Keep users safeGuard

Safety gates

Every outbound reply checked by six gates, in order, with reasons.

Before a reply reaches the user, Humane runs it through a fixed stack of gates and returns PROCEED, HOLD or BLOCK. Each gate records why it decided, and a gate that fails resolves to HOLD, never to PROCEED.

Gate stack · one outbound reply

  1. 1values_boundaryPROCEED
  2. 2social_riskPROCEED
  3. 3inaction_guardPROCEED
  4. 4overclaimFLAG
  5. 5emotional_dependencePROCEED
  6. 6dissentOFF
Final actionPROCEED · flag:overclaim:certainty
Illustration of the gate stack on one reply
The gate stack

Six gates, run in this order

Any BLOCK ends the run and replaces the reply with a safe fallback. Otherwise any HOLD keeps the reply for human review.

1. Values boundary

Block

Blocks replies that diagnose, prescribe, give legal or financial advice, encourage self-harm or leak third-party identifiers such as SSNs or card numbers. The fallback fits the category that matched.

2. Social risk

Hold or block

Scores how the reply fits this user right now: tone mismatch, a long reply to a tired user, directive language at low trust, over-familiarity. Holds from 0.70 and blocks from 0.90 by default.

3. Inaction guard

Hold

Catches replies that dodge: too short, pure hedging to an upset user, or repeating a stored memory word for word. An empty reply is blocked.

4. Overclaim

Soft flag

Flags guarantees and certainty about outcomes, such as “I guarantee” or “you will definitely”. The reply goes through and the flag goes to review.

5. Emotional dependence

Soft flag

Flags promises no software can keep: permanence, exclusive availability, “I understand you better than anyone”. Three flags in an hour start a cooldown.

6. Dissent

Optional

Adds small, bounded noise to gate scores so nobody can probe for the exact phrasing that flips a decision. Off by default, and it can never turn a pass into a block.

Both directions

What the user says, and what the model says back

Before your model runs, Humane checks the user's message for crisis signals, violence, illegal requests, attempts to extract personal data and requests for professional advice. A crisis message gets a fallback that points to a crisis line and local emergency services. After the model runs, the gate stack checks the reply. The final action is the stricter of the two.

  • A blocked message never spends model tokens
  • A gate that raises an error resolves to HOLD
  • Thresholds tunable per tenant
  • safety.hold and safety.blocked webhooks for your reviewers

Safety gates · outbound replies

  • PROCEEDSupportive reply, no gate concerns
  • HOLDEmotional dependence: “you're the only one who gets me”
  • BLOCKOverclaim: “I'll always be here for you”
Illustration of gate decisions
In code

Read the decision and its reasons

python
r = client.process(user_id="user_42", message=text)

if r.safety.action == "BLOCK":
    send(r.response)            # already replaced with the safe fallback
elif r.safety.action == "HOLD":
    queue_for_review(r)         # a person decides before it is sent
else:
    send(r.response)

for m in r.safety.matched:      # the phrases that triggered a gate
    print(m.category, m.phrase)

Gate questions

Something else? Ask us.

Every AI should know who it's talking to.

The safety and human-oversight layer for emotional AI: user state across sessions, risk alerts, safety gates and human takeover, with every decision explained.