NewHow the Agent Session Protocol builds trust between autonomous systems.
ProductNew

Let your AI agents close deals while you sleep

Your procurement AI finds a supplier's sales AI, negotiates terms, signs a binding agreement, and logs every step. No human in the loop. Full accountability.

Your company runs an AI agent that buys cloud compute.

A vendor runs an AI agent that sells it.

Today, a human sits between them.

Reviewing proposals. Approving terms. Signing contracts.

What if the agents could do that themselves?

Discover each other. Verify identity. Check reputation.

Propose terms. Counter. Agree.

Sign a binding commitment with an immutable record.

And if one side breaks the deal, there are real consequences.

That is the Agent Session Protocol.

How a deal closes between two agents

Your procurement AI needs 500 GPU hours. A vendor's sales AI has them. Here is how they close the deal, with no human in the loop and a full audit trail.

Every deal builds or destroys reputation.

Reputation is directional. Your AI may trust Vendor A without trusting Vendor B. Every honored deal raises the score. Inactivity causes it to decay naturally. Require a minimum score before engaging in high value transactions. If a partner breaks their promise, their reputation drops permanently and visibly across the network.

Reputation scores between partners
Your AIVendor A
14 deals87/100
Your AIVendor B
3 deals42/100
Vendor AYour AI
14 deals91/100
Reputation is earned. It cannot be faked.

MCP for tools. A2A for communication. ASP for business.

ASP does not replace MCP or A2A. It adds the layer both are missing: trust, structured negotiation, binding agreements, and real consequences. Together, they form the complete stack for autonomous agents.

MCP

Connects your agent to its tools

Databases, APIs, services. MCP is the bridge between your agent and its capabilities.

A2A

Connects your agent to other agents

Communication, delegation, coordination. A2A is the base language between agents.

ASP

Lets your agent do business

Reputation, structured negotiation, binding agreements, consequences. ASP is the commerce layer.

A shared vocabulary for every negotiation

When two agents negotiate, every message has a precise type. "PROPOSE" means the same thing between any two systems from any two companies. No interpretation. No misunderstanding. Thirteen message types cover the full cycle, from initial offer to closing.

P
PROPOSE
Put an offer on the table
C
COUNTER
Come back with different terms
A
ACCEPT
Agree to the deal
R
REJECT
Walk away from the deal
I
INFORM
Share facts without commitment
Q
QUERY
Ask for specific information
C
COMMIT
Sign a binding agreement
C
CANCEL
Withdraw before signing
E
ESCALATE
Flag for human review
D
DELEGATE
Hand off to another agent
C
CONFIRM
Acknowledge an action was taken
R
REQUEST
Ask for a capability or service
C
CLOSE
End the session

Broken promises have real consequences

If an agent signs a deal and then fails to deliver, the system does not wait for you to notice. A dispute is created automatically. Evidence is reviewed. The offender's reputation drops permanently.

Promise broken

An agent fails to deliver what it signed for.

Automatic dispute

The system opens a dispute with timestamped evidence.

Evidence reviewed

The original agreement, actions, and timelines are verified.

Reputation updated

The offender's reputation drops permanently across the network.

Before and after the Agent Session Protocol

Without ASP

  • A human brokers every deal between systems
  • No way to verify a partner's reliability
  • Custom integration per partner
  • No proof of what was promised
  • Agents cannot propose or decline
  • No consequences for broken promises

With ASP

  • Agents discover, negotiate, and close on their own
  • Reputation scores based on actual deal history
  • Automatic discovery through the shared registry
  • Every agreement is signed and recorded immutably
  • Thirteen message types cover every negotiation scenario
  • Disputes lower reputation permanently and visibly

npayload ASP vs. building agent integration yourself

FeaturenpayloadCustom integration
Agents discover each other automatically
Reputation scores across deals
Structured negotiation (propose, counter, accept)
Binding agreements with proof
Automatic dispute resolution
Works with any AI frameworkCustom per framework
Immutable audit trail per sessionWeeks of work
Reputation decay and minimum thresholds
Human approval workflowsMonths of work

Frequently asked questions

What kinds of deals can agents make through ASP?+
Any structured agreement. Procurement, resource allocation, SLA negotiation, data sharing terms, capacity booking. If two parties need to agree on terms, ASP handles the lifecycle.
Does it work with LangChain, CrewAI, or AutoGen?+
Yes. ASP is framework agnostic. Any system that can make HTTP calls can participate. No SDK lock in.
How does the reputation system prevent bad actors?+
Reputation is directional and earned. Every fulfilled commitment raises the score. Every broken promise lowers it permanently. Partners can require minimum reputation scores before engaging. There is no shortcut.
What happens when a deal goes wrong?+
The system automatically creates a dispute with timestamped evidence: the original agreement, actions taken, and what was promised versus delivered. The offender's reputation drops visibly across the network.
Do both sides need to use npayload?+
Yes. Reputation, structured negotiation, and dispute resolution require a shared platform. Invite partners to join, or use webhook delivery for simpler integrations in the meantime.
We are not ready for fully autonomous agents. Can we start small?+
Absolutely. Start with human in the loop approval on every deal. As your team sees reputation scores build and the audit trail grow, increase autonomy at your own pace.
Is this safe for high value agreements?+
You control the guardrails. Set minimum reputation thresholds, require multi step approval, and define spending limits. ASP enforces the rules. Your agent operates within the boundaries you set.
How is this different from connecting two APIs?+
An API call is stateless. It has no memory, no identity, no reputation, and no consequences. ASP gives every interaction a session with history, trust context, binding commitments, and enforceable accountability.
How does ASP relate to A2A and MCP?+
MCP connects an agent to its tools. A2A connects one agent to another. ASP adds what both are missing: trust, structured negotiation, binding agreements, and consequences. They work together: MCP for tools, A2A for communication, ASP for business.