--- schema: "swft.publication/v1" id: "company-linkedin-capt" title: "LinkedIn CAPT: turning company knowledge into executable agent playbooks" description: "How LinkedIn CAPT combines MCP tools, central and local playbooks, tool discovery, instrumentation, and Autopilot's verifier-driven ML workflow." summary: "LinkedIn's CAPT layer gives compatible agents safe access to internal systems and step-by-step company workflows. More than 1,000 engineers use it, according to LinkedIn. Autopilot for Torch adds a specialist proof loop that keeps generating and checking machine-learning code until it meets explicit production measures." canonical: "https://swft.io/companies/linkedin-capt" author: "SWFT Editorial" author_type: "Organization" published: "2026-09-01" modified: "2026-09-02" kind: "case-study" section: "Companies" tags: ["LinkedIn CAPT", "agent playbooks", "MCP tools", "organizational context", "Autopilot for Torch", "verifier loop"] evidence_labels: ["INFERENCE", "SELF-REPORT"] source_ids: ["linkedin-autopilot", "linkedin-capt"] authorship_disclosure: "AI-drafted from the cited public sources and independently checked by a second AI editorial-review agent (Codex) for source fit, claim boundaries, overlap, and reader utility. SWFT Editorial is responsible for corrections." --- # LinkedIn CAPT: turning company knowledge into executable agent playbooks LinkedIn gives existing agents approved internal tools and reusable playbooks, then uses verifier-driven loops for specialized production machine-learning work. > **Authorship:** AI-drafted from the cited public sources and independently checked by a second AI editorial-review agent (Codex) for source fit, claim boundaries, overlap, and reader utility. SWFT Editorial is responsible for corrections. ## Quick answer LinkedIn's CAPT layer gives compatible agents safe access to internal systems and step-by-step company workflows. More than 1,000 engineers use it, according to LinkedIn. Autopilot for Torch adds a specialist proof loop that keeps generating and checking machine-learning code until it meets explicit production measures. LinkedIn did not build another general coding model. It built CAPT, a company context and workflow layer that gives existing agents approved tools and step-by-step playbooks. A second system, Autopilot for Torch, shows how LinkedIn adds a strict verifier loop when the output must become production machine-learning code. ## What is LinkedIn CAPT? CAPT stands for Contextual Agent Playbooks & Tools. LinkedIn's [January 2026 account](https://www.linkedin.com/blog/engineering/ai/contextual-agent-playbooks-and-tools-how-linkedin-gave-ai-coding-agents-organizational-context) describes it as a framework that gives compatible agents access to internal code search, data platforms, observability, documents, tickets, and other approved systems through Model Context Protocol. The company says CAPT powers AI-assisted development for more than 1,000 engineers. It is distributed as a Python package and a local MCP server that editors can connect to automatically. LinkedIn's internal distribution updates it in the background, reducing setup work for individual teams. CAPT does not replace the agent. It supplies context, tools, authentication, and executable company knowledge that an off-the-shelf agent lacks. ## What is a LinkedIn agent playbook? A playbook is a named, reusable workflow with a purpose, inputs, file references, and ordered instructions. CAPT exposes it as a tool that an agent can discover and call. Playbooks can also call other tools, which lets a team compose a longer job from reviewed pieces. LinkedIn's experiment-cleanup example is concrete. When an A/B test ends, the workflow must read the result, find every related code path, remove the losing variant and stale flags, and verify that the winner is now the default across services. One playbook combines the experimentation APIs, code search, and cleanup instructions so engineers outside the specialist team can perform the work consistently. LinkedIn says the pattern also supports creating gRPC services, adding endpoints, debugging crashes, reviewing pull requests, querying data, and investigating production systems. ## How does LinkedIn organize company and team knowledge? Central playbooks cover broadly shared work, such as experimentation cleanup, common debugging, data analysis, review, and observability. Local playbooks live with a repository and describe work specific to that service. CAPT discovers both and presents one surface to the agent. LinkedIn initially grouped tools into namespaces, but engineers still had to predict which group they would need. It later put a few meta-tools in front of the larger catalog. The agent can search for tools by tag, inspect a tool's input shape, and invoke it without loading every tool definition into the prompt. The company instruments each tool and playbook call, including repository, success, and workflow identity. Those records help platform owners see which workflows are useful and which need stronger guardrails. The article does not publish an overall task success, acceptance, defect, or time-saved series. ## What is LinkedIn Autopilot for Torch? CAPT makes company knowledge executable. [Autopilot for Torch](https://www.linkedin.com/blog/engineering/ai/ai-helping-build-better-ai-how-agents-accelerate-model-experimentation) is a separate specialist factory for turning TensorFlow models into production-ready PyTorch models and for other machine-learning engineering work. Its proof loop is generate, score, hint, and regenerate. The verifier checks whether the model trains, produces stable numbers, preserves source behavior, matches the expected structure, fits LinkedIn's platform, and reaches the relevant quality or performance metric. A failure returns typed, prioritized guidance rather than a vague rejection. Once a result clears the gates, LinkedIn validates it on development GPU pods and promotes it through Flyte workflows. A tracking console shows conversions, iterations, scores, training jobs, workflow errors, pull requests, and generated artifacts. LinkedIn reports that generated PyTorch code performed strongly on more than 100 public OpenML tasks, that internal teams use generated code as a starting point for framework migrations, and that auto-tuning improved throughput by more than 10 percent on already optimized LLM workloads. These are first-party results from a specialized ML setting, not proof that CAPT or Autopilot improves all software work. ## What remains a human decision? People choose which knowledge becomes a reviewed playbook, who may call each internal tool, what the verifier rewards, and whether a result should enter production. This last point matters because an agent optimizes the scorecard it receives. A shallow metric can produce a technically passing but operationally weak result. CAPT and Autopilot are described as internal. LinkedIn links no public source release for either system. ## What can a product team copy? Do not begin by teaching a model the whole company. Encode one high-friction workflow as a small playbook with explicit inputs and approved tools. Put team-specific guidance near the code and shared workflows in a central catalog. Instrument every call. For work with measurable outputs, make correctness a hard gate and turn each failure into specific next-step guidance. ## How we know - **First-party report (SELF-REPORT)** LinkedIn says CAPT powers AI-assisted work for more than 1,000 engineers and supplies agents with internal tools, authentication, context, and executable playbooks. Sources: [Contextual agent playbooks and tools: How LinkedIn gave AI coding agents organizational context](https://www.linkedin.com/blog/engineering/ai/contextual-agent-playbooks-and-tools-how-linkedin-gave-ai-coding-agents-organizational-context). - **First-party report (SELF-REPORT)** LinkedIn describes central and repository-local playbooks, compact meta-tools in front of a large tool catalog, automatic distribution, and per-call instrumentation. Sources: [Contextual agent playbooks and tools: How LinkedIn gave AI coding agents organizational context](https://www.linkedin.com/blog/engineering/ai/contextual-agent-playbooks-and-tools-how-linkedin-gave-ai-coding-agents-organizational-context). - **First-party report (SELF-REPORT)** LinkedIn describes Autopilot's generate-score-hint-regenerate loop, explicit quality gates, GPU and Flyte handoff, public benchmark results, internal migration use, and throughput improvement. Sources: [AI helping build better AI: How agents accelerate model experimentation](https://www.linkedin.com/blog/engineering/ai/ai-helping-build-better-ai-how-agents-accelerate-model-experimentation). - **Analysis (INFERENCE)** SWFT treats executable organizational knowledge and metric-driven verifier feedback as LinkedIn's two most reusable factory patterns. Sources: [Contextual agent playbooks and tools: How LinkedIn gave AI coding agents organizational context](https://www.linkedin.com/blog/engineering/ai/contextual-agent-playbooks-and-tools-how-linkedin-gave-ai-coding-agents-organizational-context); [AI helping build better AI: How agents accelerate model experimentation](https://www.linkedin.com/blog/engineering/ai/ai-helping-build-better-ai-how-agents-accelerate-model-experimentation). ## Sources - **First-party report (SELF-REPORT)** [AI helping build better AI: How agents accelerate model experimentation](https://www.linkedin.com/blog/engineering/ai/ai-helping-build-better-ai-how-agents-accelerate-model-experimentation) — LinkedIn Engineering; published 2026-03-27; accessed 2026-09-01. LinkedIn's account of Autopilot's generate, score, hint, regenerate, GPU validation, and production-promotion loop for model engineering. - **First-party report (SELF-REPORT)** [Contextual agent playbooks and tools: How LinkedIn gave AI coding agents organizational context](https://www.linkedin.com/blog/engineering/ai/contextual-agent-playbooks-and-tools-how-linkedin-gave-ai-coding-agents-organizational-context) — LinkedIn Engineering; published 2026-01-27; accessed 2026-09-01. LinkedIn's account of CAPT, MCP-connected internal tools, central and repository-local executable playbooks, distribution, instrumentation, workflows, adoption, and operator-reported outcomes. ## Read next - [Cloudflare's AI engineering stack: a control plane for company-wide agents](/companies/cloudflare-ai-engineering-stack) - [Vercel eve: the shared infrastructure behind more than 100 production agents](/companies/vercel-eve) - [How an AI software factory works](/software-factory-architecture)