--- title: Compound engineering description: Practice of building AI workflows that accumulate value through reuse and continuous improvement — consult when designing systems meant to get better over time. category: patterns updated: 2026-04-27 --- # Compound engineering **Compound engineering** is the practice of building AI workflows and automations that accumulate value through reuse and refinement. Rather than solving each task from scratch, compound engineering creates reusable systems—agents, automations, and integrations—that improve each time they're applied. The name reflects the compounding nature of this investment: initial effort building a workflow pays dividends across all future uses. The approach represents a shift from ad-hoc AI assistance to systematic capability building. Instead of prompting for help with individual tasks, compound engineering creates persistent infrastructure that handles categories of work. ## The compounding mechanism When a workflow is built once and reused across projects, two forms of value compound. First, time savings accumulate with each use—the upfront investment in designing the workflow amortizes across all executions. Second, the workflow itself improves through iteration. Each use reveals edge cases, suggests refinements, and builds institutional knowledge about how to handle specific situations. This creates asymmetric returns on effort. A few hours invested in building a robust workflow might save hundreds of hours across future projects while producing consistently higher quality than ad-hoc approaches. ## Impact on work quality A counterintuitive finding emerges from compound engineering practice: automation doesn't just speed things up—it actually improves output quality. The mechanism isn't the automation itself but what it enables. When repetitive tasks no longer consume bandwidth, attention shifts to work that was previously squeezed by time constraints. Strategy, research, learner understanding, realistic scenario development—areas that often get corner-cut due to insufficient bandwidth become the main focus. These high-value activities directly improve final output quality in ways that rushing through busywork never could. The equation isn't "same work, done faster." It's "better work, because more attention goes where it matters." ## Components of a compound engineering system Effective compound engineering typically involves multiple components working together. Agents handle specific task types—collecting material, structuring content, reformatting drafts, managing reviews. Automations connect triggers to actions, handling routine flows without manual intervention. Integrations bridge different tools and data sources, creating unified workflows across previously siloed systems. These components rarely stand alone. A well-designed compound engineering system chains multiple elements: an integration pulls source material, an agent processes it according to established patterns, automation routes the output to appropriate destinations. Each piece is individually simple; the compound value emerges from orchestration. ## Building for reuse Creating genuinely reusable workflows requires thinking beyond immediate needs. Documentation matters—a workflow that only its creator understands can't compound across team members or future contexts. Generalization matters—workflows too tightly coupled to specific projects don't transfer well. Maintenance matters—workflows require upkeep as underlying tools and requirements evolve. The investment profile differs from one-off solutions. More effort goes into design and documentation upfront; less effort goes into each subsequent execution. This tradeoff only pays off when the workflow genuinely sees repeated use, making careful selection of what to systematize an essential skill. ## Continuous improvement loops The most powerful aspect of compound engineering isn't static reuse—it's systematic improvement over time. Every workflow benefits from a feedback mechanism that captures insights from each execution and folds them back into the system. This transforms workflows from fixed tools into evolving capabilities that get better with use. The before-and-after technique exemplifies this pattern. When output from an AI system requires manual correction, that correction represents valuable signal. Rather than discarding this information after fixing the immediate problem, a continuous improvement loop captures both the original output and the corrected version, then extracts rules or guidelines that prevent similar issues in future runs. A separate skill or agent can analyze these before-and-after pairs and update the underlying rules database, tone-of-voice guidelines, or workflow instructions automatically. The key insight is minimizing friction in the feedback path. If improvement requires significant manual effort, it won't happen consistently. The most effective loops embed feedback collection into natural workflow touchpoints—comments added while reviewing output, corrections made during normal use, or ratings applied as part of existing processes. A fitness protocol integrated with Todoist, for example, allows feedback through task comments that the user would write anyway. An email drafter captures corrections simply by comparing drafted and sent versions. When improvement happens as a byproduct of normal work rather than a separate activity, compound engineering reaches its full potential. Practitioners who embrace this mindset approach every repetitive workflow with a fundamental question: how does this get better each time I use it? This perspective shift—from "how do I complete this task" to "how do I make completing this task easier next time"—distinguishes compound engineering from ordinary automation. The workflow improves with each use until eventually the human role shifts from doing the work to reviewing and occasionally correcting increasingly capable systems. ## Visibility compounds capability across an organisation A second compounding mechanism appears at the organisational level, separate from the within-workflow improvement loop. When AI workflows operate in shared channels rather than private interactions, every successful execution serves as a small demonstration to everyone watching. Colleagues learn what kinds of work can be delegated to which workflow, build trust through observation rather than through individual evaluation, and absorb working patterns by scrolling back through channel history. Capability spreads sideways without needing top-down rollout. This visibility-driven compounding solves a problem that compound engineering at scale tends to run into: even well-built workflows do not propagate inside an organisation if their use is invisible. A perfectly designed automation buried in someone's private terminal helps that one person; the same automation visible in a team channel teaches the team. The cost of visibility is occasionally working in public, including with imperfect drafts; the benefit is faster diffusion of capability across the organisation than any internal documentation could achieve. The implication for design choice is concrete. When deciding where AI work should happen, defaulting to shared spaces — team channels, public documents, group conversations — produces faster organisational adoption than private interactions even when the per-task quality is identical. The compounding effect depends on the visibility, not on the workflow being any better than its private counterpart. ## Related pages - See: agent-design-principles - Principles for building reliable components of compound systems - See: ai-workflow-redesign - Methodology for identifying systematization opportunities - See: progressive-summarization - Note-taking approach that compounds knowledge value over time - See: productive-friction - Understanding when to automate versus preserve human engagement - See: personal-agents - How per-person agent ownership creates the visible, accountable surface that this compounding depends on