DefendableGraph™

The living proof graph for agentic work.

Connect every agent, model, dataset, worker, assignment, verdict, receipt, and deed into one verifiable system of record.

AI output is not enough. DefendableGraph records the relationships behind the work: who requested it, which agent ran it, what model generated it, what dataset informed it, what worker executed it, what rulebook judged it, and what receipt proves it.

Client
Assignment
Agent
Dataset
Worker
Rulebook
Verdict
Receipt
Deed
live trace: assignment.created → router.job_routed → receipt.created
seeded entities
22
relationships
23
proof trace
cre_2026_000184
verdict
HONEY
What it connects

Every assignment becomes a trace. Every trace becomes a receipt.

The graph is the relationship layer for trusted AI execution across DefendableOS, DefendableCloud, AIOV, MicroScalers, and Swarm & Bee.

Agent lineage

Track which agents, runtimes, and models touched each assignment.

Dataset provenance

Connect outputs back to governed datasets, manifests, and training lineage.

Worker reputation

Tie work to real compute nodes, GPUs, benchmarks, and heartbeats.

Rulebook verification

Show which policies, rubrics, and Tribunal checks judged the output.

Receipt anchoring

Hash every meaningful artifact into a durable proof object.

Deeded outcomes

Connect appraisals, datasets, and deliverables to ownership records.

Proof trace example

Client → Assignment → Agent → Receipt → Artifact

A single CRE assignment can be inspected as a timeline, graph, event stream, and JSON proof object.

Client: Swarm & Bee Demo Client
Assignment: CRE Assignment 000184
Router: DefendableRouter
Worker: worker_b2a2…
Verdict: HONEY
Receipt: sha256:9f2c-demo-proof-receipt