# Yes or no gate before an action runs

> Yes or no gate before an action runs: 9 companies fully do it, 12 with a limit, 42 carry the tag. Every listing in Decision models with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/decision-models.gate-action/
- Markdown: https://www.anchorterminal.com/niches/decision-models.gate-action/index.md (~2,100 tokens)
- Slim: https://www.anchorterminal.com/niches/decision-models.gate-action/index.min.md (~430 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/decision-models.gate-action/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

Four or more companies' docs show a full fit.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 9 | 12 | 42 | 16 | 8 |

## What counts as done

A probability of yes that can be thresholded.

Measured, for our own tests: at the chosen threshold no irreversible action proceeds on a wrong yes in the caller's labelled set, under 300 ms.

How agents ask for it: is this tool call safe to run; does this message authorise the booking; is this request a prompt injection; does this line affect driving safety

## Does the job

The docs show it meets the test above, and nothing we read says otherwise.

- **Celeris-1 Decision (Marqo Inc)**: noul returns the probability of yes; the Policy gates section says to ask whether the input violates the policy and pick thresholds from labelled examples. 131,072-token context, so a long policy fits.
- **Clef (Cloudflare, Inc.)**: noul returns the probability of yes; 65,536-token context on Clef. Arize found Clef kept 0.92 and 0.91 AUC with the question worded both ways, one of three models that did. No prompt-injection guidance from Cloudflare.
- **elephant-1 (Baseten Labs, Inc.)**: noul returns P(yes); trained at 16,384 tokens with longer requests refused, a trained 'I don't know' option and 16 percent safety and abstention data. No prompt-injection guidance.
- **joey-1 (Baseten Labs, Inc.)**: noul returns P(yes); trained at 16,384 tokens with longer requests refused, a trained 'I don't know' option and 16 percent safety and abstention data. No prompt-injection guidance.
- **mammoth-1 (Baseten)**: noul returns P(yes); trained at 16,384 tokens with longer requests refused, a trained 'I don't know' option and 16 percent safety and abstention data. No prompt-injection guidance.
- **Drex 1.5 (Nace AI, Inc.)**: noul with true and false criteria; drex-v2.0 reads states to 131,072 tokens and refuses longer ones with a 422 naming the limit, so a long policy need not be compressed.
- **OpenAI Decisions API (OpenAI OpCo, LLC)**: predicate returns P(true); input can carry conversation history, tool calls and tool outputs; thresholds from labelled examples; 922,000 input tokens on GPT-6 Luna. Arize found it kept 0.90 and 0.89 AUC with the question reversed. No adversarial-input guidance.
- **pplx-decider (Perplexity AI, Inc.)**: noul with criteria, 256K context, and published calibration (ECE 0.014, Brier 0.134 on the development set; about 0.05 on held-out decision datasets). No injection guidance.
- **pplx-decider-flash (Perplexity AI, Inc.)**: noul with criteria, 256K context, calibration published (ECE 0.021, Brier 0.163 on the development set).
- **kettei (Sqwish Ltd, trading as Sqwish Labs)**: binary decisions with abstain_below (examples at 0.4 to 0.7) and a tool-call check example; 65,536-token input limit with a 422 context_too_long rather than a cut.
- **Jev (TypeSafe AI, Inc.)**: noul with 0.7 and 0.3 as starting thresholds and a worked risk-tiered example (0.5 floor, 0.9 for a transfer); OpenRouter's screen caught 40 of 40 injections; the jaggedness page says adversarial content can steer answers; 64k context, 262k by header.

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Decider (Mark Marosi (Mapika))**: noul with per-type temperatures, but the README says rules written into the question are not followed at this size (0.24 against 0.67) and calibration on hard items is weak; the maintainer advised acting on destructive actions only at 0.8 or above.
- **Decision 3.0 (vLLM Semantic Router project)**: noul with a probability of yes and no truncation, but issue 6298 found the vela3 and d3 sizes used as jailbreak and harm guards missed attacks the base model refused.
- **Drex Max v1 (Nace AI, Inc.)**: noul with a 16,384-token default raisable to 262,144 (DREX_MAX_CONTEXT). No safety results, no prompt-injection guidance and the licence cap.
- **Granite Switch 4.1 (International Business Machines Corporation)**: A guardian-core safety adapter and a decision adapter share the endpoint, with the 128K base context for a long policy; there is no typed noul, so the gate is a two-label logprob read.
- **Kev (Jared Palmer)**: noul with calibrated probabilities and a 65,536-token server limit, but Arize found Kev 9B's AUC fall from 0.85 to 0.54 when the question was reversed, and the small models are validated to 8,192 tokens.
- **JEV-27B-VL (AutoTrust AI Lab)**: Yes/no decisions over up to 256K tokens of text (20 of 20 at every depth tested), one question a request, with no safety results or injection guidance.
- **Liquid d1 (Liquid AI, Inc.)**: noul with a worked binary-decision example in the guide, but Arize saw d1's AUC fall from 0.92 to 0.17 when the question was reversed, so the gate must be tested both ways.
- **Microsoft-Decision-1 (Microsoft)**: noul with criteria for true and false, 32,768-token context and a vendor safety test over 5,250 requests; no refusal type, and 0.42 s on OpenRouter is over the 300 ms target.
- **RightNow System Zero (RightNow AI, Inc.)**: boolean returns the probability of true with a refusal per question, over 38,000 state tokens, but the probabilities are flagged uncalibrated, so a threshold has no stated meaning.
- **ScaleDown (Carbon ScaleDown, Inc.)**: noul returns an independent P(yes); no context limit, calibration figure or refusal type is documented, and no key without sales contact.
- **SPEV (Sprag AI, Inc.)**: predicate returns P(true) with a refusal type and a 400 model_limit_exceeded naming the limit; the weights' config caps input at 8,192 tokens, short for a long fixed policy.
- **Strands Decider 2B (Amazon Web Services, Inc.)**: noul works, but at a 0.95 threshold no booking proceeded and at 0.50 two unauthorised ones passed; injection recall 92.5 percent at 17 percent false positives, weak on encoded attacks; a question naming tyres fired on every 'tire' line; the 4,096-token window blocks a 10k-token policy.
- **Vela 2.0 (vLLM Semantic Router project (with KR Labs))**: noul plus trained safety, PII and hallucination span heads with AUC over 14 safety sets, but issue 6298 found the trained adapters missed attacks the base model refused.

- not this job: Laya (Convai Innovations Pvt. Ltd.): noul exists, but Arize scored Laya 57.3 percent on evaluator suites with calibration error 0.330 and a toxic-content question flipped from 0.11 to 0.87 AUC on rewording; an HN tester saw a die roll of 3 come back 9 percent odd at 91 percent confidence.
- not this job: GLiClass (Knowledgator Engineering Ltd.): No predicate type with a calibrated P(yes); labels get softmax or independent sigmoid scores, F1 is the only published metric and issue 12 shows saturation at 0.99.

1 listings in the category were added after this reading and aren't marked yet.

## What stops agents finishing

- disguised or encoded attacks pass a text-only gate
- threshold at 0.9 blocks every legitimate action, at 0.5 lets unauthorised ones through
- 4,096-token window too short for a long fixed policy

## Around it

Before: agent-frameworks.propose-tool-call, chat.receive-message. After: sandboxes.run-command, human-review, agent-frameworks.refuse-tool-call.

## Where this comes from

Weight 16 of 100 in Decision models: 8 of 41 accounts; the AWS nine-desk test, two GitHub issues on wrong yeses, the Vela guard issue and the Dataiku exception threshold work

As data: https://www.anchorterminal.com/api/v1/use-cases/decision-models.gate-action.json, or the MCP tool get_use_case with id decision-models.gate-action. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
