Skip to content

Rank #2 of 5 in Expense Management

Brex logo

Brex Inc. (a Capital One company) · commercial

no public signals

Showcase

Brex homepage screenshot
homepage · captured Sep 2026 · view live ↗
Brex docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with Brex 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://platform.brexapis.com/v2/transactions/card/primary | head -1 # the documented platform API, keyless → 401recorded session — replayed, not live
recorded 2026-09-14 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

By theme — the product's score on each story themeBy theme

Accounting close — stories about accounting close in this arenaAccounting closeevidence →

Stories about accounting close in this arena

28.0/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

46.0/100

Ai automation — stories about ai automation in this arenaAi automationevidence →

Stories about ai automation in this arena

61.0/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

40.3/100

Bills ap — stories about bills ap in this arenaBills apevidence →

Stories about bills ap in this arena

80.0/100

Cards controls — stories about cards controls in this arenaCards controlsevidence →

Stories about cards controls in this arena

73.8/100

Expense data access — stories about expense data access in this arenaExpense data accessevidence →

Stories about expense data access in this arena

35.3/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

26.4/100

Policy approvals — stories about policy approvals in this arenaPolicy approvalsevidence →

Stories about policy approvals in this arena

53.1/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Receipts capture — stories about receipts capture in this arenaReceipts captureevidence →

Stories about receipts capture in this arena

25.7/100

Reimbursements — stories about reimbursements in this arenaReimbursementsevidence →

Stories about reimbursements in this arena

18.0/100

Spend visibility — stories about spend visibility in this arenaSpend visibilityevidence →

Stories about spend visibility in this arena

74.0/100

Travel — stories about travel in this arenaTravelevidence →

Stories about travel in this arena

63.3/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full7/10C

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10C

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial7/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1noneuntestednone yet

Codify our expense policy — limits by category, role, and context — so in-policy expenses auto-approve and only exceptions reach a human C

Policy engine

finance leadPolicy approvals — stories about policy approvals in this arenaPolicy approvals3full8/10C

Issue physical and virtual corporate cards to the team in minutes, each with its own spend limit C

Card issuance

founderCards controls — stories about cards controls in this arenaCards controls3full8/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial7/10C

Pull transactions, expenses, and receipts through a documented REST API with OAuth and scoped tokens C

Api access

developerExpense data access — stories about expense data access in this arenaExpense data access3partial7/10T

Restrict cards by category, merchant, and amount — and the platform auto-locks or declines out-of-policy spend at the point of sale C

Card controls

finance leadCards controls — stories about cards controls in this arenaCards controls3full7/10C

See company spend in real time — by team, category, and merchant — the day it happens, not when statements land C

Dashboards

founderSpend visibility — stories about spend visibility in this arenaSpend visibility3full7/10C

An agent can pull uncoded transactions via API or MCP, propose categorizations and policy flags, and push clean coding back for review C

Agent access

ai-native userExpense data access — stories about expense data access in this arenaExpense data access3partial6/10T

Snap a photo or forward an email and the platform OCRs the receipt and files it against the right transaction C

Receipt capture

employeeReceipts capture — stories about receipts capture in this arenaReceipts capture3partial6/10C

Submit an out-of-pocket expense and get reimbursed by direct deposit in days, tracked from submission to payout C

Domestic

employeeReimbursements — stories about reimbursements in this arenaReimbursements3partial5/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial4/10C

Transactions sync to QuickBooks, NetSuite, or Xero with GL account, class, and department mappings I control C

Accounting sync

finance leadAccounting close — stories about accounting close in this arenaAccounting close3none0/10

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3n/auntestednone yet

AI codes and audits expenses for me — reading receipts, suggesting categories and memos, and catching duplicates or fraud C

Ai coding

ai-native userAi automation — stories about ai automation in this arenaAi automation2full8/10C

Allocate budgets to teams and projects and have card limits and approvals actually enforce them C

Budgets

finance leadSpend visibility — stories about spend visibility in this arenaSpend visibility2full8/10C

Book flights and hotels in-platform with travel policy applied at booking time, not expensed and argued about later C

Booking

employeeTravel — stories about travel in this arenaTravel2full8/10X

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2full8/10C

Run accounts payable in the same platform — capture invoices, route approvals, and pay vendors by ACH, check, or wire C

Bill pay

finance leadBills ap — stories about bills ap in this arenaBills ap2full8/10C

Spend is coded as it happens — merchant, category, memo, receipt — so month-end close is a review, not an archaeology dig C

Close

finance leadAccounting close — stories about accounting close in this arenaAccounting close2full8/10C

An AI assistant enforces policy conversationally — chasing missing receipts, explaining declines, and answering "can I expense this?" before the spend happens C

Ai policy

ai-native userAi automation — stories about ai automation in this arenaAi automation2partial7/10C

Create single-vendor virtual cards for SaaS subscriptions and procurement so one compromised vendor never exposes shared credit C

Virtual cards

finance leadCards controls — stories about cards controls in this arenaCards controls2full7/10C

Every expense carries a full audit trail — edits, approvals, policy checks — that survives an external audit C

Audit trail

finance leadPolicy approvals — stories about policy approvals in this arenaPolicy approvals2partial6/10C

Receipts match to card transactions automatically — with e-receipts pulled from integrations — and I get nudged only when one is genuinely missing C

Receipt matching

employeeReceipts capture — stories about receipts capture in this arenaReceipts capture2partial6/10C

Build multi-step approval chains — manager, budget owner, finance — with delegation and escalation when approvers sit on requests C

Approvals

finance leadPolicy approvals — stories about policy approvals in this arenaPolicy approvals2partial5/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial5/10T

Issue and manage cards programmatically — create a card with a limit, lock it, update controls — via the public API C

Card api

developerExpense data access — stories about expense data access in this arenaExpense data access2partial4/10C

Run multiple legal entities and currencies in one account with consolidated reporting and per-entity books C

Multi entity

finance leadAccounting close — stories about accounting close in this arenaAccounting close2partial3/10C

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial3/10C

Log mileage with map-based distance and claim per-diem rates without building the expense by hand C

Mileage perdiem

employeeReceipts capture — stories about receipts capture in this arenaReceipts capture2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2n/auntestednone yet

Reimburse employees abroad in their local currency without running a separate international payments process C

International

finance leadReimbursements — stories about reimbursements in this arenaReimbursements2noneuntestednone yet

A trip's expenses — bookings, cards, receipts — collect themselves into one itinerary-linked report C

Trip expenses

employeeTravel — stories about travel in this arenaTravel1partial5/10C

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 32 stories with headroom

What would move Brex’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.

  1. 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

    Evidence only shows Brex publishing its own MCP server so external AI assistants can call Brex's tools (docs-3, docs-24, probe-3) — the reverse of this story, which asks whether Brex can consume/plug in external MCP servers to use their tools.

  2. Accounting close — stories about accounting close in this arenaTransactions sync to QuickBooks, NetSuite, or Xero with GL account, class, and department mappings I control

    nonemoves PA Scoreimpact 30

    The evidence pack shows Brex has a one-click accounting sync feature, but it is documented only as syncing to Puzzle (brex-docs-17, 18, 40), with no mention of QuickBooks, NetSuite, or Xero, nor any documentation of finance-lead-controlled GL account, class, or department mapping for such syncs.

  3. Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models

    nonemoves PA Scoreimpact 30

    No evidence pack item addresses AI training data usage, opt-out settings, or a data-privacy policy regarding model training; the evidence only covers API/product features and unrelated community complaints about account closures.

  4. Agenticness — how well agents can access and operate the productUse an official CLI

    nonemoves agent-readyimpact 30

    Evidence pack shows Brex's developer platform (APIs, Postman collection, MCP server, Zapier/Pipedream/Workato integrations) but no mention of an official CLI tool anywhere in docs or changelog.

  5. Agenticness — how well agents can access and operate the productBuild against official SDKs

    nonemoves agent-readyimpact 30

    Brex documents REST APIs (OpenAPI specs), authentication, webhooks, a Postman workspace, and third-party integrations (Pipedream, Zapier, Workato), but nowhere in the evidence pack is there mention of official client-library SDKs (e.g., Node.js, Python, Java packages) that AI-native developers could build against.

  6. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    The evidence shows a changelog tracking feature additions (e.g., new filter params, policy fields) but nothing documenting API versioning scheme or a deprecation policy for breaking changes.

  7. Reimbursements — stories about reimbursements in this arenaReimburse employees abroad in their local currency without running a separate international payments process

    nonemoves PA Scoreimpact 20

    Evidence covers global card acceptance (210+ countries), bill pay wires 'in more currencies' for vendor payments, and general 'global spend' messaging, but nothing specifically addresses reimbursing employees abroad in their local currency or eliminating a separate international payments process for reimbursements.

  8. Receipts capture — stories about receipts capture in this arenaLog mileage with map-based distance and claim per-diem rates without building the expense by hand

    nonemoves PA Scoreimpact 20

    No evidence in the pack mentions mileage tracking, GPS/map-based distance calculation, or per-diem rate claims; Brex's expense documentation focuses on card transactions, receipt upload/matching, and policy enforcement but never describes mileage or per-diem automation.

Showing the top 8 of 32 — 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 map10 surfaces · 38 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

Openapi docs25 stories

Product docs20 stories

AI docs16 stories

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://platform.brexapis.com/v2/transactions/card/primary | head -1 # the documented platform API, keyless → 401reproduced
$ curl -si https://platform.brexapis.com/v2/transactions/card/primary | head -1  # the documented platform API, [redacted]less → 401
HTTP/2 401
$curl -si -X POST https://api.brex.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>' # Brex's hosted MCP server, keyless → OAuth challengereproduced
$ curl -si -X POST https://api.brex.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'  # Brex's hosted MCP server, [redacted]less → OAuth challenge
HTTP/2 401

www-authenticate: Bearer realm="api", error="invalid_[redacted]", error_description="Missing or invalid Authorization header", authorization_uri="https://accounts-api.brex.com/oauth2/default/v1/authorize", resource_metadata="https://api.brex.com/.well-known/oauth-protected-resource/mcp"
$curl -s https://developer.brex.com/_bundle/openapi/expenses_api.yaml | head -3 # published OpenAPI specreproduced
$ curl -s https://developer.brex.com/_bundle/openapi/expenses_api.yaml | head -3  # published OpenAPI spec
openapi: 3.0.1
info:
  title: Expenses API
$curl -sL https://www.brex.com/llms.txt | head -3reproduced
$ curl -sL https://www.brex.com/llms.txt | head -3
# LLM documentation for Brex

Brex is an AI-powered financial platform providing corporate credit cards, expense management, bill pay, and business banking for modern companies. Use the following documentation to understand Brex's capabilities and find relevant information for business financial operations.

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 16 testable claims verified · 1 contradictedintegrity 19/100

22 distinct capability claims found in Brex’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

10

Unverified

1

Contradicted

23

Undersold

Verified (5)
Unverified (16)
Contradicted (1)
Undersold (23)
Claims outside our story set (1)

Real capability claims found in Brex’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.

  • Card can be managed from a mobile app, including Apple Pay, cancellation, and spend viewing

    source ↗
Suggest a story for these →

Business model

free-tierinterchangesubscription-per-seatenterprise-custom

Essentials is free and interchange-funded; Premium is $12/user/mo; Enterprise is custom — still sold standalone under the Brex brand since Capital One's April 2026 acquisition.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score30 (Sep 14 '26)38 (Sep 15 '26)
Agent-ready46 (Sep 14 '26)49 (Sep 15 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

Data