# Mint Starter Kit ## Docs - [Claude Code setup](https://docs.trysquad.ai/ai-tools/claude-code.md): Configure Claude Code for your documentation workflow - [Cursor setup](https://docs.trysquad.ai/ai-tools/cursor.md): Configure Cursor for your documentation workflow - [Windsurf setup](https://docs.trysquad.ai/ai-tools/windsurf.md): Configure Windsurf for your documentation workflow - [Create Plant](https://docs.trysquad.ai/api-reference/endpoint/create.md): Creates a new plant in the store - [Delete Plant](https://docs.trysquad.ai/api-reference/endpoint/delete.md): Deletes a single plant based on the ID supplied - [Get Plants](https://docs.trysquad.ai/api-reference/endpoint/get.md): Returns all plants from the system that the user has access to - [New Plant](https://docs.trysquad.ai/api-reference/endpoint/webhook.md): Information about a new plant added to the store - [Introduction](https://docs.trysquad.ai/api-reference/introduction.md): Example section for showcasing API endpoints - [Agent Orchestration Workloads: Distributing Team-Level Work](https://docs.trysquad.ai/blog/agent-orchestration-workloads.md): We reduced 2-week sprint work to 2 hours by orchestrating 8 parallel agents with Squad's Director-Scout-Engineer architecture. - [Building Agentic Distributed Systems at Scale](https://docs.trysquad.ai/blog/agentic-distributed-systems.md): Applying distributed systems principles to multi-agent coordination: consistency, availability, partition tolerance for AI agents. - [The AI Coding Tool Bake-Off: Claude Code vs Squad vs Cursor](https://docs.trysquad.ai/blog/bakeoff-claude-code-squad-cursor.md): We benchmarked Claude Code, Squad, and Cursor on the same tasks. Here's which tool wins at different scales, with real data. - [Closing the Loop: How Artifacts Enable Agent Verification](https://docs.trysquad.ai/blog/closing-the-loop-artifacts.md): Artifacts provide proof that agents completed work correctly. How receipts, frozen contracts, and evidence close the verification loop. - [The Code Review Liquidity Crisis](https://docs.trysquad.ai/blog/code-review-liquidity-crisis.md): When AI agents generate more code than humans can review, code review becomes the bottleneck. Here's how receipts solve the liquidity crisis. - [Context Engineering Is Not Prompt Engineering](https://docs.trysquad.ai/blog/context-engineering-not-prompt-engineering.md): Google's ADK, Stanford's ACE paper, and Squad independently arrived at the same insight: context is a compiled view over stateful systems, not a string to optimize. Here's what we learned before the docs existed. - [Context Management for Multi-Agent Systems](https://docs.trysquad.ai/blog/context-management-multi-agent.md): How we reduced context size by 73% while improving task success from 61% to 94% through active context management. - [The DAG Parallelization Problem in Multi-Agent Systems](https://docs.trysquad.ai/blog/dag-parallelization-problem.md): Dependency analysis and task parallelization in multi-agent systems. How we detect critical paths and maximize parallel execution. - [Dogfooding Squad: Building Squad With Primitive Squad](https://docs.trysquad.ai/blog/dogfooding-squad-with-primitive-squad.md): We used a primitive version of Squad to build Squad itself. The meta-development insights and what worked (and what broke). - [How We Review 50+ Agent-Generated PRs Per Week Without Losing Our Minds](https://docs.trysquad.ai/blog/how-we-review-agent-prs.md): When agents save developer time but humans become the review bottleneck, you haven't solved anything—you've just moved the problem. Here's how we went from 47-minute reviews to 4.2 minutes with an 87% auto-merge rate. - [Long-Running Agents: Building Systems That Don't Need You Watching](https://docs.trysquad.ai/blog/long-running-agents.md): Most agents fail after 15 minutes. We built state persistence and failure recovery to enable 4.5-hour unattended executions with 94% success rate. - [I Had a Call With a Meta AI Engineer. Here's What He Said About Our Architecture.](https://docs.trysquad.ai/blog/meta-ai-engineer-validation.md): When Meta's AI infrastructure team independently built the same receipt system we use for Squad, we knew we were onto something real. Here's what validation from Meta Superintelligence Labs taught us about building autonomous agents. - [Receipts-First Governance: Building Trust in Autonomous Agent Systems](https://docs.trysquad.ai/blog/receipts-first-governance.md): Trust is the bottleneck in autonomous agent adoption. We went from 23% to 87% autonomous approval by making every agent decision auditable with receipts. - [Reinforcement Learning in Multi-Agent Coordination](https://docs.trysquad.ai/blog/reinforcement-learning-multi-agent.md): Self-improving multi-agent systems through reinforcement learning feedback loops. How agents learn from their mistakes. - [Security, Observability, and Governance for Autonomous Agents](https://docs.trysquad.ai/blog/security-observability-governance.md): Real-time monitoring, governance controls, and audit trails for production multi-agent systems. Dark mode dashboards included. - [Six Limitations of Claude Code That Squad Solves](https://docs.trysquad.ai/blog/six-limitations-claude-code-squad-solves.md): Claude Code is excellent for individual tasks. Squad solves six specific limitations for team-level work. Here's the exact comparison. - [Temporal Coupling: The Achilles' Heel of Autonomous Agents](https://docs.trysquad.ai/blog/temporal-coupling-achilles-heel.md): 37% of agent failures trace to one problem: reality changes after the agent's snapshot. A Meta AI engineer told us this is frontier research. Then we found Parallel's Monitor API. Here's how we're solving it. - [Development](https://docs.trysquad.ai/development.md): Preview changes locally to update your docs - [Code blocks](https://docs.trysquad.ai/essentials/code.md): Display inline code and code blocks - [Images and embeds](https://docs.trysquad.ai/essentials/images.md): Add image, video, and other HTML elements - [Markdown syntax](https://docs.trysquad.ai/essentials/markdown.md): Text, title, and styling in standard markdown - [Navigation](https://docs.trysquad.ai/essentials/navigation.md): The navigation field in docs.json defines the pages that go in the navigation menu - [Reusable snippets](https://docs.trysquad.ai/essentials/reusable-snippets.md): Reusable, custom snippets to keep content in sync - [Global Settings](https://docs.trysquad.ai/essentials/settings.md): Mintlify gives you complete control over the look and feel of your documentation using the docs.json file - [Introduction](https://docs.trysquad.ai/index.md): Welcome to the new home for your documentation - [Quickstart](https://docs.trysquad.ai/quickstart.md): Start building awesome documentation in minutes ## OpenAPI Specs - [openapi](https://docs.trysquad.ai/api-reference/openapi.json) ## Optional - [Documentation](https://mintlify.com/docs) - [Blog](https://mintlify.com/blog)