OpenChainGraph Suite · §22.8 Escalation · OCG v0.8.2

DORA Escalation Demo Chain

Note (dated 2026-08-04): a chain composes independent computations performed in an analytical order. No step's output is carried into the next step by the execution model; each step computes from its own declared inputs. This is true of every chain on this site, including chains whose per-step copy below reads as a data handoff.

Demonstrates OCG §22.8.2 escalation EMIT/HALT semantics. DORA Readiness Diagnostic runs first: a grade F triggers the escalate gate, halts the chain, and opens an escalation record. A passing grade routes forward to DORA Incident Classifier.

OpenChainGraph · 2 Steps compliance mandate §22.8 Escalation Gate Hash-Anchored §4 Client-Side · Zero PII
§22.8 Escalation EMIT/HALT

When the gate fires escalate, the run halts immediately. Remaining steps are marked skipped_by_escalation (distinct from skipped_by_gate). An open escalation record is emitted with a deterministic record_hash over { decision, halted_steps }; opened_at is excluded from the preimage so the hash is stable across runs. The composite execution hash is computed over ran steps only, before the escalation record is attached.

Chain Topology: DORA Readiness Diagnostic (escalation gate: grade=F → HALT / default → DORA Incident Classifier)
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 2 Steps (1 escalation gate)
1 ROOT · ESCALATION GATE node
DORA Readiness Diagnostic art-29-dora-readiness-diagnostic
grade (A–F) → gate: grade=F escalates (HALT, open record); otherwise routes to DORA Incident Classifier
§22.8.1 Decision Gate
rule[0]: if output.grade == "F"  →  next: escalate   (§22.8.2 HALT + open record)
default:                         →  next: art-09-dora-incident-classifier
Default continues to: art-09-dora-incident-classifier
MCP Call · run_dora_readiness_diagnostic
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "run_dora_readiness_diagnostic",
    "arguments": {}
  },
  "id": 1
}
↓
2 TERMINAL node
DORA Incident Classifier art-09-dora-incident-classifier
incident_severity, rts_criteria_flags — continuation when readiness passes the gate. Skipped if step 1 escalated.
MCP Call · classify_dora_incident
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "classify_dora_incident",
    "arguments": {}
  },
  "id": 1
}
Export Artifacts
Download the §4 chain definition artifact (hash-anchored composite JSON) or the §13.11 W3C Verifiable Credentials view. Both derive from the chain definition. Available after hash computation.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.

Question: Our compliance answers just went through review. What DORA readiness grade do the twelve controls earn, and which ones stay open?
Run the AINumbers MCP tool `run_chain` with {"chain":"dora-escalation-demo"} and read `art-29-dora-readiness-diagnostic.grade`.
Re-run with `inputs` for `art-29-dora-readiness-diagnostic`, reusing the values that result echoed, with `answers` changed so every q1 to q12 answer is yes. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/dora-escalation-demo.html