Onboarding decision system

Brex’s onboarding system verifies applicants and synthesizes KYC and underwriting evidence into decisions for its operations team.

Company: Brex
Approach type: Agent
Work: Finance ops
Human involvement: Autonomous
Invocation: Event-driven
Deployment stage: Deployed
Evidence strength: Detailed primary
Entry reviewed: 2026-09-17

Copy as MD Ask ChatGPT

How it works

customer application → onboarding decision or analyst escalation.

Gather evidence

Specialists segment businesses, verify documents and identity, and reconstruct financial profiles.^{[Source 1]}

Decide or escalate

A decision agent combines policy, evidence and confidence; uncertain cases go to analysts.^{[Source 1]}

Where people stay involved

People review, approve, or guide the agent’s work here.

Supervision level
Exception-only
A person returns when the system raises an exception.
Level 5 of 5
- customer application → onboarding decision or analyst escalation^{[Source 1]}

How supervision levels work

Implementation details

Model: Not reported
Harness: Specialists exchange structured claims, evidence and confidence.^{[Source 1]}
Sandbox: Not reported
Tool access: Not reported
Knowledge: Documented analyst judgment and Brex onboarding policies.^{[Source 1]}
Context management: Not reported
Credentials: Not reported
Interfaces: Not reported

Validation and failure handling

Evaluate decisions

Brex benchmarks agents against re-reviewed, labeled historical applications.^{[Source 1]}

Reported observations

These results come from the sources. Notes below each result explain what it covers and any reported limits.

Key observation

Brex reports card-application auto-approval rose from 0% to 40% in weeks.^{[Source 1]}

Reported by: Brex
Scope: Onboarding decision system: Brex reports card-application auto-approval rose from 0% to 40% in weeks.

The source does not report the denominator of this figure.

About this result

Category: Adoption output
Evidence type: Reported measurement
What it covers: Onboarding decision system: Brex reports card-application auto-approval rose from 0% to 40% in weeks.

Lessons

Not reported: The available sources do not report lessons from this work.

Back to agents

Improve this record

Give your coding agent the context and instructions to prepare a source-backed update.

Suggest on GitHub

Paste the prompt into your coding agent, then describe the correction or add a public source.

Preview prompt

Help me update the Internal Agents Map record for Onboarding decision system at Brex.

Repository: https://github.com/steel-experiments/internal-agents-map
Record: data/agents/brex-onboarding.yaml
Published record: https://internal-agents.com/agents/brex-onboarding
Readable context: https://internal-agents.com/agents/brex-onboarding.md

Use the correction or public source I provide in this conversation. If I have not supplied either, ask what I want changed before editing.

Use an existing checkout of this repository, or clone it if needed. Read the current record from the repository. Follow AGENTS.md, CONTRIBUTING.md, and the relevant instructions in data/schema.md.

Verify that the evidence supports the requested change. Preserve uncertainty and distinguish reported facts from catalog judgments. Follow the repository process for capturing new sources. If evidence is insufficient, explain the gap instead of inventing details.

Make a focused change on a branch. Regenerate derived files and run the required checks. Do not edit generated content by hand.

Show me the change, supporting evidence, and check results, including any checks you could not run. Ask whether to submit a pull request unless I already requested one. Do not merge the pull request. If you cannot edit the repository, prepare a source-backed issue draft.

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

The end of the trade-off: How AI agents broke the onboarding trilemmahttps://www.brex.com/journal/rebuilding-onboarding-ai-nativeEngineering blog · First party · Last source verification: 2026-09-17
Preserved copy

Question coverage and scope

purpose: Reported
workflow: Reported
human involvement: Reported
implementation: Reported
validation: Reported
observations: Reported
lessons: Not reported

Research details for every claim on this page

Summary
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale; How the onboarding agents work together
Harness
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale; How the onboarding agents work together
Knowledge
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale; How the onboarding agents work together
Gather evidence
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale; How the onboarding agents work together
Decide or escalate
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale; How the onboarding agents work together
Evaluate decisions
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaEncoding human judgment at scale: historical cases re-reviewed and labeled as the benchmark
Key observation
Statement type
Metric
Provenance
Reported
Confidence
Medium
Confidence reason
Self-reported by the source; no independent verification.
Reported by
Brex
Scope
Onboarding decision system: Brex reports card-application auto-approval rose from 0% to 40% in weeks.
Denominator
Not reported
Method
Not reported
Observation date
Not reported
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaWhat we learned: SME and builder partnership raised card-application auto-approval from 0% to 40% in weeks
Operating model assessment
Statement type
Inference
Provenance
Catalog judgment
Confidence
Medium
Confidence reason
Brex explicitly distinguishes instant high-confidence decisions from uncertain cases escalated to analysts.
Observation date
2026-01-20
- SupportsThe end of the trade-off: How AI agents broke the onboarding trilemmaHow the onboarding agents work together: Decision agent makes high-confidence decisions and escalates below-threshold cases