Accor - Plateforme d'agents de dev

An internal dev-agent platform, inside the AWS Accor perimeter.

dev-agents

~ ❯ agent run --from slack

✔ Request scoped from Slack and confirmed

✔ Context injected: design system, conventions, RAG

✔ Ephemeral runner started, agent on AWS Bedrock

✔ Code changed, tests and lint passing

✔ Merge request opened, waiting for a human review

Task cost tracked, under budget

Status
Internal project
Year
2026
Role
AI Engineer - design & implementation (Accor engagement)
Stack
  • AWS Bedrock
  • Agents
  • MCP
  • RAG
  • pgvector
  • Hono
  • pg-boss
  • Docker
  • Nuxt
  • TypeScript

Internal project: architecture and results shown without code or public link.

The context

Accor's web teams pile up mechanical tasks (migrations, dependency bumps, missing tests) and already have a headless agent and a model catalogue on Bedrock. The challenge: industrialize that into a governed platform, without any data leaving the AWS perimeter.

What I built

A multi-entry platform (Slack, GitLab issues, dashboard) wired to an orchestrator (Hono, pg-boss) that spins up ephemeral runners. Each runner runs an agent on Bedrock, leverages an MCP context server (design system, conventions, pgvector RAG) and opens a human-reviewed Merge Request. Costs and token budgets tracked to the cent.

Architecture

  1. 01RequestSlack, GitLab issue or dashboard, scoped then confirmed.
  2. 02OrchestratorQueue, priorities, budget and injected context.
  3. 03Runner + agentEphemeral container, agent on Bedrock, MCP server.
  4. 04Merge RequestTests passed, report attached, human review required.
  5. 05DashboardAcceptance rate, time saved and cost per MR.

Results & impact

  • Inference 100% within the AWS Accor perimeter (Bedrock), no data leaving.
  • A human always validates: agents open MRs, never merge.
  • Per-task costs tracked and token budgets capped with alerting.

Skills applied

  • Agents and orchestration
  • RAG and MCP
  • LLMOps and production

Got a project in mind?

An application to build, a team to strengthen or an AI product to launch: let's talk.