Collections response agent

Brex uses an agent to personalize delinquent-account outreach and help its servicing team respond to customers.

Company: Brex
Approach type: Agent
Work: Finance ops
Human involvement: Drafts reviewed
Deployment stage: Deployed
Evidence strength: Limited primary
Entry reviewed: 2026-09-17

Copy as MD Ask ChatGPT

How it works

customer reply → draft selected or edited by servicing staff.

Start outreach

Initial outreach uses an automated personalized template.^{[Source 1]}

Analyze the reply

The agent combines the customer response with account context and negotiating guidelines.^{[Source 1]}

Prepare response options

Servicing staff select, customize or send proposed drafts with different tones.^{[Source 1]}

Where people stay involved

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

Supervision level
Work-product review
A person reviews the draft or implementation.
Level 3 of 5
- customer reply → draft selected or edited by servicing staff^{[Source 1]}

How supervision levels work

Implementation details

Model: Not reported
Harness: Not reported
Sandbox: Not reported
Tool access: Not reported
Knowledge: Account context, servicing procedures and negotiating guidelines.^{[Source 1]}
Context management: Not reported
Credentials: Not reported
Interfaces: Not reported

Validation and failure handling

Not reported: The available sources do not describe how the team checks the output.

Reported observations

Not reported

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 Collections response agent at Brex.

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

Agent, Human, Ops: How Brex Is Changing Roles and Workflowshttps://www.firstround.com/ai/brexCase study · Independent secondary · Last source verification: 2026-08-31
Preserved copy

Question coverage and scope

purpose: Reported
workflow: Reported
human involvement: Reported
implementation: Reported
validation: Not reported
observations: Not 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.
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: delinquent account servicing
Knowledge
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: delinquent account servicing
Start outreach
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: delinquent account servicing
Analyze the reply
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: delinquent account servicing
Prepare response options
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: delinquent account servicing
Operating model assessment
Statement type
Inference
Provenance
Catalog judgment
Confidence
Medium
Confidence reason
The follow-up response workflow returns options to the servicing team to select, edit or send. Initial automated outreach is a separate step.
Observation date
2025-09-25
- SupportsAgent, Human, Ops: How Brex Is Changing Roles and WorkflowsSubjective judgement: staff pick a proposed draft and customize or send it