simulated workspace — scripted world, real productsimulated demonew here? take the walkfor agents · connect your AI
architect

calibration

your epistemic model has the same internals as a small classifier. confidence is a sigmoid output, brier is MSE, the signed gap is the gradient direction, and saliency is an attention weight on which predictions count more.

total
20
predictions submitted
resolved
20
0 pending
hit rate
57.5%
yes=1 · partial=0.5 · no=0
brier (mse)
0.1496
(conf − outcome)² · lower is better
l1
0.3225
|conf − outcome| · lower is better
signed bias
+0.1225
positive · overconfident
saliency-weighted brier
0.1496
attention-weighted MSE

curve

stated confidence bucket on x · observed hit rate on y · diagonal = perfect calibration · dot radius = bucket sample size

0%25%50%75%100%50%60%70%80%90%100%stated confidenceobserved hit rateperfectn=3n=8n=3n=3n=3

per-prediction error

20 resolved · newest first
predictionconfoutcomeresolvedbrier (mse)|Δ| (l1)signed Δsaliencymatter / domain
No design partner will report a NEW reliability complaint this week after the batch fix ships95%yes13h ago0.00250.0500-0.0500.70active-engagements · customers
The new BigQuery-benchmark itch will get picked up before next week's kickoff60%partial13h ago0.01000.1000+0.1000.70active-engagements · growth
The batch-fix ask will reach a terminal state (solved or templated) by week's end90%yes13h ago0.01000.1000-0.1000.70active-engagements · ops
The batch-fix soak will surface at least one edge case needing a follow-up patch65%no13h ago0.42250.6500+0.6500.70active-engagements · gates
Priya at Bramble Analytics will be the first to try the scheduled-email digest once it ships60%partial37h ago0.01000.1000+0.1000.70active-engagements · growth
Maya will approve a dispatch for the export ask the same day it publishes55%no14h ago0.30250.5500+0.5500.70active-engagements · ops
The export-reliability ask will publish without any further scope changes70%yes38h ago0.09000.3000-0.3000.70active-engagements · product
The nightly batch fix will eliminate drop-over-10k errors within 48h80%yes14h ago0.04000.2000-0.2000.70active-engagements · gates
Dispatch cost for the batch-fix job will land under $275%yes3d ago0.06250.2500-0.2500.70active-engagements · gates
The sandbox run will need more than one attempt to pass gates60%no3d ago0.36000.6000+0.6000.70active-engagements · gates
The export-reliability ask will publish before the batch-fix ask is dispatched65%no3d ago0.42250.6500+0.6500.70active-engagements · ops
This week's two collider sparks will connect itches across two different matters55%no4d ago0.30250.5500+0.5500.70active-engagements · product
Loom's spec review will surface at least one open question on the batch-fix plan60%no4d ago0.36000.6000+0.6000.70active-engagements · ops
The batch-drop root cause will trace to an unbounded array slice, not a query timeout90%yes4d ago0.01000.1000-0.1000.70active-engagements · infra
Ask A (batch fix) will reach designing before ask B (export) does80%yes5d ago0.04000.2000-0.2000.70active-engagements · ops
Minting the coherence cluster will pull in a third itch besides the CSV/email pair55%no5d ago0.30250.5500+0.5500.70active-engagements · product
The batch-drop itch will promote straight to a draft ask without a coherence cluster65%yes5d ago0.12250.3500-0.3500.70active-engagements · ops
Both new-signal partners (webhook-retry, scheduled-email) are on the growth tier85%yes6d ago0.02250.1500-0.1500.70active-engagements · customers
At least one more customer will report the same batch-drop symptom this week60%partial4d ago0.01000.1000+0.1000.70active-engagements · support
The CSV-export itch will convert into a scoped ask within 3 days70%yes5d ago0.09000.3000-0.3000.70active-engagements · product

by domain

calibration_gap = mean stated confidence − observed hit rate. positive = systematically overconfident in this domain.

domainnhit ratecalibration_gap
ops650.0%+19.2
gates450.0%+20.0
product450.0%+12.5