{"uid":"cap_0P1noEyk1s7w_K__yK--R","slug":"dexl-pii-redaction-a3a482a9","name":"DexL PII Redaction","description":"Replace personal data in text with typed placeholders. Emails, phone numbers, cards, IBANs and IP addresses are matched by exact pattern and never left to the model - the deterministic cases cannot be missed. Names, addresses and ids are judged by a model, and output shorter than half the input is rejected, so redaction never silently deletes text. The method is returned with the result.","url":"https://agents.dexl.io/v1/tools/redact-pii","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","maxLength":8000},"kinds":{"type":"array","items":{"enum":["email","phone","person","address","card","id","iban","ip"],"type":"string"},"description":"What to remove. Defaults to all of: email, phone, person, address, card, id, iban, ip."}}},"responseSchema":{"type":"json","example":{"units":1,"cached":false,"output":{}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_P_23C7sKAk9PryamjDAXm","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Replaces personally identifiable information (emails, phones, cards, IBANs, IPs, names, addresses, IDs) in text with typed placeholders using a hybrid deterministic+model approach","exampleAgentPrompt":"Can you redact all the PII from this customer support message before I store it — strip out emails, phone numbers, names, addresses, credit card numbers, IBANs, and IP addresses, and replace each one with a labeled placeholder: 'Dear John Smith, please call us at 555-123-4567 or email john@example.com. Your card ending 4242 was charged.'","exampleUseCases":[{"title":"GDPR-safe support ticket logging","prompt":"Before saving this support ticket to our database, redact all PII — names, emails, phone numbers, and any card or IBAN numbers — and replace them with typed placeholders so we stay GDPR-compliant: 'Hi, I'm Maria Rossi, my email is maria@rossi.it and my IBAN is DE89370400440532013000.'"},{"title":"Sanitize user input before LLM processing","prompt":"I need to pass this user message to a language model but first scrub out any personal data — remove emails, IP addresses, and person names, and swap them for placeholders: 'My name is Alex Chen, I'm at 192.168.1.1 and you can reach me at alex.chen@corp.com.'"},{"title":"Anonymize logs for analytics","prompt":"Anonymize these server log entries for our analytics team by replacing all IP addresses, email addresses, and any identifiable IDs with placeholders — here's the log: '2024-01-15 GET /api/user from 203.0.113.42 by user john.doe@company.com id=USR-00492.'"}],"resultDescription":"A JSON object containing the redacted output text with PII replaced by typed placeholders (e.g. [EMAIL_1], [PHONE_1], [PERSON_1]), the method used for redaction, the number of units consumed, and whether the result was cached. Output shorter than half the input length is rejected to prevent silent text deletion.","failureModes":["Input text exceeds 8000 character limit — request rejected","Invalid PII kind enum value in kinds array — validation error","Output shorter than 50% of input rejected to prevent silent deletion — error returned","Network timeout on model-based judgments for names/addresses","Malformed JSON request body — 400 error"],"whenToPreferThis":"Choose this endpoint when you need reliable, typed-placeholder PII redaction with a hybrid approach: deterministic regex for high-precision fields (email, phone, card, IBAN, IP) combined with model judgment for harder cases (names, addresses, IDs). Prefer it over pure regex tools when named entities matter, and over pure LLM redaction when you need deterministic guarantees for structured PII like card numbers. The rejection guard (output < 50% input = error) makes it safer than alternatives that might silently delete text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T12:51:49.197Z","isFirstParty":false}