Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
## The Trust Gap in Multi-Agent Deployments
Every platform governs its own agents. Nobody verifies trust across platforms. 60% of enterprises are scaling AI agents, yet only 4% are governing them at scale. 97% have had identity-related security incidents. The trust gap is widening, not closing.
Show the rest of the publisher’s description (26 more lines)
Assay by Foundry Labs is the neutral trust broker - cross-platform agent identity, trust scoring, and coordination infrastructure that works with AWS Bedrock agents, Azure agents, Claude agents, and custom agent frameworks.
## How Assay Works
Assay computes trust scores from verified operational outcomes - not self-reported, not token-staked, not voted on. The gaming-resistant algorithm uses recency weighting, counterparty verification, velocity anomaly detection, and industry-specific presets for manufacturing, pharma, logistics, energy, and financial services.
Assay is read-only by design. It never controls your agents. It scores them, verifies them, and issues credentials. Your orchestration layer decides what to do with the trust data.
## Key Capabilities
**Agent Passports**
Signed, portable credentials that prove an agent's identity, capabilities, and verified track record. Any platform can verify a passport in one API call. Features include 24-hour expiry, cryptographic signing, and independent verifiability.
**Work Cells**
Trust-gated coordination groups where agents form teams based on earned competence. Define roles, set minimum trust thresholds, and specify completion conditions in natural language. Agents that have not earned sufficient trust cannot participate, and the system tells them exactly what is needed to qualify.
**Cross-Platform Agent Identity and Trust Scoring**
- Gaming-resistant trust algorithm with recency weighting and counterparty verification
- Velocity anomaly detection to prevent score manipulation
- Industry-specific presets for manufacturing, pharma, logistics, energy, and financial services
## Platform Integrations
- **AWS Bedrock** - Industrial agent trust verification
- **ServiceNow** - Trust-verified dispatch
- **Salesforce** - Cross-platform agent discovery
- **Supply Chain** - Verified supplier intelligence
Compatible with Bedrock agents, Azure agents, Claude agents, and custom agent frameworks.
## Why Assay
Agent discovery and authentication tell you who an agent is.
Assay tells you how good it is at its job. Not what
permissions it has, but what outcomes it has delivered.
Built by Foundry Labs and used in production across 16,000+ verified operations. The same trust infrastructure that powers industrial equipment coordination, available as a standalone platform for any agent deployment.
## Getting Started
Subscribe through AWS Marketplace and connect Assay to your existing agent infrastructure. Use platform integration templates to begin verifying agent trust across your multi-agent deployments immediately.
Highlights
Highlighted by the publisher on AWS Marketplace.
Cross-platform agent trust scoring computed from verified operational outcomes, not self-reported data. Gaming-resistant algorithm with recency weighting, counterparty verification, and velocity anomaly detection. Industry-specific presets for manufacturing, pharma, logistics, energy, and financial services. Compatible with AWS Bedrock, Azure, Claude, and custom agent frameworks.
Agent Passports provide signed, portable credentials proving an agent's identity, capabilities, and verified track record. Any platform can verify a passport in a single API call. Passports feature 24-hour expiry, cryptographic signing, and independent verifiability. Read-only by design - Assay never controls your agents, it scores and verifies them.
Work Cells enable trust-gated coordination where agents form teams based on earned competence. Define roles, set minimum trust thresholds, and specify completion conditions in natural language. Agents without sufficient trust cannot participate and receive clear guidance on qualification requirements. Used in production across 16,000+ verified operations.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Plans and pricing as listed
10 listed- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
- Units
Refund terms
As stated by the publisher on AWS Marketplace.
Foundry Labs offers a pro-rated refund for unused contract time on cancellation of Pro and Business subscriptions. Per-call API usage already consumed is non-refundable. For refund requests, contact forge@foundrynet.io.
Sources
Linked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.