Thibitisha mdai ni mwenye sera, zuia ushahidi wa video wa deepfake, gundua nyaraka bandia, chunguza dhidi ya orodha za vikwazo, tafuta vikundi vya majeraha vilivyopangwa, katika kikao kimoja cha /v3/. $0.53 kwa kila dai, 500 bure kila mwezi.
Robinhood Ventures
Inaaminika na mashirika 2,000+ duniani kote.
Kinacholipwa kisichostahili
Muungano Dhidi ya Ulaghai wa Bima unakadiria kuwa wabebaji wa Marekani hupoteza karibu $308 bilioni kwa mwaka. Mengi ya haya hutokana na madai yasiyo na uhakiki wa utambulisho wa mdai na hakuna uchunguzi wa ushahidi. Didit huziba mapengo yote mawili katika mfumo mmoja wa kazi, $0.53 kwa kila dai, 500 bila malipo kila mwezi.
Chagua ukaguzi unaotaka, ID, liveness, face match, sanctions, address, age, phone, email, maswali maalum. Ziburute kwenye mtiririko katika dashibodi, au tuma mtiririko huo huo kwenye API yetu. Panga masharti, fanya majaribio ya A/B, hakuna code inayohitajika.
Pachika asili na Web, iOS, Android, React Native, au Flutter SDK yetu. Elekeza upya kwenye ukurasa uliopangishwa. Au tuma tu kiungo kwa mtumiaji wako, kwa barua pepe, SMS, WhatsApp, popote. Chagua kinachofaa stack yako.
Didit huandaa kamera, ishara za mwanga, uhamishaji wa simu, na ufikiaji. Wakati mtumiaji yuko kwenye mtiririko, tunapima ishara 200+ za ulaghai kwa wakati halisi na kuthibitisha kila sehemu dhidi ya vyanzo vya data vya kuaminika. Matokeo chini ya sekunde mbili.
Webhooks zilizotiwa saini kwa wakati halisi huweka database yako sawa mara tu mtumiaji anapoidhinishwa, kukataliwa, au kutumwa kwa ukaguzi. Uliza API inapohitajika. Au fungua console kukagua kila session, kila ishara, na kudhibiti kesi kwa njia yako.
Didit · Maumbo ya Madai
Didit · Uthibitishaji wa Mdai
Dai · 4 / 5
Linganisha na sera
Didit · OCR ya Hati + Kudanganya
Didit · Uhai Tulivu · iBeta L1 PAD
Didit · AML + Utafutaji wa Nyuso
Uchunguzi wa AML
Utafutaji wa Uso · wadai wa awali
Didit · Webhook · X-Signature-V2
{
"session_id": "claim-8821",
"vendor_data": "claim-8821",
"status": "In Review",
"face": { "similarity_score": 0.42 },
"aml": { "status": "In Review",
"hits": [{ "list": "PEP" }] },
"face_search": { "matches": [
{ "session_id": "claim-7710",
"similarity": 0.94 }
] }
}$ curl -X POST https://verification.didit.me/v3/session/ \
-H "x-api-key: $DIDIT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"workflow_id": "wf_claim_verify",
"vendor_data": "claim-8821",
"metadata": { "policy_id": "POL-44120" }
}'{ "session_url": "verify.didit.me/..." }// X-Signature-V2 verified upstream
if (payload.status === "Imeidhinishwa") {
releasePayout(payload.vendor_data);
} else if (payload.status === "In Review") {
routeToSiu(payload.face_search.matches);
}hali Imeidhinishwa · Imekataliwa · Inapitiwa · HaijakamilikaYou are integrating Didit into an insurance carrier's claim workflow at first notice of loss (motor, health, property, travel, business interruption). Goal: catch ghost claims, deepfake video evidence, forged supporting documents, sanctions hits on the claimant, and organised-injury rings before the payout enters the queue. One API call. One signed webhook. Five fraud signals.
WHY THIS SHAPE
- The Coalition Against Insurance Fraud estimates fraud costs the US industry around $308 billion / year (2022 figures). Most of that walks in through claims with no identity check on the claimant and no document forensics on the evidence.
- Five signals settle the question on most claims: (1) the claimant is the policyholder, (2) the claimant is alive and present (not a deepfake), (3) the supporting documents are not tampered or templated, (4) the claimant is not on a sanctions list, (5) the claimant has not already filed N near-identical claims across your portfolio.
- One Didit /v3/session/ call bundles all five. $0.33 KYC + $0.20 AML = $0.53 per claim. Face Search 1:N is free per search. 500 verifications free every month.
PRE-REQUISITES
- Production API key from https://business.didit.me (sandbox key in 60 seconds, no credit card).
- A webhook endpoint with HMAC SHA-256 verification of the X-Signature-V2 header using your webhook secret.
- A Workflow Builder workflow bundling ID Verification + Passive Liveness + Face Match 1:1 (with the policyholder portrait as comparison target) + AML Screening + Face Search 1:N (gallery scoped to prior claimants on your account).
- Reference to the policy ID and policyholder portrait on file from your Policy Administration System (PAS) — passed as metadata on the session.
STEP 1 — Open the claim-verification session
POST https://verification.didit.me/v3/session/
Headers:
x-api-key: <your api key>
Content-Type: application/json
Body:
{
"workflow_id": "<wf id bundling ID + Liveness + Face Match + AML + Face Search 1:N>",
"vendor_data": "<your claim id, max 256 chars>",
"callback": "https://<your-app>/claims/verify/callback",
"metadata": {
"policy_id": "<your policy id>",
"line_of_business": "motor",
"loss_date": "2026-04-12"
}
}
Response: 201 Created with a hosted session URL. Send it to the claimant by email / Short Message Service (SMS) / inside the claims app. The claim stays in HOLD on your side until the signed webhook lands.
STEP 2 — Read the signed webhook
Didit POSTs the verdict. Verify X-Signature-V2 (HMAC SHA-256 of the raw body) BEFORE reading the JSON.
Payload (excerpted):
{
"session_id": "<uuid>",
"vendor_data": "<your claim id>",
"status": "In Review",
"id_verification": { "status": "Approved" },
"liveness": { "status": "Approved" },
"face": { "status": "Approved", "similarity_score": 0.92 },
"aml": { "status": "In Review", "hits": [{ "list": "PEP" }] },
"face_search": {
"matches": [
{ "session_id": "claim-7710", "similarity": 0.94, "vendor_data": "claim-7710" }
]
}
}
Session status enum (exact case, Title Case With Spaces): Approved | Declined | In Review | Resubmitted | Expired | Not Finished | Kyc Expired | Abandoned.
STEP 3 — Branch on the verdict
Approved → release the claim into the standard payout queue.
In Review → route to the Special Investigations Unit (SIU) with the per-module signals + face-search match list as the case file.
Declined → decline + open file. Block the payout. The decision payload is the audit pack.
Not Finished → resend the session link.
STEP 4 — Document forensics on supporting evidence (separate sub-flow)
For each supporting PDF / image uploaded (police report, repair quote, medical invoice, photo of loss), run Didit Document Optical Character Recognition (OCR). The OCR response surfaces:
- Field-level extracted text (claim amount, names, dates)
- Tamper score per region (pixel-level edits)
- Template match against prior submissions (reused PDF skeleton)
- EXIF / metadata mismatch (date in photo vs date of loss)
A high tamper score or a template match against a prior claim flips the case status to In Review.
STEP 5 — Pull the full decision for the case file
GET https://verification.didit.me/v3/session/{session_id}/decision/
Headers:
x-api-key: <your api key>
Returns the full decision payload — per-module signals, raw face-similarity scores, AML hit list with source list per match, face-search candidate list with scores. Use this as the audit pack for any dispute.
WEBHOOK EVENT NAMES
- Sessions: standard session webhook. One endpoint, status field tells you the lifecycle.
- Verify X-Signature-V2 (HMAC SHA-256) on every payload.
CONSTRAINTS
- Session statuses use Title Case With Spaces. Never UPPER_SNAKE_CASE — that's the Transactions API.
- The Face Match comparison target is the policyholder portrait from your Policy Administration System (PAS). A deepfake of the policyholder cannot pass when Passive Liveness is also in the workflow.
- Face Search 1:N gallery is scoped to YOUR account — Didit does not search across carriers. To collaborate across an industry pool, use a shared workflow_id pointing at a multi-carrier gallery you own.
- 200+ fraud signals are surfaced on every session at no extra cost — read them off the decision payload, don't re-query.
- Default retention is the standard 5-year insurance horizon; adjust per workflow if your jurisdiction differs.
Read the docs:
- https://docs.didit.me/sessions-api/create-session
- https://docs.didit.me/core-technology/face-match/overview
- https://docs.didit.me/core-technology/aml-screening/overview
- https://docs.didit.me/core-technology/face-search/overview
- https://docs.didit.me/integration/webhooks
Start free at https://business.didit.me — sandbox key in 60 seconds, 500 verifications free every month, no credit card.$0 / mwezi. Hakuna kadi ya mkopo inayohitajika.
Lipa tu kwa unachotumia. Moduli 25+. Bei za umma kwa kila moduli, hakuna ada ya chini ya kila mwezi.
MSA & SLA maalum. Kwa idadi kubwa na programu zilizodhibitiwa.
Anza bure → lipa tu wakati ukaguzi unafanyika → fungua Enterprise kwa mkataba maalum, SLA, au uhifadhi wa data.
Didit ni miundombinu ya utambulisho na udanganyifu, jukwaa ambalo tulitamani lingekuwepo tulipokuwa tukijenga bidhaa sisi wenyewe: wazi, rahisi, na rafiki kwa wasanidi, ili lifanye kazi kama sehemu halisi ya stack yako badala ya sanduku jeusi unalounganisha.
API moja inashughulikia kuthibitisha watu (KYC, mjue mteja wako), kuthibitisha biashara (KYB, ijue biashara yako), kuchunguza pochi za crypto (KYT, ijue miamala yako), na kufuatilia miamala kwa wakati halisi, kwenye stack iliyojengwa kuwa:
Miundombinu iliyo chini: aina 14,000+ za hati katika lugha 48+, vyanzo vya data 1,000+, na ishara za udanganyifu 200+ kwenye kila kipindi. Miundombinu ya Didit hujifunza kwa nguvu kutoka kila kipindi na inaboreshwa kila siku.
Muungano Dhidi ya Udanganyifu wa Bima ulikadiria kuwa bima za Marekani hupoteza karibu $308.6 bilioni kwa mwaka kutokana na udanganyifu katika sekta zote (utafiti wa 2022). Shirika la bima la Ulaya Insurance Europe linaripoti sehemu sawa ya hasara ya malipo katika EU yote.
Nyingi ni za fursa, kiasi kidogo kilichopandishwa bei kwenye madai halali. Sehemu ndogo ni vikundi vya kitaalamu vinavyowasilisha hasara ileile kwa watoa huduma tofauti. Aina zote mbili zina udhaifu mmoja: hakuna anayechunguza ni nani mdai wakati wa taarifa ya kwanza ya hasara.
Dai la mzimu ni pale ambapo mtu anayewasilisha dai si mwenye sera. Mfumo wa kawaida: mshambuliaji ananunua data ya mteja iliyovuja kutoka kwa uvunjaji wa usalama, anampigia simu mtoa huduma akijifanya kuwa mwenye sera, anawasilisha dai dogo la hasara, na anaomba malipo yatumwe kwenye akaunti mpya ya benki.
Shambulio linafanikiwa wakati hakuna ukaguzi wa kibayometriki unaounganisha mpigaji simu na mtu aliye kwenye sera. Face Match 1:1 dhidi ya picha ya mwenye sera inaziba pengo hili kwa sekunde mbili.
Mchakato mzima kwa kawaida huchukua chini ya sekunde 30 kuanzia mwanzo hadi mwisho, chukua kitambulisho, piga picha hati, piga selfie, umemaliza. Huu ndio mchakato wa haraka zaidi sokoni. Watoa huduma wa zamani wa KYC kwa kawaida huchukua zaidi ya sekunde 90 kwa mchakato kama huo.
Kwa upande wa back end, Didit inarudisha matokeo kwa chini ya sekunde mbili kwa p99, ikipimwa kuanzia wakati mtumiaji anamaliza selfie hadi wakati webhook yako inapoanza. Upigaji picha wa simu umeboreshwa kwa simu za polepole na mitandao ya polepole: ukandamizaji wa picha unaoendelea, upakiaji wa polepole wa software development kit, na uhamishaji wa kugusa mara moja kutoka desktop kwenda simu kupitia QR code ikiwa mtumiaji anaanza kwenye web.
Kwenye kila hati inayounga mkono ambayo mdai anapakia, ripoti ya polisi, makadirio ya ukarabati, ankara ya matibabu, picha ya hasara, Didit huendesha:
Alama ya juu ya udanganyifu au kulingana na template hubadilisha dai kutoka Approved kwenda In Review kiotomatiki.
Kila kipindi huishia kwenye mojawapo ya hali saba zilizo wazi, hivyo code yako inajua nini cha kufanya kila wakati:
Approved, kila ukaguzi umefaulu. Endeleza mtumiaji.Declined, ukaguzi mmoja au zaidi umeshindwa. Unaweza kumruhusu mtumiaji kutuma tena hatua maalum iliyoshindwa (kwa mfano, kupiga selfie tena) bila kuendesha upya mchakato mzima.In Review, imewekwa alama kwa ukaguzi wa kufuata sheria. Fungua kesi kwenye console, angalia kila ishara, amua kuidhinisha au kukataa.In Progress, mtumiaji yuko katikati ya mchakato.Not Started, kiungo kimetumwa, mtumiaji bado hajafungua. Tuma ukumbusho ikiwa itakaa muda mrefu sana.Abandoned, mtumiaji alifungua kiungo lakini hakumaliza kwa wakati. Mshirikishe tena au muda wake uishe.Expired, kiungo cha kipindi kimepitwa na wakati. Unda kipindi kipya.Webhook iliyosainiwa huwashwa kwenye kila mabadiliko ya hali, hivyo database yako inabaki sawa kila wakati. Vipindi vilivyoachwa na vilivyokataliwa ni bure.
Data ya uzalishaji inachakatwa na kuhifadhiwa katika Umoja wa Ulaya kwa chaguo-msingi, kwenye Amazon Web Services. Mikataba ya biashara inaweza kuomba maeneo mbadala kwa mamlaka ambazo wasimamizi wake wanahitaji.
Usimbaji fiche kila mahali. AES-256 wakati wa kupumzika kwenye kila database, hifadhi ya vitu, na backup. Transport Layer Security 1.3 wakati wa usafirishaji kwenye kila API call, webhook, na kipindi cha Business Console. Data ya kibayometriki imesimbwa kwa kutumia Customer Master Key tofauti.
Uhifadhi ni wako kudhibiti. Uhifadhi wa chaguo-msingi ni usio na kikomo (unlimited) isipokuwa ukisanidi muda mfupi zaidi, kati ya siku 30 na miaka 10 kwa kila programu, na unaweza kufuta kipindi chochote cha kibinafsi wakati wowote kutoka kwenye dashibodi au API.
Vyeti: SOC 2 Type 1 (ukaguzi wa Type 2 unaendelea), ISO/IEC 27001:2022, iBeta Level 1 PAD, na uthibitisho wa umma kutoka Tesoro / SEPBLAC / CNMV ya Hispania kwamba uhakiki wa utambulisho wa mbali wa Didit ni salama zaidi kuliko kumhakiki mtu ana kwa ana. Ripoti kamili inapatikana kwenye /security-compliance.
Didit inatii sheria kwa chaguo-msingi kwa wasimamizi muhimu kwa miundombinu ya utambulisho:
Memo ya kina, kila cheti, kila barua ya mdhibiti: /security-compliance.
Njia tatu za kuunganisha, chagua inayofaa stack yako:
Dashibodi sawa, bili sawa, bei sawa ya kulipa kwa mafanikio kwa zote tatu. Mwongozo wa hatua kwa hatua unapatikana kwenye docs.didit.me/integration/integration-prompt.
Kwa kila dai:
Takriban \$0.53 kwa dai lililochunguzwa kikamilifu. Uhakiki 500 wa kwanza kila mwezi ni bure kwenye kila akaunti, jaribu mchakato ndani ya kiwango cha bure.
Hakuna viwango vya chini, hakuna ahadi ya kila mwaka, hakuna bei kwa kila kiti.
Webhook iliyosainiwa ndiyo ishara ya kuelekeza. Kwenye status: In Review, back-end yako inaelekeza kesi kwa Special Investigations Unit (SIU) na ishara za kila moduli + orodha ya kulinganisha uso kama faili ya ufunguzi wa kesi.
Vuta mzigo kamili wa uamuzi kupitia GET /v3/session/[id]/decision/ kwa mchambuzi, alama za kufanana kwa uso, orodha ya AML hit na orodha ya chanzo kwa kila kulinganisha, orodha ya wagombea wa utafutaji wa uso na alama, matokeo ya document forensics. Mzigo wa uamuzi ndio rekodi ya ukaguzi kwa mzozo wowote.
Biometric vectors ni data ya kategoria maalum chini ya General Data Protection Regulation (GDPR) ya EU. Msingi halali ni maslahi halali ya uchunguzi wa madai pamoja na mchakato wa idhini mwanzoni mwa kipindi.
Uhifadhi wa chaguo-msingi ni miaka 5 ya bima, rekebisha kwa kila mchakato ikiwa mamlaka yako au msimamizi wako ni tofauti. Nyumba ya sanaa ya Face Search 1:N imewekwa kwa akaunti yako kwa makusudi, hakuna utafutaji wa kuvuka mtoa huduma isipokuwa ujiunge na muungano na uendeshe workflow_id iliyoshirikiwa.
API moja kwa KYC, KYB, Ufuatiliaji wa Miamala, na Uchunguzi wa Wallet. Unganisha ndani ya dakika 5.