top of page
Search

When AI Knows the Difference: How Starlight Unlocks Feedback on Staff Training

  • Adam Sturdee
  • Sep 8
  • 3 min read
ree

One of the most striking features of Starlight is its intelligence. Recently, I uploaded audio from a whole-staff training session. This wasn’t a classroom lesson — it was professional development time. Yet Starlight immediately understood the difference.


Instead of defaulting to classroom-based feedback, it generated a report tailored to the leadership and coaching context. It identified how the session built trust, set norms, and addressed boundaries between coaching and QA — issues unique to professional development. In short, Starlight knew this was not about students in desks, but teachers in dialogue.


This matters. Schools invest heavily in professional development. CPD budgets in the UK run to hundreds of millions each year, with secondary schools often allocating £20–30k annually. Yet the feedback loop on CPD is notoriously thin — most training goes unevaluated beyond a quick survey. Starlight changes that.


By analysing transcripts of staff training sessions, Starlight:


  • Provides evidence-based insight into what resonated, what created clarity, and where anxieties remain.

  • Surfaces themes across departments, helping leaders see if messages are landing consistently.

  • Highlights the tone and climate of the session — trust, safety, openness — which are essential for adult learning.

  • Suggests actionable next steps, ensuring training translates into real cultural and pedagogical change.


In effect, Starlight transforms CPD from a one-off event into an ongoing, evidence-driven coaching cycle. Research into Transcript-Based Lesson Analysis (TBLA) shows that transcripts reveal hidden factors and cultural scripts of teaching. By extending this approach to professional development, Starlight allows leaders to reflect on the micro-moments of their facilitation with the same rigour teachers now apply to classroom practice.


Here’s an example from the report generated on that staff training session (shared in full below). Notice how it captures leadership moves, the quality of questioning, and even the clarity of vocabulary used to distinguish coaching from QA:

“Your facilitation of this SLT/department coaching session continues to showcase the consultative, inclusive leadership you’ve developed over recent months. You built on established strengths from previous sessions—particularly around creating safe spaces for reflection, fostering transparency, and integrating staff feedback into new initiatives. Notably, you were attentive to both the opportunities and risks of departmentalisation and cross-pollination… An area for further development is ensuring absolute clarity at all stages around boundaries between coaching, QA, and capability.”

That is not generic feedback. It’s targeted, sophisticated, and immediately useful.

For schools, the implications are profound. Every training session can now produce a coaching-quality feedback report — unlocking insight not only into teaching but into how we lead, support, and grow as professionals. This is feedback not just for lessons, but for the lessons we run for each other.


You can read the full coaching report here:



🎥 Subscribe to our channel here: https://www.youtube.com/@Star21-ai

🌐 Read more on our blog: www.coaching.software

💡 Explore the platform: www.starlightmentor.com

🐦 Follow us on X: @star21starlight


The Insight Engine is written by Adam Sturdee, co-founder of Starlight—the UK’s first AI-powered coaching platform—and Assistant Headteacher at St Augustine’s Catholic College. This blog is part of a wider mission to support educators through meaningful reflection, not performance metrics. It documents the journey of building Starlight from the ground up, and explores how AI, when shaped with care, can reduce workload, surface insight, and help teachers think more deeply about their practice. Rooted in the belief that growth should be private, professional, and purposeful, The Insight Engine offers ideas and stories that put insight—not judgment—at the centre of development.

 
 
 

Comments


bottom of page