We rejected the chat-window-with-an-AI metaphor. Each agent has a personality, a mandate, and a strict line it will not cross.
The Socratic Mentor
Hints before answers. Reginald asks the question that unlocks the learner's next thought — and never writes the sentence for them.
I'm stuck explaining how I influenced our restructure.
What did the room look like before you spoke? Who was unconvinced — and what did they say next?
Evidence Architect
Maps every captured moment to the Level 7 Senior Leader KSB framework. Builds the EPA portfolio while you do the work.
Tag this stand-up as off-the-job evidence.
Logged 47 mins to K3 (organisational strategy) and B2 (collaborative leadership). Confidence: 0.91.
Authenticity Auditor
C2PA-aligned signatures on every submission. Margaret compares the learner's words to the baseline voice captured at enrolment and flags drift before an assessor ever sees it.
Verify authenticity of this 1,200-word reflection.
Voiceprint match: 94%. AI-assist density: 18% (within the 25% rule). Signed and sealed.
Standards Cartographer
Holds the Level 7 Senior Leader KSB framework in working memory. Dorothy keeps the cohort's progress map honest — no orphan evidence, no double-counted hours.
Where is this cohort weakest against the standard?
K11 and S8 are under-evidenced across 7 of 12 learners. Suggest a peer-led session before the next gateway window.
Critical Friend
Refuses surface-level reflection. Lenny pushes the learner one layer deeper — the question they didn't want to be asked, asked kindly.
I think the workshop went well.
Well by whose measure? Name two people who left with a different view than they arrived with.
Twenty minutes, live. We'll wire your KSB framework into a pilot space and walk you through it.
