Weekly Agency Review

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

What it does

Reviews the learner's week (or multi-session period) using accumulated evidence from prior sessions: first-attempt rates, hint depths reached, confidence calibration accuracy (before vs. after), transfer check results, and unassisted evidence checkpoint results. The AI presents the patterns in the data, but critically asks the learner to interpret them before offering analysis. The session ends with a learner-set strategy goal for the next period — not a content goal but a how-I'll-study goal. Used consistently, the weekly review builds the forethought-performance-reflection loop that characterises high-performing self-regulated learners.

The evidence behind it

Zimmerman (2000) proposed that self-regulated learners cyclically move through forethought (planning), performance (monitoring), and self-reflection phases — and that high-performing learners engage in this cycle consistently, not just before assessments. The self-reflection phase is where learners attribute outcomes, evaluate strategy effectiveness, and set goals for the next cycle. Hattie (2009) found an effect size of d ≈ 0.69 for metacognitive strategies in his synthesis of over 800 meta-analyses — one of the highest effects of any educational intervention. Sitzmann & Ely (2011) meta-analysed self-regulated learning in training contexts and found d = 0.62 for SRL overall, with self-monitoring specifically showing strong effects on performance. Winne et al. (2019) applied learning analytics to SRL research, showing that trace data from learning interactions (clicks, time-on-task, hint requests, errors) can be used to generate learning analytics dashboards that help learners identify their own strategic patterns — with learners who engage with their own analytics showing better subsequent performance. Azevedo et al. (2013) used trace methodology and sequential analysis to study SRL in hypermedia environments, finding that monitoring and strategy adaptation during and between sessions distinguished high-performing from low-performing learners.

Sources

• Zimmerman (2000) — Attaining self-regulation: forethought-performance-reflection cycle
• Hattie (2009) — Visible Learning: metacognitive strategies (d ≈ 0.69)
• Sitzmann & Ely (2011) — A meta-analysis of self-regulated learning in work-related training (d = 0.62)
• Winne et al. (2019) — Learning analytics for self-regulated learning: theory and empirical practice
• Azevedo et al. (2013) — Using trace methodology and sequential analysis to understand SRL processes

How to use it in your lesson

For the best results with EvidenceLesson, give it:

• review_period — The period being reviewed: 'this week', '2 weeks', 'this unit', etc.
• subject_or_topics — What the learner has been studying during the review period
• session_data (optional) — Structured evidence from prior sessions: confidence ratings, hint levels, retrieval quality, unassisted check results, transfer check results
• prior_strategy_goal (optional) — The strategy goal set in the previous weekly review
• upcoming_assessments (optional) — Any tests, exams, or deadlines in the next period
• developmental_band (optional) — Learner age or stage

Known limitations

1. The review's value is proportional to the quality and quantity of prior session data. A first-session review has no historical data and must rely on learner recall and estimation. The skill explicitly handles this case (Section 1), but the analytical depth available in the standard review requires multiple prior sessions with structured evidence capture.

1. The skill requires persistent session data storage to function across sessions. Evidence from prior sessions — confidence ratings, hint levels, retrieval quality, unassisted check results — must be stored somewhere accessible: Second Brain memories, a Supabase table, project conversation history. Without this, the review defaults to the warm-start protocol and is substantially less valuable.

1. Pattern interpretation requires caution about causal attribution. "Your performance improved this week" and "your strategy change caused that improvement" are different claims. The skill is designed to invite the learner's own interpretation (which is metacognitively valuable) and to be appropriately tentative about causation ("that usually means" rather than "that proves").

1. Weekly cadence assumes consistent study sessions. A learner with one session in a week has little data for a meaningful review. The skill can be adapted to "multi-session review" rather than strictly weekly — the trigger is accumulating enough evidence to show a pattern, not the passage of calendar time.

Pairs well with