docs: publish the runs of 2026-10-21

The evaluation (both cases three times: report, results, spread, each
run's Deliverables and lesson candidates) and the hand-off through the
Orchestration engine (report, the document of links, both agents' kept
files and records). Benchmark cases only, all fictional; no machine paths,
and the links carry no signatures. Other runs stay ignored.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-22 09:25:03 +01:00
parent 1fed1cb538
commit 628b6ee170
159 changed files with 37817 additions and 2 deletions

View File

@@ -0,0 +1,19 @@
# Solution architecture to operating model, through the Orchestration engine
Run `20261021T203623Z`. One pre-approved request for `architecture_and_operating_model` to the Orchestration engine: the solution architecture agent designed from the benchmark scope spec, and its kept files went to the operating model agent as `sources`. The case is fictional; no customer's data is in it.
- **Status:** completed
- **Customer case:** case-08-landing-zone
- **Minutes, end to end:** 74.9
| Agent | Execution | Ended | Files kept |
|---|---|---|---|
| solution_architecture | 6c316f05-9643-492c-bab1-eed56e108754 | completed | 15 |
| operating_model | 1f8f30a1-7b74-4d23-9fb0-aec58089c506 | completed | 11 |
## The operating model
- Operational requirements: 24; verified by a Check: 24
- Capabilities: 21; Roles: 8; Checks: 26
- Scenarios with a path: 44 of 44
- People: 12.2; cost a month: 87,959 GBP