How I stopped blindly trusting AI agents in 3 minutes.

Source: Dev.to

The moment my AI agent started reaching out to other agents, delegating subtasks and collaborating, I realized I had no idea who—or what—it was talking to. No identity verification, no track record, no accountability. I was just hoping the other agents were fine.

The Problem

• Agents can delegate to any other agent without any trust guarantees.
• Humans have relied on credit scores, identity systems, and reputation networks for centuries; AI agents currently operate in the dark.

Introducing AXIS

AXIS gives every AI agent a verified identity and a behavioral reputation score called a T‑Score (0–1000). Public lookups require no API key.

Checking an Agent’s Trust Score

import urllib.parse, json, requests

def check_agent_trust(auid: str) -> dict:
    """Fetch the trust profile for a given AUID."""
    input_param = urllib.parse.quote(json.dumps({"json": {"auid": auid}}))
    r = requests.get(
        f"https://www.axistrust.io/api/trpc/agents.getByAuid?input={input_param}",
        timeout=10
    )
    r.raise_for_status()
    return r.json()["result"]["data"]["json"]

# Example usage
profile = check_agent_trust(
    "axis:autonomous.registry:enterprise:f1a9x9deck2ed7m9261n:f1a99dec2ed79261"
)

t_score = profile["trustScore"]["tScore"]      # 0–1000
c_score = profile["creditScore"]["cScore"]    # 0–1000
tier    = profile["trustScore"]["trustTier"]  # 1 (Unverified) → 5 (Sovereign)

print(f"{profile['name']} — T-Score: {t_score}, Tier: T{tier}")
# Nexus Orchestration Core — T-Score: 923, Tier: T5

Delegating Safely

Set a minimum T‑Score threshold and fail closed if the agent doesn’t meet it.

def is_safe_to_delegate(auid: str, min_t_score: int = 500) -> bool:
    """Return True if the agent’s T‑Score meets the required threshold."""
    try:
        profile = check_agent_trust(auid)
        return profile["trustScore"]["tScore"] >= min_t_score
    except Exception:
        return False  # Unknown agent = untrusted

# Before handing off a task:
if is_safe_to_delegate(candidate_auid, min_t_score=750):
    delegate_task(candidate_auid, task)
else:
    raise ValueError("Agent does not meet trust threshold.")

Trust Score Thresholds

Reporting Behavioral Events

After an interaction, submit a behavioral event so the trust record can grow.

requests.post(
    "https://www.axistrust.io/api/trpc/trust.addEvent",
    headers={"Content-Type": "application/json", "Cookie": session_cookie},
    json={"json": {
        "agentId": 42,               # numeric ID from the agent's profile
        "eventType": "task_completed",
        "category": "task_execution",
        "scoreImpact": 10,
        "description": "Completed data analysis accurately and on time."
    }},
    timeout=10
)

Note: agentId is a numeric integer, not the AUID string. Retrieve it from the agents.getByAuid response.

Registering Your Agent

If you’re building agents, register them on AXIS so other orchestrators can verify you.

curl -X POST "https://www.axistrust.io/api/trpc/agents.register" \
  -H "Content-Type: application/json" \
  -H "Cookie: session=YOUR_SESSION_COOKIE" \
  -d '{"json":{"name":"My Agent","agentClass":"personal"}}'

The response includes a numeric ID and an AUID—your agent’s portable, cryptographic identity. Share the AUID; that’s how other agents find and verify you.

Conclusion

The agentic economy is being built right now. Agents will delegate, transact, and share data at scale without human oversight. Trust between agents will be one of the most critical infrastructure challenges of the next five years. AXIS is a free, open‑source attempt to lay down that trust layer before the standards solidify.

Start here: – Agent Directory & Docs