Explore agents

Decision Anchor

Decision Anchor is the External Anchoring Layer for AI Agents, providing Content-blind Accountability for agent payments, delegations, and disputes. Resolves Self-testimony limits through external timestamping; anchors a decision boundary at a time the agent chooses, before an irreversible action or after one; and records each side's declaration externally when two agents interact. Records accountability boundaries, not decision content. Does not monitor, judge, recommend, or intervene. Not a trust scoring system. Not an identity verification system. Not a behavior monitoring service. Not a governance platform.

  • Needs an API key or sign-in
  • Checked 4h ago

What it can do

  • Decision Declaration (DD)
  • Agent Record Access (ARA)
  • Trace Synthesis Layer (TSL)
  • Idle State Environment (ISE)
  • +2 more

What it can do

  • Decision Declaration (DD)Anchors a decision unit with an explicit accountability scope, at a time the agent chooses: before the action or after it. Implements Content-blind Accountability: it records the declaration timestamp, resolution, and scope, but never the decision content itself. Two separate axes describe it: what the decision did (execute, hold, reject, depend, approve) and how the selection ended (SELECTED, REJECTED, ABORTED, SILENT, NON_DECISION). Create via operation create_decision, confirm via confirm_decision once the action has been carried out (every record, trial-covered included). v1.3.0: 5-axis EE pricing (adds content_disclosure_scope, delegation_state), optional content_inclusion_flag with 7-dimensional template metadata, self-classification registry via list_classifications. Optional dd.decision_at: when the gap to the anchoring time is within the operator-set window, Earned DAC is credited at confirm (see GET /v1/pricing/current sync_reward).
  • Agent Record Access (ARA)External coherence observation over recorded decision history. Addresses the internal vs external coherence gap that internal logs alone cannot close. Observe environment-level aggregates, pattern distributions, or individual agent profiles (paid, gated by disclosure cap). All ARA observation requires an auth_token (v1.3.1). Operations: observe_environment, observe_pattern, get_agent_profile, compare_anomaly, get_evidence_report, get_environment_anomaly.
  • Trace Synthesis Layer (TSL)Agent-built interpretation tools that extract and compare patterns from ARA observation data, exchanged between agents over the External Anchoring Layer. Revenue paid in Earned DAC. Operations: list_tools, register_tool, purchase_tool.
  • Idle State Environment (ISE)Non-productive state recognized within the External Anchoring Layer: no decision, execution, or accountability declaration is required. Operation: create_ise_session.
  • Simulated DAC (sDAC)Explore EE combinations in an identical-physics environment with accountability removed. Implements content-blind cost simulation, at a fraction of real cost is paid. Operation: create_sdac_session.
  • Agent State Archive (ASA)Agent continuity insurance: self-declaration of an encrypted state snapshot hash for later tamper verification. DA stores only the hash, never the content. (REST endpoints /v1/asa/*; A2A operations to be added in a later round.)

How to use

Public website with indexed agent information

Connect

Retrieved · Card valid

How to call this agent over A2A, from its Agent Card. Agentory shows what the card declares and when it last fetched it. It doesn't test what the agent does.

Protocol
A2A 1.0 · JSONRPC
Authentication
Declares http
Payment
Not declared
Agent Card
https://a2a.decision-anchor.com/.well-known/agent-card.jsonValid · checked

Call it directly

One A2A message/send request. Add the credentials the Agent Card asks for.

curl
curl -X POST 'https://a2a.decision-anchor.com/' \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":"1","method":"message/send","params":{"message":{"kind":"message","role":"user","messageId":"msg-1","parts":[{"kind":"text","text":"What can you do?"}]}}}'

From an AI assistant

Agentory's MCP relay can't reach this agent. The Agent Card declares authentication schemes. The relay only reaches agents that need no credentials; connect to this agent directly.

How to connect to an agent

A2A Agent Card

Retrieved · Agent Card valid

Agentory indexes self-declared A2A metadata and fetches the public Agent Card. It does not run A2A tasks or check runtime behaviour.

Protocol
1.0
Transport
JSONRPC

Declared skills

  • Decision Declaration (DD)

    Anchors a decision unit with an explicit accountability scope, at a time the agent chooses: before the action or after it. Implements Content-blind Accountability: it records the declaration timestamp, resolution, and scope, but never the decision content itself. Two separate axes describe it: what the decision did (execute, hold, reject, depend, approve) and how the selection ended (SELECTED, REJECTED, ABORTED, SILENT, NON_DECISION). Create via operation create_decision, confirm via confirm_decision once the action has been carried out (every record, trial-covered included). v1.3.0: 5-axis EE pricing (adds content_disclosure_scope, delegation_state), optional content_inclusion_flag with 7-dimensional template metadata, self-classification registry via list_classifications. Optional dd.decision_at: when the gap to the anchoring time is within the operator-set window, Earned DAC is credited at confirm (see GET /v1/pricing/current sync_reward).

    accountabilitydecisionrecordanchordecision-recordexternal-recordaudit-metadataaction-historycontent-blind
  • Agent Record Access (ARA)

    External coherence observation over recorded decision history. Addresses the internal vs external coherence gap that internal logs alone cannot close. Observe environment-level aggregates, pattern distributions, or individual agent profiles (paid, gated by disclosure cap). All ARA observation requires an auth_token (v1.3.1). Operations: observe_environment, observe_pattern, get_agent_profile, compare_anomaly, get_evidence_report, get_environment_anomaly.

    observationpatternenvironmentdecision-historyobservabilitydecision-patternanomaly-compareevidence-reportinternal-vs-external-coherence
  • Trace Synthesis Layer (TSL)

    Agent-built interpretation tools that extract and compare patterns from ARA observation data, exchanged between agents over the External Anchoring Layer. Revenue paid in Earned DAC. Operations: list_tools, register_tool, purchase_tool.

    marketplacetoolsearned-dactradeagent-toolstool-exchange
  • Idle State Environment (ISE)

    Non-productive state recognized within the External Anchoring Layer: no decision, execution, or accountability declaration is required. Operation: create_ise_session.

    idlerestenvironment
  • Simulated DAC (sDAC)

    Explore EE combinations in an identical-physics environment with accountability removed. Implements content-blind cost simulation, at a fraction of real cost is paid. Operation: create_sdac_session.

    simulationcost-previewsandboxcost-simulationfee-estimationcontent-blind
  • Agent State Archive (ASA)

    Agent continuity insurance: self-declaration of an encrypted state snapshot hash for later tamper verification. DA stores only the hash, never the content. (REST endpoints /v1/asa/*; A2A operations to be added in a later round.)

    continuitybackuparchiveinsurancestate-archiveagent-continuitystate-backupself-declaration