1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl
Chi tiết nguồn
<p>When hundreds of agents serve thousands of developers, enterprise governance can’t be an afterthought.</p> <p>At the BMW Group’s R&D, more than 12,500 developers work on approximately 500 million lines of vehicle software code. This software is augmented by the BMW Connected Vehicle backend, a cloud-based system of more than 1,300 microservices providing digital services for 24 million vehicles in the field. In regulated industry, the bar for (software) quality, stability, and governance compliance is exceptionally high.</p> <p>While research, frameworks, and guidelines now facilitate building agents, industrializing and operating high-quality agents in an efficient, scalable manner remains a significant challenge.</p> <p>Scaling agentic AI across a large organization cannot be achieved by isolated teams. It requires collective effort, locally driven experimentation, and active knowledge sharing across the enterprise. This creates a fundamental governance dichotomy: Development teams need the freedom to innovate rapidly, while the enterprise must enforce standards for safety, security, composability, and cost-efficiency. Without that balance, organizations risk a fragmented landscape of AI islands and costly duplicate work. This presents a real challenge given hundreds of globally distributed teams building agents across the BMW Group.</p> <p>In this post, we detail the practices and patterns that support BMW’s R&D teams in building, governing and operating agents at scale without sacrificing speed, quality or compliance.</p> <h2 id="solution">Solution</h2> <p>Our premise is straightforward: build agents that can cooperate from the start. This requires an architecture that makes diversity composable, governable, and automatable, without requiring a single framework or toolchain.</p> <p>Central to this architecture is the agent harness, a runtime layer wrapped around a large language model (LLM). It provides the execution loop, tool dispatch, memory management, and observability hooks for autonomous operation.</p> <p>Just as the <a href="https://aws.amazon.com/architecture/well-architected/" target="_blank" rel="noopener">AWS Well-Architected Framework</a> standardized cloud infrastructure design, agentic systems need equivalent patterns, reusable blueprints encoding governance, composability, and operational best practices from the start.</p> <p>We organize our solution around five interlocking practices, drawn from hands-on experience building and operating agentic systems at enterprise scale since 2023. Each practice is codified as infrastructure as code (IaC), making adoption repeatable, auditable, and enforceable across teams without blocking DevOps velocity.</p> <h3 id="govern-proactively-not-retroactively">Govern proactively, not retroactively</h3> <p>Governance must be structural from the start and maintained across the full lifecycle. We advocate for three properties of effective agentic governance:</p> <p><strong>Framework-agnostic and externalized:</strong> Governance rules such as authentication, authorization, rate limiting and content filtering are enforced at the integration layer. This includes a Model Context Protocol (MCP) gateway, a central agent registry and orchestration boundary, rather than within individual agent codebases. This means governance survives framework migrations, model swaps, and team reorganizations.</p> <p><strong>Domain-sensitive and graduated:</strong> Not every agent action carries the same risk: drafting documentation, updating customer records, and production database writes demand very different levels of oversight. We implement graduated trust through per-step autonomy levels:</p> <ul> <li><strong>Level 0 (Human-in-the-loop):</strong> Every action requires explicit human approval. This is the starting point for new agents and high-risk operations.</li> <li><strong>Level 1 (Human-on-the-loop):</strong> The agent executes autonomously but surfaces decisions for asynchronous human review. Suitable for medium-risk tasks with defined inputs, outputs, and rollback options.</li> <li><strong>Level 2 (Autonomous within guardrails):</strong> The agent operates independently within strictly defined policy boundaries, enforced deterministically rather than through prompt instructions (see below). Reserved for low-risk, well-understood operations with verified track records.</li> </ul> <p>Assign trust levels per step, not per agent. A single workflow can include steps at all three levels, so teams can start conservatively and incrementally increase autonomy as confidence builds, grounded in measurable evaluation data, not assumptions.</p> <p><strong>Deterministically enforced:</strong> Governance runs as deterministic code outside the agent’s reasoning loop. In practice, this happens mainly in the CI/CD pipeline. Permission checks, policy-as-code rules, and compliance validations gate every deployment there, before an agent reaches production. Because these checks run separately from the agent, neither the agent nor its prompts are in a position to override them. Egress controls (recipient allowlisting, outbound secret scanning) help prevent an agent holding confidential data from disclosing it through an otherwise legitimate call.</p> <h3 id="instrument-verify-and-evaluate-continuously">Instrument, verify, and evaluate continuously</h3> <p>Observability in agentic systems goes beyond traditional application monitoring. The real question is no longer whether a service returned an HTTP 200 status, but whether an agent produced a faithful, policy-compliant output, and how this can be demonstrated through observable execution traces. Answering that requires a ground-truth dataset covering common queries and edge cases. This dataset is used for evaluation from day one, so quality is measured against representative and appropriately governed evaluation datasets for evaluation, not synthetic prompts.</p> <p>This infrastructure cannot be retrofitted an