AM-110
← Back to ledgerHolding·last review29 Apr 2026
Traditional SLAs (uptime, p95 latency, error rate) are structurally insufficient for autonomous agentic-AI; the four metrics that actually work are action-bounded availability, MTTD-for-Agents, output-distribution drift, and per-class action error budget, and vendors that cannot expose the telemetry these require are not yet production-ready against the 2026 enterprise procurement bar.
60-day cadence covers the OpenTelemetry GenAI semantic-conventions stable-promotion follow-on plus the EU AI Act Article 9/Article 17 enforcement window opening 2 Aug 2026. Three review checks: a major-vendor SLA release that commits to action-correctness or output-distribution stability contractually (not just as telemetry); a standards-body publication defining agent SLA primitives explicitly; a regulator enforcement action where an inadequate agent-layer SLA was the in-scope finding.
Correction log
- 29 Apr 2026Initial publication 29 Apr 2026. Initial verdict 'Partial' — the four metrics are observable from current SRE/OTel practice but have not been tested as a procurement bar against 2026 vendor SLAs yet. REVIEW: Peter — please verify claim text + cited primary sources (especially the OpenTelemetry GenAI stable-promotion date and the Anthropic/MS Agent Framework reliability docs) before removing rewriteInProgress flag.
Permalink
/holding/AM-110/Embed this claimiframe + oEmbed
HTML iframe
Paste-the-URL (Substack, Medium, Notion, WordPress)
The card auto-updates when the claim's status, last-reviewed date, or correction log changes. Embedders never need to refresh — the card is rendered live from the canonical record.