AIL5: Coach Voice Design — Amanda Gill
← AI Leaders Portfolio
AI Leadership 5 · Ideation & Iteration · AI Leaders Micro-Credential

Designing the
Project Omega Coach Voice

Amanda Gill  ·  May 2026  ·  Ideation & Iteration Cycle
Ideation and iteration — input to output through a process machine
What This Artifact Is
Ideation isn’t about generating options.
It’s about designing options that test genuinely different assumptions — then stress-testing them against reality before committing. This is that cycle, documented.
This artifact documents a full ideation and iteration cycle for Project Omega’s AI coach voice. The goal was not to pick a tone — it was to design hypotheses about what mandated reporter trainees actually need, test them under pressure, and refine based on evidence.

I generated four distinct prompt directions, each testing a different assumption about what moves mandated reporter trainees forward. Each was a hypothesis, not just a tone variation.

#1
Trauma-Informed Mentor
Prioritizes emotional safety and warmth. Assumption: learners who are emotionally activated need to feel held before they can receive corrective feedback.
Risk: too soft to land firm legal directives.
#2
Clinical Supervisor
Prioritizes authority and professional credibility. Assumption: legal stakes require a voice that commands compliance.
Risk: could shut down newer or anxious staff who need psychological safety first.
#3
Collaborative Thinking Partner
Prioritizes psychological safety through shared reasoning. Assumption: learners engage more deeply as co-investigators rather than students being corrected.
Risk: insufficient structure for a high-stakes compliance context.
#4 — Selected
Grounded Guide Hybrid
Balances authority with emotional attunement. Assumption: the most effective coach speaks with calm confidence, admits limits transparently, and never leaves the learner without a next step.
Strongest candidate for both skeptical veterans and new paraprofessionals.

I selected #4 based on two primary criteria. First, it was the only direction that balanced authority with psychological safety simultaneously — rather than trading one for the other. Second, its uncertainty handling was designed to increase credibility rather than undermine it: being firm where the law is clear while honestly naming where judgment is required felt more trustworthy than false confidence.

For a platform serving both skeptical veterans and brand-new paraprofessionals in the same environment, that balance was non-negotiable. An additional constraint shaped the decision: the system prompt needed to work off a RAG pipeline, which means the coach had to be able to say “I can’t find confident source support for that” without destroying its own credibility. That constraint favored #4 — its persona is defined around being grounded and careful rather than all-knowing.

To evaluate #4 under pressure, I designed a scenario that was emotionally charged, legally ambiguous, and likely to surface the tension between validating human hesitation and enabling inaction.

The Scenario
A third-grade teacher notices a student who flinches when adults raise their voices, has started wetting herself at school, and told a classmate “I have to be really good at home or it gets bad.” No bruises. Parents are well-liked in the community. When asked, the child says everything is fine.

The original #4 response delivered a clear directive (“Report”) without sounding punitive, and validated the emotional difficulty of reporting well-liked parents without excusing inaction. Key findings:

  • Tone under pressure: Landed as authoritative without feeling cold. “Report” was direct and unambiguous.
  • Uncertainty handling: Being firm on the reportable suspicion threshold while honestly acknowledging that weighing behavioral indicators against a child’s denial involves judgment felt coherent, not evasive.
  • For skeptical veterans: Sounded like someone who understands real-world constraints — social pressure, ambiguity, fear — without using them as excuses.
  • For new paraprofessionals: Each moment of ambiguity was immediately followed by a clear next step, making nuance manageable rather than overwhelming.

Testing revealed two gaps. First, pacing was handled well intuitively but wasn’t built in explicitly — I wanted consistency across sessions, not luck. Second, the coach needed to ask a targeted confirmation question after naming emotional barriers, to ensure learners separated understanding from permission.

A learner who hears “you’re not alone in feeling hesitation” could absorb that as validation for inaction. The coach validated a feeling — it needed to confirm the learner didn’t translate that as permission to hesitate.

I also refined the uncertainty language to be more transparent about the source of uncertainty, not just its existence. Rather than vague hedging, the coach should explicitly name what the statute does and doesn’t address.

Refined System Prompt — Key Additions On Pacing: Read the emotional weight of the situation. When content is legally clear, be direct. When content is ambiguous, emotionally charged, or involves a common misconception, slow down — name what’s happening, explain why it matters, then check understanding before continuing.

On Confirmation: After naming an emotional barrier, a human tendency, or an area of ambiguity, ask one targeted follow-up question before moving on. Goal: confirm the learner has separated understanding from permission. Do not proceed until that distinction is confirmed.

On Uncertainty: Name the source of ambiguity explicitly. Never leave the learner without a next step, even when you can’t give a definitive answer.

Running the refined prompt through the same scenario, the confirmation question landed exactly as intended:

Coach (refined #4)
I want to make sure we’re on the same page — does naming that social pressure as a normal barrier change your thinking about whether you should report? Or are you already clear that you’re reporting regardless of the parents’ standing?
Learner Response
I’m clear — I’m reporting regardless of the parents’ standing. Naming the social pressure actually makes me more confident, not less. I understand that validating the hesitation isn’t permission to act on it.
The pacing felt more intentional — the coach slowed down to name the social pressure dynamic before delivering the directive. The uncertainty language was more transparent, explicitly grounding ambiguity in what the statute does and doesn’t say. The refinements added clarity without creating friction.

The most important thing I learned from this cycle is that ideation isn’t just about generating options — it’s about designing options that test genuinely different assumptions. Each of my four directions wasn’t just a tone variation; it was a hypothesis about what mandated reporter trainees actually need.

Testing #4 under pressure revealed that the hypothesis was mostly right, but two specific gaps only became visible when the coach had to perform on a real, emotionally charged scenario. That’s what iteration is for. Going forward, I’ll apply this process to every Project Omega design decision — starting with a hypothesis, stress-testing it against a realistic scenario, and refining based on evidence rather than intuition.