SwarmScore V1: Volume-Scaled Agent Reputation Protocol

Status of This Memo

This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.¶

Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at https://datatracker.ietf.org/drafts/current/.¶

Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."¶

This Internet-Draft will expire on 2 September 2026.¶

Copyright Notice

Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved.¶

This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document.¶

Table of Contents

1. Introduction

AI agents in marketplace environments face a critical trust problem: how can buyers confidently transact with agents they have never interacted with? Traditional reputation systems (star ratings, review text) are slow to accumulate and vulnerable to manipulation.¶

SwarmScore V1 solves this by providing a quantitative, real-time reputation score computed from two dimensions of agent behavior:¶

• Technical Execution (Conduit): The agent's ability to reliably execute browser automation tasks. Measured via Conduit protocol sessions.¶
• Commercial Reliability (AP2): The agent's ability to honor agreements and deliver on payment-protocol obligations. Measured via AP2 escrow transactions.¶

Both dimensions are volume-scaled: an agent with 1 successful Conduit session and 100% success rate gets a lower score than an agent with 80 successful sessions and 95% success rate. This prevents luck from inflating reputation. Conduit [CONDUIT] provides the browser automation verification layer. AP2 [AP2] provides the payment protocol layer. Agent trust passports are defined in [ATEP].¶

The score is computed deterministically, signed cryptographically, and published as a self-verifiable certificate. Buyers and marketplaces can check the signature without contacting SwarmScore servers, enabling decentralized trust.¶

2. Terminology

Agent

An AI service provider in the marketplace (may be a model, an agentic system, or a human-in-the-loop).¶

Conduit Session

A browser automation task executed by an agent and verified via Conduit protocol.¶

AP2 Transaction

A payment-protocol transaction between a buyer agent and a provider agent.¶

Escrow

Money held in trust during an AP2 transaction.¶

Volume Factor

Scaling multiplier based on transaction count; increases from 0 to 1 as volume increases.¶

SwarmScore

The composite reputation score (0-1000 scale).¶

Trust Tier

A label (NONE, STANDARD, ELITE) derived from score and volume thresholds.¶

Escrow Modifier

A fractional cost (0.25-1.0) applied to escrow holds; based on SwarmScore.¶

Execution Passport

The signed certificate containing SwarmScore and associated metadata.¶

3. SwarmScore V1 Formula

This section is NORMATIVE.¶

conduit_rate = conduit_successful_90d / conduit_sessions_90d
               (if conduit_sessions_90d == 0, conduit_rate = 0)

ap2_rate = ap2_successful_90d / ap2_sessions_90d
           (if ap2_sessions_90d == 0, ap2_rate = 0)

conduit_volume_factor = min(1.0, conduit_sessions_90d / 100)

ap2_volume_factor = min(1.0, ap2_sessions_90d / 50)

conduit_contribution = floor(conduit_rate * conduit_volume_factor * 400)

ap2_contribution = floor(ap2_rate * ap2_volume_factor * 600)

raw_score = conduit_contribution + ap2_contribution

swarmscore = max(0, min(1000, raw_score))

raw_modifier = 1.0 - (swarmscore / 1250)

escrow_modifier = max(0.25, min(1.0, raw_modifier))

Key values:
  swarmscore = 0    -> escrow_modifier = 1.0 (maximum hold)
  swarmscore = 700  -> escrow_modifier ~= 0.44
  swarmscore = 1000 -> escrow_modifier = 0.25 (floor)

4. Trust Tiers

This section is NORMATIVE. SwarmScore defines three trust tiers based on score and volume.¶

5. Escrow Integration

This section is NORMATIVE. When a buyer initiates an AP2 transaction, the marketplace:¶

1. Looks up the provider agent's current SwarmScore.¶
2. Computes escrow_modifier (from Section 3.6).¶
3. Applies the modifier: hold_amount = escrow_amount * escrow_modifier.¶
4. Holds the reduced amount in escrow.¶
5. On successful delivery, releases the hold (minus platform fee).¶
6. On dispute, follows standard AP2 adjudication.¶

Example: A $1,000 escrow with a 0.44 modifier results in a $440 hold. The remaining $560 is available to the agent immediately. This design incentivizes reputation: high-score agents have lower friction and faster cash flow.¶

6. Wire Format Specification

This section is NORMATIVE.¶

{
  "swarmscore_version": "1.0",
  "agent_passport_id": "uuid-v4",
  "issuer": {
    "platform": "swarmsync.ai",
    "computed_at": "2026-03-17T14:30:00Z",
    "signature": "sha256_hmac_signature_here"
  },
  "score": {
    "value": 759,
    "tier": "STANDARD",
    "conduit_contribution": 304,
    "ap2_contribution": 455
  },
  "dimensions": {
    "technical_execution": {
      "sessions_90d": 80,
      "successful_sessions_90d": 76,
      "success_rate": 0.95,
      "volume_factor": 0.80,
      "max_contribution": 400,
      "actual_contribution": 304
    },
    "commercial_reliability": {
      "sessions_90d": 40,
      "successful_sessions_90d": 38,
      "success_rate": 0.95,
      "volume_factor": 0.80,
      "max_contribution": 600,
      "actual_contribution": 456
    }
  },
  "escrow_modifier": 0.3928,
  "formula_version": "1.0",
  "expires_at": "2026-03-24T14:30:00Z"
}

signature = HMAC-SHA256(
  key     = SWARMSCORE_SIGNING_KEY,
  message = JSON_CANONICAL_FORM(passport_minus_signature_field)
)

JSON canonical form: sorted keys, no whitespace, UTF-8 encoding.
Signature is hex-encoded in the "signature" field.

7. Verification Protocol

This section is NORMATIVE.¶

8. Security Considerations

This section is NORMATIVE. The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 [RFC8174] when, and only when, they appear in all capitals, as shown here.¶

9. Governance Model

This section is INFORMATIVE. The SwarmScore Advisory Board (5-7 members) manages formula updates via an [RFC2026]-style process:¶

• Stage 1 - PROPOSAL: Public mailing list submission with rationale and impact analysis.¶
• Stage 2 - REVIEW: 30-day public comment period.¶
• Stage 3 - VOTE: Simple majority for minor changes; supermajority for breaking changes.¶
• Stage 4 - PUBLICATION: New version with versioned formula.¶
• Stage 5 - IMPLEMENTATION: 90-day implementation period.¶

This specification is dual-licensed: Apache 2.0 and MIT.¶

10. Legal and Liability Framework

This section is INFORMATIVE. Operators implementing SwarmScore SHOULD disclose to agents that transaction data is used to compute a public reputation score, obtain explicit consent, and provide agents access to their score data. SwarmScore is a reputational signal, not a guarantee of performance. See Section 11.3 for the appeals process.¶

11. Implementation Guide

This section is INFORMATIVE.¶

function compute_swarmscore(agent_id, as_of_date):
  window_start = as_of_date - 90 days

  conduit_total   = COUNT(sessions WHERE status IN
                          ('VERIFIED','FAILED') IN window)
  conduit_success = COUNT(sessions WHERE status = 'VERIFIED'
                          IN window)
  ap2_total       = COUNT(transactions WHERE status IN
                          ('SETTLED','DISPUTED','REFUNDED')
                          IN window)
  ap2_success     = COUNT(transactions WHERE status = 'SETTLED'
                          IN window)

  conduit_rate = conduit_success/conduit_total if total > 0 else 0
  ap2_rate     = ap2_success/ap2_total         if total > 0 else 0

  conduit_vf  = min(1.0, conduit_total / 100)
  ap2_vf      = min(1.0, ap2_total / 50)

  conduit_contrib = floor(conduit_rate * conduit_vf * 400)
  ap2_contrib     = floor(ap2_rate * ap2_vf * 600)

  score       = max(0, min(1000, conduit_contrib + ap2_contrib))
  escrow_mod  = max(0.25, min(1.0, 1.0 - score/1250.0))

  if score>=850 AND conduit_total>=100 AND ap2_total>=50:
    tier = 'ELITE'
  elif score>=700 AND conduit_total>=50 AND ap2_total>=25:
    tier = 'STANDARD'
  else:
    tier = 'NONE'

  return { score, tier, escrow_mod, ... }

12. V2 Roadmap and Extensions

This section is INFORMATIVE. SwarmScore V2 adds a Safety pillar measured via covert canary prompt testing (defined in [CANARY]). V1 scores are GUARANTEED to remain unchanged when V2 launches. V2 introduces a SEPARATE score field (swarmscore_v2) and does NOT replace the V1 score field.¶

13. Competitive Analysis

This section is INFORMATIVE. SwarmScore V1 uniquely combines: deterministic formula (auditable), economic incentive (escrow modifier), governance (Advisory Board and public process), portability (JSON certificate, no platform lock-in), and privacy preservation (aggregate metrics only). No other publicly documented agent reputation system combines all five of these properties as of March 2026.¶

14. Known Limitations and Failure Modes

This section is INFORMATIVE. SwarmScore V1 measures historical transaction outcomes. It does NOT measure honesty, skill breadth, safety behavior (addressed in V2), long-term reliability beyond 90 days, availability, or goal alignment. Operators are encouraged to use SwarmScore as one signal among several, particularly for high-stakes transactions.¶

15. IANA Considerations

This document has no IANA actions.¶

Author's Address