
You raise a function by applying ready-made skills. Adopting a skill is itself a supply-chain risk, so SkillGuard admits every skill before it is applied. It is the gate on this one step, not a tool off to the side.
Read the function
The maturity check finds the gate-blocking gaps: the controls sitting below target.
Fit the skills
The reading names the ready-made skills that close each gap, the capability to add.
SkillGuard admits
Every prescribed skill passes the scan before it can be applied.
See the pre-check →Move the lever
Only admitted skills are applied: the People, Process, or Technology change that raises the control.
Watch it move
Re-run the check: governance rises, the gate opens, autonomy may climb, safely.
↻ Re-assess feeds the next diagnose, each turn earning the next rung.
Upstream · what stocks 02 Prescribe
02 Prescribe draws from a living library, and a governed autonomous agent (Hermes) keeps it current: it watches the field and proposes new skills from a chat window, inside a gate of three tools it cannot cross. SkillGuard admits what it proposes, so the loop never runs on unvetted capability. How we govern our own agent →