Source: https://internal-agents.com/agents/brex-agent-platform # Brex — Internal Agent Platform Brex built an internal platform in Retool where operations staff build, test and deploy agents for KYC checks, card disputes, support quality assurance and collections. A roughly 25-person systems engineering team maintains it, and analysts still review every case the agents do not handle with high confidence. > This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a platform. The record also reports a workflow. - Approach type: Platform - Deployment stage: Scaled - Autonomy: Human in loop - Evidence strength: Secondary only - Status: Internal - First reported year: 2025 - Work: Finance ops, Support, Customer success - Interfaces: Slack, Internal ui - Invocation: Interactive - Entry reviewed: 2026-09-15 ## Where people stay involved - **internal operations request → completed operation** — Continuous steering · Level 2 ## Overview ### Summary Brex built an internal platform in Retool where operations staff build, test and deploy agents for KYC checks, card disputes, support quality assurance and collections. A roughly 25-person systems engineering team maintains it, and analysts still review every case the agents do not handle with high confidence. Fact · Reported · Medium confidence · `brex-agent-platform--summary` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ## How it works ### Supporting component Non-technical ops staff design prompts, test across models, deploy with QA oversight Fact · Reported · Medium confidence · `brex-agent-platform--primitives-0` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Supporting component Product features exposed to internal agents through one MCP server Fact · Reported · Medium confidence · `brex-agent-platform--primitives-1` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ## Supervision evidence ### Operating model assessment Level 2 for internal operations request → completed operation; human attention boundary: continuous-steering. Inference · Catalog judgment · Medium confidence · `brex-agent-platform--operating-models-0` Confidence reason: The secondary report describes a human remaining in the middle of the workflow, but does not fully specify each review surface. Qualifications: - Observation date: 2025-09-25 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ## Implementation details ### Sandbox Retool-hosted runtime (no bespoke execution env described) Fact · Reported · Medium confidence · `brex-agent-platform--architecture-sandbox` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Harness Retool-based builder with prompt management and multi-model testing/evaluation; built by a ~25-person systems-engineering team Fact · Reported · Medium confidence · `brex-agent-platform--architecture-harness` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Model Multi-model Fact · Reported · Medium confidence · `brex-agent-platform--architecture-model` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Interfaces slack, internal-ui Fact · Reported · Medium confidence · `brex-agent-platform--architecture-interfaces` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Tool access An MCP server exposes external product features to the internal platform; new product tools become internally available immediately; invoked via Slack /c1 Fact · Reported · Medium confidence · `brex-agent-platform--architecture-tool-access` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Knowledge Standard operating procedures uploaded as a knowledge base, such as 100-page dispute guides; customer account data Fact · Reported · Medium confidence · `brex-agent-platform--architecture-knowledge` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Credentials SSO via internal Retool proxies (no per-user accounts); ConductorOne access management; Okta auth; data classified by risk; ≤30-day retention, no training on inputs Fact · Reported · Medium confidence · `brex-agent-platform--architecture-credentials` Confidence reason: A linked participant or independent source reports the claim. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ## Reported metrics ### Headline claim Dispute processing time fell from three hours to three seconds Metric · Reported · Medium confidence · `brex-agent-platform--headline-metric` Confidence reason: A linked participant or independent source reports the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Brex - Scope: Dispute-submission preparation using the internal agent platform; not end-to-end chargeback resolution - Observation date: 2025 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) · Preserved content.md, lines 179–189 ### Key observation 50%+ of customer-support cases resolved by chatbot as first touch Metric · Reported · Medium confidence · `brex-agent-platform--key-metrics-0` Confidence reason: A linked participant or independent source reports the claim. Qualifications: - Reported by: Brex - Scope: Customer-support cases resolved by the chatbot at first touch - Denominator: Customer-support cases; exact sample size not provided - Observation date: 2025 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) · Preserved content.md, lines 76 ### Key observation Dispute processing: 3 hours → 3 seconds Metric · Reported · Medium confidence · `brex-agent-platform--key-metrics-1` Confidence reason: A linked participant or independent source reports the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Brex - Scope: Dispute-submission preparation using the internal agent platform; not end-to-end chargeback resolution - Observation date: 2025 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) · Preserved content.md, lines 179–189 ### Key observation QA covers every support interaction; one person using AI instead of five QA specialists Metric · Reported · Medium confidence · `brex-agent-platform--key-metrics-2` Confidence reason: A linked participant or independent source reports the claim. Qualifications: - Reported by: Brex - Scope: Quality assurance of customer-support interactions - Denominator: Every support interaction - Method: Agent applies the quality rubric to every response; one person oversees instead of five QA specialists - Observation date: 2025 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) · Preserved content.md, lines 80 ### Key observation KYC adverse-media accuracy 85% → 88% Metric · Reported · Medium confidence · `brex-agent-platform--key-metrics-3` Confidence reason: A linked participant or independent source reports the claim. Qualifications: - The source does not report the denominator of this figure. - Reported by: Brex - Scope: KYC adverse-media classification; human versus agent accuracy - Observation date: 2025 Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) · Preserved content.md, lines 163–167 ## Lessons and interpretation ### Lesson Target 40% automation, not 100%; the last mile drives investments that often yield zero value Inference · Catalog judgment · Medium confidence · `brex-agent-platform--lessons-learned-0` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Lesson Brex reports that it manages the internal platform with practices used for an external product Inference · Catalog judgment · Medium confidence · `brex-agent-platform--lessons-learned-1` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Lesson Don't skip the human in the middle; end-to-end automation fails on accuracy Inference · Catalog judgment · Medium confidence · `brex-agent-platform--lessons-learned-2` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Lesson Map workflows to the discrete steps a human would take, then translate each to LLM instructions Inference · Catalog judgment · Medium confidence · `brex-agent-platform--lessons-learned-3` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ### Lesson Architecture beats vendor; legal/data approvals should follow data-handling characteristics, not the tool name Inference · Catalog judgment · Medium confidence · `brex-agent-platform--lessons-learned-4` Confidence reason: The catalog derives this observation from the linked sources. Evidence: - Supports · [1] [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/brex-agent-platform-source-1/content.md) ## Sources 1. [Agent, Human, Ops: How Brex Is Changing Roles and Workflows](https://www.firstround.com/ai/brex) - Case study · Independent secondary · Evidence - Original URL: - Published: 2025-09-25 · Accessed: 2026-08-12 · Last verified: 2026-08-31 - Preserved copy in the repository: