open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 4 Activity

refactor(examples): replace sector-specific example material with generic, fictitious examples

Browse source 
Reference files, test fixtures, the playground demo project and one design
document now use generic, fictitious examples (buildings, energy, water,
grants, municipal services). The playground demo (17 fixtures plus the
embedded demo state) tells one consistent story: a municipal customer
chatbot that pre-screens housing-benefit applications, classified under
Annex III point 5(a). The embedded demo copies were edited in place rather
than regenerated, because they already carry newer AI Act dates than the
fixture files.

Legal text is unchanged. Test semantics are unchanged. Four dark-theme
onboarding screenshots with outdated placeholder text are removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-23 14:03:53 +02:00
commit 544934dc57
Signed by: ktg
SSH key fingerprint: SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
77 changed files with 363 additions and 368 deletions
Download patch file Download diff file Expand all files Collapse all files

8
playground/test-fixtures/cost.md
View file

@ -18,7 +18,7 @@ Valuta: NOK
|-----------|-------------------|
| Azure AI Services (OCR + classification) | 64 000 |
| Azure OpenAI (forklaringsmodell) | 28 000 |
| Azure AI Search (indeks for objektregister) | 12 000 |
| Azure AI Search (indeks for regelverk og tjenesteinformasjon) | 12 000 |
| Storage (blob + cosmos for audit) | 8 500 |
| Compute (Container Apps for orchestration) | 11 000 |
| Networking (Private Endpoints + egress) | 5 200 |
@ -35,13 +35,13 @@ Valuta: NOK
## Kostnadsdrivere
- Datavolum: ~12 millioner Acme Kunde-chatbot-deteksjoner/mnd
- Forklaring-prompt-tokens: ~250 tokens per flagged hendelse
- Datavolum: ~1,2 millioner chatbot-meldinger og vedlegg/mnd
- Forklaring-prompt-tokens: ~250 tokens per flaggede søknad
- Reservert kapasitet for 99.9% SLA
## Konfidensgradering
P50 er beregnet med 95% konfidens basert på 6 måneder pilot-data. P90 inkluderer 2× volum-skalering ved fullnasjonal utrulling. P10 forutsetter optimaliserte prompt-cache (>40% hit-rate).
P50 er beregnet med 95% konfidens basert på 6 måneder pilot-data. P90 inkluderer 2× volum-skalering ved utvidelse til flere tjenesteområder. P10 forutsetter optimaliserte prompt-cache (>40% hit-rate).
## Anbefaling