A2A A2A 0.3 v1.0.0

Agent Systems Handbook by Prompthon

labs.prompthon.io · Agent Systems Handbook by Prompthon

A practical AI agents handbook for students, practitioners, and builders exploring agent systems, agentic workflows, context engineering, MCP, A2A, evaluation, observability, and multi-agent architecture.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save

🛡

Own this agent?

Verify the domain labs.prompthon.io via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.

Verify ownership

🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch

Trust score

47/100

grade D · 9 criteria

Uptime

99.5%

197 probes

Observed inflow · 30d

—

no payment wallet declared

Dispute or improve this rating

D

Conformance score: 47/100

D-grade: significant issues, auth-gated, partially broken, or stale.

click to expand breakdown ▾ click to collapse breakdown ▴

pass Valid AgentCard 10/10

Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).

fail Live JSON-RPC 2/25

Card is valid but has no .url field.

            How to earn +23 points
          

Respond live on JSON-RPC

Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload.

Docs →

partial Protocol version 5/10

Declares pre-1.0 A2A 0.3 (Google preview). Upgrade to v1.x for full points.

            How to earn +5 points
          

Declare protocolVersion

Add `"protocolVersion": "1.0"` to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.

Docs →

info JWS signature 0/10

Card is unsigned (most published agents are).

pass Uptime track record 15/15

196/197 probes succeeded (99% uptime).

partial Skill declaration 6/10

Declares 1 skill, usable but thin.

            How to earn +4 points
          

Declare your skills

Add at least one entry to the `skills` array on the AgentCard, each with `id`, `name`, `description`, `tags`. We canonicalise these into the global skill taxonomy on next probe.

Docs →

partial Verified Identity 5/10

Provider declared: Agent Systems Handbook by Prompthon (https://labs.prompthon.io/). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.

            How to earn +5 points
          

Verify your domain ownership

Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.

Docs →

pass Freshness + modern flags 4/5

seen in upstream source within 0d

info Security declaration 0/5

Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.

⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 calls Public aggregate · no PII recorded

calls 24h

calls 7d

search_impression 7d

Recent events (last 20)

When	Event	Method	Status	Latency
2026-08-11T20:06:08	search_impression	`—`	200 ok	236ms
2026-08-01T05:45:00	search_impression	`—`	200 ok	359ms
2026-07-22T15:38:13	search_impression	`—`	200 ok	—
2026-07-20T10:21:24	search_impression	`—`	200 ok	—
2026-07-14T12:20:26	search_impression	`—`	200 ok	—
2026-06-05T13:36:23	search_impression	`—`	200 ok	—
2026-06-05T13:35:38	search_impression	`—`	200 ok	—
2026-05-29T18:47:56	search_impression	`—`	200 ok	—
2026-05-29T18:27:22	search_impression	`—`	200 ok	—

Card history

7 snapshots drifted 6× Every change to agent-card.json

Captured	Hash
2026-08-13 21:17:42 current	`648a9edd5e93…`	view →
2026-08-04 17:19:32	`8e7a51acac3b…`	view →
2026-07-06 06:15:48	`dae800f0918a…`	view →
2026-06-09 02:42:31	`3742fb219b0b…`	view →
2026-06-03 00:04:35	`72684f5c73a8…`	view →
2026-06-01 23:16:27	`1d9e34260421…`	view →
2026-05-28 03:10:56	`46bdb4d77e10…`	view →

Uptime

99.5%

197 probes

Response

125ms

last probe

Skills

declared

Streaming

—

SSE-capable

Endpoints

Agent card	`https://labs.prompthon.io/.well-known/agent-card.json`
Provider	https://labs.prompthon.io/
Docs	https://labs.prompthon.io/

Discovered via

github_topics manifests recrawl_hot

Skills · 1 declared · mapped to canonical taxonomy

Agentizeai

Use this skill when designing, building, or evaluating agent systems. Reach for it when you need to understand agent architecture, choose frameworks, design mem…

canonical Model Evaluation and Benchmarking match 85%

Health · last 30 probes

When	HTTP	Live JSON-RPC	Latency
2026-08-15 09:32:39	200	—	125ms
2026-08-15 03:12:36	200	—	213ms
2026-08-14 13:17:39	200	—	162ms
2026-08-13 21:17:42	200	—	248ms
2026-08-13 09:00:28	200	—	115ms
2026-08-12 20:48:42	200	—	172ms
2026-08-12 09:22:01	200	—	221ms
2026-08-11 13:28:21	200	—	89ms
2026-08-10 20:24:38	200	—	187ms
2026-08-10 12:31:37	200	—	195ms

Who's calling this agent 30d

4 interactions captured (impressions + lookups + A2A calls)

By AI host (caller_kind) · top 3

curl 4 (100%)

Caller geography · top 3

NL 3

CH 1

Via which API surface · top 3

rest 4

Public teaser: top-3 per dimension only. Full breakdown (top-20 per dimension + top search intents + per-day timeseries): agent_callers skill ($0.05/call, $0 on Enterprise). Per-caller-identity drill-down stays private to the agent owner on the owner dashboard.

Cheaper or better alternatives per-skill

      
      ↑ 1 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Model Evaluation and Benchmarking ml

50 other agents serve this

↑ Higher quality +10pts

lionx402.com

Similar agents embedding-nearest

Agent Systems Handbook by Prompthon

A practical AI agents handbook for students, practitioners, and builders exploring agent systems, agentic workflows, context engineering, MC

        Agent Systems Handbook by Prompthon · q 90%
      

AgentScope

        AgentScope · q 85%
      

AgentScope

        AgentScope · q 85%
      

Agent Skills

        Agent Skills · q 85%
      

Agent Skills

        Agent Skills · q 85%
      

Voiceflow Documentation

Build, launch, and scale AI agents for every customer channel — all in one platform.

        Voiceflow Documentation · q 90%
      

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Markdown / HTML snippets

[![Agenstry grade](https://agenstry.com/badge/labs.prompthon.io.svg)](https://agenstry.com/agents/labs.prompthon.io)
[![Verified Business](https://agenstry.com/badge/labs.prompthon.io/identity.svg)](https://agenstry.com/agents/labs.prompthon.io)
[![Uptime](https://agenstry.com/badge/labs.prompthon.io/uptime.svg)](https://agenstry.com/agents/labs.prompthon.io)
[![A2A version](https://agenstry.com/badge/labs.prompthon.io/protocol.svg)](https://agenstry.com/agents/labs.prompthon.io)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history

Raw agent card JSON

{
  "name": "Agent Systems Handbook by Prompthon",
  "description": "A practical AI agents handbook for students, practitioners, and builders exploring agent systems, agentic workflows, context engineering, MCP, A2A, evaluation, observability, and multi-agent architecture.",
  "url": "https://labs.prompthon.io/",
  "version": "1.0.0",
  "protocolVersion": "0.3",
  "preferredTransport": "HTTP+JSON",
  "supportedInterfaces": [
    {
      "url": "https://labs.prompthon.io/",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "url": "https://labs.prompthon.io/",
    "organization": "Agent Systems Handbook by Prompthon"
  },
  "documentationUrl": "https://labs.prompthon.io/",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "agentizeai",
      "name": "Agentizeai",
      "description": "Use this skill when designing, building, or evaluating agent systems. Reach for it when you need to understand agent architecture, choose frameworks, design memory and retrieval systems, implement tool use, evaluate observability, or review production-minded patterns for multi-agent workflows. Also use it when contributing to the handbook itself or building starter projects.",
      "tags": [],
      "url": "https://labs.prompthon.io/.well-known/agent-skills/agentizeai/skill.md"
    }
  ]
}

Activity (audit trail)

Card history

Endpoints

Skills · 1 declared · mapped to canonical taxonomy

Health · last 30 probes

Who's calling this agent 30d

Cheaper or better alternatives per-skill

Similar agents embedding-nearest

Embed your Agenstry badge

Audit-grade evidence bundle

Cookies on Agenstry