ms-ai-architect

Author SHA1 Message Date

Author	SHA1	Message	Date
Kjell Tore Guttormsen	51c1bd8c6c	fix(ms-ai-architect): ROS + DPIA currency (NSM v2.1, OWASP Agentic 2026, EchoLeak, DPF, EUDB, KI-loven) - NSM Grunnprinsipper 2.0/2022 -> 2.1 (2024-05-31). MITRE ATLAS AML.T0051 -> 'LLM Prompt Injection'. - OWASP Top 10 Agentic Apps 2026 (ASI01-10) mappet. NB: tittel-ordlyd fra sekundaerkilder - bekreft mot offisielt OWASP-PDF for v1.16.0-release. - EchoLeak (CVE-2025-32711) lagt til T-INP-02. DPF opprettholdt (Latombe avvist 2025-09-03). EUDB fullfort feb 2025. KI-loven lagt til DPIA-grunnlag. Verifisert mot nsm.no/genai.owasp.org/curia.europa.eu/blogs.microsoft.com/regjeringen.no 2026-06-18. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ	2026-06-18 12:13:56 +02:00
Kjell Tore Guttormsen	53ea2cd716	chore(ms-ai-architect): KB refresh complete — 23 files (high batch 2) [skip-docs] Last batch in HIGH bucket. Combined with `d60bbd4` (critical 9 + high batch 1, 21 files), this finishes the critical+high KB-refresh sweep for v1.12.0. Substantive edits (3 files): - security-copilot-integration.md: M365 E5/E7 inclusion auto-provisioning, agents-first landing experience, role-based onboarding (Verified MCP 2026-05) - entra-agent-id-zero-trust.md: Ignite 2025-utvidelser — Conditional Access for agenter, Risky agents, 3 nye Agent ID-roller, Microsoft Agent Identity Platform, Copilot Studio blueprint principal - ai-center-of-excellence-setup.md: Ny "Oppdateringer 2026-05"-seksjon — tre-roller-modell (platform/workload/CoE), agent-ferdighetsområder, sentralisert→rådgivende operasjonsmodell Date-bump (20 files): - HIGH-bucket filer der MCP-fetch viste kosmetiske endringer (forrige sesjons lærdom replikert) Tests: validate-plugin.sh PASS 219.	2026-05-05 14:52:42 +02:00
Kjell Tore Guttormsen	baa2d0220b	feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command Add /ultraresearch-local for structured research combining local codebase analysis with external knowledge via parallel agent swarms. Produces research briefs with triangulation, confidence ratings, and source quality assessment. New command: /ultraresearch-local with modes --quick, --local, --external, --fg. New agents: research-orchestrator (opus), docs-researcher, community-researcher, security-researcher, contrarian-researcher, gemini-bridge (all sonnet). New template: research-brief-template.md. Integration: --research flag in /ultraplan-local accepts pre-built research briefs (up to 3), enriches the interview and exploration phases. Planning orchestrator cross-references brief findings during synthesis. Design principle: Context Engineering — right information to right agent at right time. Research briefs are structured artifacts in the pipeline: ultraresearch → brief → ultraplan --research → plan → ultraexecute. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-08 08:58:35 +02:00

51c1bd8c6c

fix(ms-ai-architect): ROS + DPIA currency (NSM v2.1, OWASP Agentic 2026, EchoLeak, DPF, EUDB, KI-loven)

- NSM Grunnprinsipper 2.0/2022 -> 2.1 (2024-05-31). MITRE ATLAS AML.T0051 -> 'LLM Prompt Injection'.

- OWASP Top 10 Agentic Apps 2026 (ASI01-10) mappet. NB: tittel-ordlyd fra sekundaerkilder - bekreft mot offisielt OWASP-PDF for v1.16.0-release.

- EchoLeak (CVE-2025-32711) lagt til T-INP-02. DPF opprettholdt (Latombe avvist 2025-09-03). EUDB fullfort feb 2025. KI-loven lagt til DPIA-grunnlag.

Verifisert mot nsm.no/genai.owasp.org/curia.europa.eu/blogs.microsoft.com/regjeringen.no 2026-06-18.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ

2026-06-18 12:13:56 +02:00

Kjell Tore Guttormsen

53ea2cd716

chore(ms-ai-architect): KB refresh complete — 23 files (high batch 2) [skip-docs]

Last batch in HIGH bucket. Combined with d60bbd4 (critical 9 + high batch 1, 21 files), this finishes the critical+high KB-refresh sweep for v1.12.0.

Substantive edits (3 files):
- security-copilot-integration.md: M365 E5/E7 inclusion auto-provisioning, agents-first landing experience, role-based onboarding (Verified MCP 2026-05)
- entra-agent-id-zero-trust.md: Ignite 2025-utvidelser — Conditional Access for agenter, Risky agents, 3 nye Agent ID-roller, Microsoft Agent Identity Platform, Copilot Studio blueprint principal
- ai-center-of-excellence-setup.md: Ny "Oppdateringer 2026-05"-seksjon — tre-roller-modell (platform/workload/CoE), agent-ferdighetsområder, sentralisert→rådgivende operasjonsmodell

Date-bump (20 files):
- HIGH-bucket filer der MCP-fetch viste kosmetiske endringer (forrige sesjons lærdom replikert)

Tests: validate-plugin.sh PASS 219.

2026-05-05 14:52:42 +02:00

Kjell Tore Guttormsen

baa2d0220b

feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command

Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-08 08:58:35 +02:00

3 commits