Access
Install
npm install @unit-finance/unit-node-sdkTry itExperimental
See what an agent can do with Unit before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -si https://api.s.unit.sh/accounts | head -3 # keyless → 401 (application/vnd.api+json)recorded session — replayed, not liveVerified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Account provisioning — stories about account provisioning in this arenaAccount provisioningevidence →
Stories about account provisioning in this arena
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Banking agent access — stories about banking agent access in this arenaBanking agent accessevidence →
Stories about banking agent access in this arena
Banking cards — stories about banking cards in this arenaBanking cardsevidence →
Stories about banking cards in this arena
Banking ledger — stories about banking ledger in this arenaBanking ledgerevidence →
Stories about banking ledger in this arena
Banking onboarding — stories about banking onboarding in this arenaBanking onboardingevidence →
Stories about banking onboarding in this arena
Banking risk controls — stories about banking risk controls in this arenaBanking risk controlsevidence →
Stories about banking risk controls in this arena
Money movement — stories about money movement in this arenaMoney movementevidence →
Stories about money movement in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Sponsor model — stories about sponsor model in this arenaSponsor modelevidence →
Stories about sponsor model in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Unit stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Account provisioning — stories about account provisioning in this arenaAccount provisioning
Stories about account provisioning in this arena
Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launch
~4/10
The account structure is transparent — whether funds sit in FBO pools or individual accounts, where FDIC insurance actually attaches, and who can see the ledger, all documented plainly
~4/10
Issue unique account and routing numbers at scale — virtual accounts for reconciliation, per-customer collection accounts, and sub-accounts under a master structure
~5/10
Idle balances can earn — interest-bearing accounts or documented sweep options, with the rate mechanics and who keeps the spread spelled out
—–
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
~5/10
unlocks → Webhooks · Official SDKs · Scoped API keys · MCP server · Machine-readable spec · Versioning policy · API sandbox · Official CLI · Headless / CI · Full data export · An agent can operate an account within policy — scoped credentials that let it read balances and initiate transfers under amount caps and counterparty allowlists, a use the vendor documents by name · The product ships its own AI for banking operations — natural-language search over transactions, drafted responses to disputes and alerts, anomaly summaries — built in, not bolted on
Subscribe to events via webhooks
—–
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
—–
Connect an agent via an official MCP server
—0/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
—0/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
n/an/a
Operate the product with natural-language commands
—–
Plug MCP servers into this product so it can use their tools
—–
Get AI-generated insights and suggestions from my data inside the product
—0/10
Set up automations that run autonomously in the background
—–
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Banking agent access — stories about banking agent access in this arenaBanking agent access
Stories about banking agent access in this arena
An agent can operate an account within policy — scoped credentials that let it read balances and initiate transfers under amount caps and counterparty allowlists, a use the vendor documents by name
—–
An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboard
~5/10
The product ships its own AI for banking operations — natural-language search over transactions, drafted responses to disputes and alerts, anomaly summaries — built in, not bolted on
—–
Banking cards — stories about banking cards in this arenaBanking cards
Stories about banking cards in this arena
Accounts come with cards — issue virtual and physical debit cards tied to the account through the same API, with spend controls and digital wallet support
~6/10
Card and ACH disputes are handled properly — Reg E investigation timelines, provisional credit mechanics, and my operational responsibilities documented and tooled
—–
Banking ledger — stories about banking ledger in this arenaBanking ledger
Stories about banking ledger in this arena
The ledger is real-time and event-driven — balance reads that reflect holds and pending activity, and webhooks for every transaction state change so my system mirrors the bank exactly
~3/10
Transaction data is rich enough to build on — counterparty details, rail-specific metadata, stable identifiers, and enrichment that makes a raw bank feed usable in-product
~4/10
The paper obligations are automated — monthly statements generated per account, and tax documents (1099-INT) produced and retrievable through the API
—–
Banking onboarding — stories about banking onboarding in this arenaBanking onboarding
Stories about banking onboarding in this arena
Customer verification is programmatic — KYC for individuals and KYB for businesses with document collection, watchlist screening, and clearly modeled application states
—0/10
Work the onboarding queue — see why an application is pending, supply additional documents, and understand which decisions are mine versus the bank's
—–
Banking risk controls — stories about banking risk controls in this arenaBanking risk controls
Stories about banking risk controls in this arena
Set risk controls per account and per program — transaction and velocity limits, holds on suspicious activity, and account freezes with documented reinstatement paths
—0/10
Fraud economics are explicit — who eats ACH return fraud, card disputes, and account takeover losses, with the platform's prevention tooling documented alongside the liability split
—–
Growth doesn't hit invisible walls — program-level limits, approval stages, and the path to raising them are documented rather than discovered in an email from the bank
—–
Money movement — stories about money movement in this arenaMoney movement
Stories about money movement in this arena
Originate ACH through the API — credits and debits, same-day windows, and the unhappy paths (returns, NOCs, reversals) modeled as first-class objects with webhooks
~3/10
Checks still work — programmatic check issuance and check deposit with image capture, because real businesses still receive and send paper
~3/10
The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documented
~4/10
Money can cross borders — international wires or SWIFT, FX with transparent rates, and the coverage map of currencies and corridors documented
~3/10
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Sponsor model — stories about sponsor model in this arenaSponsor model
Stories about sponsor model in this arena
Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform fails
~3/10
The compliance workload is tooled — transaction monitoring, sanctions screening, case management for alerts, and SAR-filing support with a clear split of duties between me, the platform, and the bank
—0/10
The platform ledger reconciles to the bank core — documented daily reconciliation between what the API reports and what the bank holds, the failure that sank Synapse-era programs
—–
Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 5/10 | Tprobed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | untested | none yet | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | untested | none yet | |
Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launch C Account opening | developer | Account provisioning — stories about account provisioning in this arenaAccount provisioning | 3 | partial | 4/10 | Tprobed | |
The account structure is transparent — whether funds sit in FBO pools or individual accounts, where FDIC insurance actually attaches, and who can see the ledger, all documented plainly C Fbo structures | finance lead | Account provisioning — stories about account provisioning in this arenaAccount provisioning | 3 | partial | 4/10 | Cclaimed | |
Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform fails C Charter clarity | founder | Sponsor model — stories about sponsor model in this arenaSponsor model | 3 | partial | 3/10 | Cclaimed | |
Originate ACH through the API — credits and debits, same-day windows, and the unhappy paths (returns, NOCs, reversals) modeled as first-class objects with webhooks C Ach | developer | Money movement — stories about money movement in this arenaMoney movement | 3 | partial | 3/10 | Cclaimed | |
The ledger is real-time and event-driven — balance reads that reflect holds and pending activity, and webhooks for every transaction state change so my system mirrors the bank exactly C Balances events | developer | Banking ledger — stories about banking ledger in this arenaBanking ledger | 3 | partial | 3/10 | Cclaimed | |
Customer verification is programmatic — KYC for individuals and KYB for businesses with document collection, watchlist screening, and clearly modeled application states C Kyc kyb | developer | Banking onboarding — stories about banking onboarding in this arenaBanking onboarding | 3 | none | 0/10 | ||
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
An agent can operate an account within policy — scoped credentials that let it read balances and initiate transfers under amount caps and counterparty allowlists, a use the vendor documents by name C Agent operations | ai-native user | Banking agent access — stories about banking agent access in this arenaBanking agent access | 3 | none | untested | none yet | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
The platform ledger reconciles to the bank core — documented daily reconciliation between what the API reports and what the bank holds, the failure that sank Synapse-era programs C Reconciliation | finance lead | Sponsor model — stories about sponsor model in this arenaSponsor model | 3 | none | untested | none yet | |
Accounts come with cards — issue virtual and physical debit cards tied to the account through the same API, with spend controls and digital wallet support C Card issuance | developer | Banking cards — stories about banking cards in this arenaBanking cards | 2 | partial | 6/10 | Cclaimed | |
An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboard C Agent visibility | ai-native user | Banking agent access — stories about banking agent access in this arenaBanking agent access | 2 | partial | 5/10 | Tprobed | |
Issue unique account and routing numbers at scale — virtual accounts for reconciliation, per-customer collection accounts, and sub-accounts under a master structure C Virtual accounts | developer | Account provisioning — stories about account provisioning in this arenaAccount provisioning | 2 | partial | 5/10 | Tprobed | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 4/10 | Tprobed | |
The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documented C Instant rails | developer | Money movement — stories about money movement in this arenaMoney movement | 2 | partial | 4/10 | Tprobed | |
Transaction data is rich enough to build on — counterparty details, rail-specific metadata, stable identifiers, and enrichment that makes a raw bank feed usable in-product C Data quality | developer | Banking ledger — stories about banking ledger in this arenaBanking ledger | 2 | partial | 4/10 | Cclaimed | |
Checks still work — programmatic check issuance and check deposit with image capture, because real businesses still receive and send paper C Checks | ops user | Money movement — stories about money movement in this arenaMoney movement | 2 | partial | 3/10 | Cclaimed | |
Money can cross borders — international wires or SWIFT, FX with transparent rates, and the coverage map of currencies and corridors documented C International | founder | Money movement — stories about money movement in this arenaMoney movement | 2 | partial | 3/10 | Cclaimed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | 0/10 | ||
Set risk controls per account and per program — transaction and velocity limits, holds on suspicious activity, and account freezes with documented reinstatement paths C Limits holds | ops user | Banking risk controls — stories about banking risk controls in this arenaBanking risk controls | 2 | none | 0/10 | ||
The compliance workload is tooled — transaction monitoring, sanctions screening, case management for alerts, and SAR-filing support with a clear split of duties between me, the platform, and the bank C Compliance tooling | ops user | Sponsor model — stories about sponsor model in this arenaSponsor model | 2 | none | 0/10 | ||
Card and ACH disputes are handled properly — Reg E investigation timelines, provisional credit mechanics, and my operational responsibilities documented and tooled C Disputes | ops user | Banking cards — stories about banking cards in this arenaBanking cards | 2 | none | untested | none yet | |
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Fraud economics are explicit — who eats ACH return fraud, card disputes, and account takeover losses, with the platform's prevention tooling documented alongside the liability split C Loss allocation | finance lead | Banking risk controls — stories about banking risk controls in this arenaBanking risk controls | 2 | none | untested | none yet | |
Growth doesn't hit invisible walls — program-level limits, approval stages, and the path to raising them are documented rather than discovered in an email from the bank C Program scaling | founder | Banking risk controls — stories about banking risk controls in this arenaBanking risk controls | 2 | none | untested | none yet | |
Idle balances can earn — interest-bearing accounts or documented sweep options, with the rate mechanics and who keeps the spread spelled out C Yield | finance lead | Account provisioning — stories about account provisioning in this arenaAccount provisioning | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | n/a | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
The paper obligations are automated — monthly statements generated per account, and tax documents (1099-INT) produced and retrievable through the API C Statements | ops user | Banking ledger — stories about banking ledger in this arenaBanking ledger | 2 | none | untested | none yet | |
The product ships its own AI for banking operations — natural-language search over transactions, drafted responses to disputes and alerts, anomaly summaries — built in, not bolted on C Builtin ai | ops user | Banking agent access — stories about banking agent access in this arenaBanking agent access | 2 | none | untested | none yet | |
Work the onboarding queue — see why an application is pending, supply additional documents, and understand which decisions are mine versus the bank's C Review queues | ops user | Banking onboarding — stories about banking onboarding in this arenaBanking onboarding | 2 | none | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | n/a | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 46 stories with headroom
What would move Unit’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
Unit is a banking-as-a-service/fintech infrastructure platform; no evidence of any MCP server support or integration for plugging tools into an AI agent.
Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server
nonemoves agent-readyimpact 45
Missing: any documentation of an MCP server, agent integration tooling, or even an OpenAPI spec that could underpin one.
Banking agent access — stories about banking agent access in this arenaAn agent can operate an account within policy — scoped credentials that let it read balances and initiate transfers under amount caps and counterparty allowlists, a use the vendor documents by name
nonemoves PA Scoreimpact 30
Unit's evidence describes general banking-as-a-service capabilities (accounts, payments, cards) but contains no mention of AI agents, scoped credentials, amount caps, counterparty allowlists, or any agent-specific access model named by the vendor.
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events
nonemoves PA Scoreimpact 30
Missing: any documentation of webhook/event subscription system, rule definition interface, or automated action triggers.
Banking onboarding — stories about banking onboarding in this arenaCustomer verification is programmatic — KYC for individuals and KYB for businesses with document collection, watchlist screening, and clearly modeled application states
nonemoves PA Scoreimpact 30
The evidence pack only vaguely references 'compliance' data access (unit-docs-5) but contains no specifics on programmatic KYC/KYB flows, document collection, watchlist screening, or modeled application states — capabilities Unit is known to offer but which are unevidenced here.
Sponsor model — stories about sponsor model in this arenaThe platform ledger reconciles to the bank core — documented daily reconciliation between what the API reports and what the bank holds, the failure that sank Synapse-era programs
nonemoves PA Scoreimpact 30
No evidence of documented daily reconciliation processes, ledger-to-bank-core matching, or any explicit reconciliation guarantee; evidence only covers general account/payment/card capabilities and real-time balances, not reconciliation controls addressing the Synapse-style failure mode.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
Missing: any documented export/download feature, open-format data export (CSV/JSON dumps), or portability/exit tooling.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
The evidence pack contains no mention of AI model training, data usage policies for AI, or opt-out mechanisms; Unit's documentation focuses entirely on banking infrastructure (accounts, payments, cards, credit).
Showing the top 8 of 46 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map4 surfaces · 15 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
llms.txt15 stories
- Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launch
- The account structure is transparent — whether funds sit in FBO pools or individual accounts, where FDIC insurance actually attaches, and who can see the ledger, all documented plainly
- Issue unique account and routing numbers at scale — virtual accounts for reconciliation, per-customer collection accounts, and sub-accounts under a master structure
- Point an agent at llms.txt or agent-oriented docs
- Drive the product through a documented public API
- An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboard
- Accounts come with cards — issue virtual and physical debit cards tied to the account through the same API, with spend controls and digital wallet support
- The ledger is real-time and event-driven — balance reads that reflect holds and pending activity, and webhooks for every transaction state change so my system mirrors the bank exactly
- Transaction data is rich enough to build on — counterparty details, rail-specific metadata, stable identifiers, and enrichment that makes a raw bank feed usable in-product
- Originate ACH through the API — credits and debits, same-day windows, and the unhappy paths (returns, NOCs, reversals) modeled as first-class objects with webhooks
- Checks still work — programmatic check issuance and check deposit with image capture, because real businesses still receive and send paper
- The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documented
- Money can cross borders — international wires or SWIFT, FX with transparent rates, and the coverage map of currencies and corridors documented
- Do everything through the API that I can do in the UI
- Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform fails
OpenAPI spec6 stories
- Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launch
- Point an agent at llms.txt or agent-oriented docs
- Drive the product through a documented public API
- An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboard
- The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documented
- Do everything through the API that I can do in the UI
docs5 stories
- Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launch
- Drive the product through a documented public API
- An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboard
- The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documented
- Do everything through the API that I can do in the UI
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -si https://api.s.unit.sh/accounts | head -3 # keyless → 401 (application/vnd.api+json)reproduced$ curl -si https://api.s.unit.sh/accounts | head -3 # [redacted]less → 401 (application/vnd.api+json) HTTP/2 401 date: Tue, 15 Sep 2026 09:12:27 GMT content-type: application/vnd.api+json; charset=utf-8
$curl -sL https://www.unit.co/llms.txt | head -3reproduced$ curl -sL https://www.unit.co/llms.txt | head -3 # Unit > **Unit is a financial infrastructure platform for technology companies that want to build products that let their customers store, move, spend, and borrow money inside their product.**
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
3 of 11 testable claims verified · 0 contradicted → integrity 27/100
16 distinct capability claims found in Unit’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
3
Verified
8
Unverified
0
Contradicted
4
Undersold
Verified (3)
“Support sub-accounts and multi-party fund flows under a master account structure”
Issue unique account and routing numbers at scale — virtual accounts for reconciliation, per-customer collection accounts, and sub-accounts under a master structurepartialproof ↗
“Send and receive domestic wires and real-time payments”
The faster rails are there when I need them — domestic wires, RTP, and FedNow origination and receipt through the same API, with per-rail capabilities documentedpartialproof ↗
“Dashboard and APIs expose customer, account, payment, card, transaction, compliance, and operational data”
Drive the product through a documented public APIpartialproof ↗
Unverified (11)
“Create deposit and wallet accounts held in FBO structures for various use cases”
The account structure is transparent — whether funds sit in FBO pools or individual accounts, where FDIC insurance actually attaches, and who can see the ledger, all documented plainlypartialproof ↗
“Real-time balances and transaction data for accounts”
The ledger is real-time and event-driven — balance reads that reflect holds and pending activity, and webhooks for every transaction state change so my system mirrors the bank exactlypartialproof ↗
“Originate ACH payments (credits and debits) through the API”
Originate ACH through the API — credits and debits, same-day windows, and the unhappy paths (returns, NOCs, reversals) modeled as first-class objects with webhookspartialproof ↗
“Issue and process paper checks”
Checks still work — programmatic check issuance and check deposit with image capture, because real businesses still receive and send paperpartialproof ↗
“Send and receive international payments”
Money can cross borders — international wires or SWIFT, FX with transparent rates, and the coverage map of currencies and corridors documentedpartialproof ↗
“Settlement-level visibility into transaction data across payment rails”
Transaction data is rich enough to build on — counterparty details, rail-specific metadata, stable identifiers, and enrichment that makes a raw bank feed usable in-productpartialproof ↗
“Issue physical and virtual cards with configurable controls and lifecycle management”
Accounts come with cards — issue virtual and physical debit cards tied to the account through the same API, with spend controls and digital wallet supportpartialproof ↗
“Real-time card authorization capabilities”
The ledger is real-time and event-driven — balance reads that reflect holds and pending activity, and webhooks for every transaction state change so my system mirrors the bank exactlypartialproof ↗
“Companies can work with one or multiple Unit bank partners through the same infrastructure”
Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform failspartialproof ↗
“Registered Federal Reserve service provider with direct connectivity to Fed systems for partner banks”
Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform failspartialproof ↗
“Direct, bare-metal access to the Federal Reserve, card networks, and bank partners”
Exactly who holds the charter — whether the platform is a bank, a direct program with a named partner bank, or middleware between me and someone else's sponsor — and what happens to my customers if the platform failspartialproof ↗
Undersold (4)
Open a real, insured deposit account through the API — application to active account fully programmatic, with sandbox parity so the flow is tested before launchpartialproof ↗
Point an agent at llms.txt or agent-oriented docsfullproof ↗
An agent can read the full banking picture — accounts, transactions, pending activity, documents — through a clean API or MCP surface without screen-scraping a dashboardpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Claims outside our story set (2)
Real capability claims found in Unit’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Build business capital and credit products: charge cards, revolving credit, lines of credit, merchant cash advances, invoice factoring, instant funds access”
source ↗“Offers Managed Solutions for Banking and Bill Pay for faster time to market with less operational ownership”
source ↗
Business model
Contact-sales only — no published pricing page; revenue comes from program fees plus interchange and deposit economics negotiated per program with the partner banks (Thread, Vantage, Lincoln Savings).
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
