# For Developers: Trace, debug, and control every AI agent decision > Developer portal: AISquare captures the reasoning behind every agent decision. Connect any agent stack through the SDK or the proxy, trace every decision, find what broke across runs, and fix behavior without a redeploy cycle. - **URL:** https://aisquare.studio/developers - **Audience:** Engineers building or debugging AI agents - **Topics:** agent debugging, tracing, SDK, proxy, API, observability, policy violations, open source, Discord ## Trace, debug, and control every AI agent decision. AISquare captures the reasoning behind every agent decision. Debug faster, catch regressions before they ship, and build AI systems that are explainable, reliable, and production-ready. - Connect with any agent stack - See why. Not just what happened. - Debug and fix. No redeploy cycle. - Govern and scale AI Agents. CTAs: Read the docs (https://docs.aisquare.studio/) and Contribute to open source (https://github.com/AISquare-Studio/awesome-aisquare). ## Agent debugging is still guesswork. You can trace every run. You still struggle to debug it. - **Same input. Different output. No idea why.** Your traces show both runs. They don't explain why your agent chose different paths. - **Something changed. Your traces can't say what.** Behavior shifted after a deployment. Pinpointing the cause is hours in the traces. Sometimes a full day. - **Found the bug. Now the real work starts.** Fixing one bad decision means cycling through traces, prompts, and redeploys until something sticks. ## Add trust to your AI development workflow Connect in minutes. Trace every decision. Fix behavior before it ships. - **01 Connect to your stack in minutes.** Install the SDK or connect through the proxy. AISquare starts capturing agent runs without forcing your team into a new workflow. Quick setup: generate an API key for the Studio, install the SDK with `pip install "aisquare[explainability]"`, then call `sdk.init_from_env()` (auto-configure from environment) and wrap your agent with `GovernedAgent.from_agno(my_agent)`. - **02 Trace every decision as it happens.** Every agent run produces a complete execution graph. See inputs, tool calls, reasoning steps, and outputs in one place so your team can understand how each run actually happened. - **03 Catch what exactly broke across runs.** Compare runs, click the flagged node, and pinpoint why behavior shifted after a prompt tweak, tool update, context change, or release. Everything you need to understand the issue in one view. - **04 Fix behavior where it breaks.** Apply targeted controls, policies, and interventions instead of bouncing between traces, prompts, code, and redeploys. No prompt trial-and-error. - **05 Fix once. Every future run covered.** Turn the fix into persistent policy and feedback so the same failure does not keep coming back. ## Start integrating AISquare into your AI stack Connect AISquare to the agent frameworks, model providers, and runtimes your team already uses: Agno, LangChain, LlamaIndex, CrewAI, OpenAI, Claude, Gemini, Mistral, OpenClaw. - **Docs:** Guides, quickstarts, and concepts to get you building fast. - **API Reference:** Explore endpoints, schemas, and integration patterns for AISquare systems. - **SDKs:** Drop-in Python SDK to add explainability to any AI agent or pipeline. - **Open Source:** A curated list of AISquare projects, integrations, and community resources. ## Build with AISquare Start building, contribute in public, and get help when you need it. - **Open source repos:** AISquare-Studio-QA (AI-powered GitHub Action that converts natural language test descriptions into Playwright tests), django-ais (Django-native orchestration framework for agentic workflows with DB-backed job management and real-time event streaming), and aisquare-integrations (adapters for LangChain, CrewAI, AutoGen; coming soon). - **Join the community:** 500+ developers building with AISquare, with a 24h average response time. Ask questions, share what you're building, and stay ahead of what's shipping next on Discord. The page also lists the three most recent events (upcoming or past), the latest blog posts and the changelog (https://aisquare.featurebase.app/changelog). ## Bring trust, traceability, and control into your AI workflow Get a complete picture of every decision your agent makes. CTAs: Get API Keys (https://docs.aisquare.studio/docs/getting-started/authentication) and Read the docs. AISquare is the audit, trust, and governance layer for AI systems. ## Links - [Documentation](https://docs.aisquare.studio/docs/getting-started/overview) - [Quickstart](https://docs.aisquare.studio/docs/getting-started/quickstart) - [API reference](https://docs.aisquare.studio/docs/api-reference/overview) - [Python SDK](https://pypi.org/project/aisquare-explainability/) - [Open source](https://github.com/AISquare-Studio/awesome-aisquare) - [Discord](https://discord.com/invite/8tJ3aCDYur) --- **Machine-readable AISquare** - Site index for LLMs: https://aisquare.studio/llms.txt - Agent instructions (when to use AISquare): https://aisquare.studio/agents.md - OpenAPI specification: https://aisquare.studio/openapi.json - MCP endpoint (Streamable HTTP, POST): https://aisquare.studio/mcp - Sitemap: https://aisquare.studio/sitemap.xml - Blog feed (RSS, full posts): https://aisquare.studio/blogs/rss.xml - Any page on this site also serves markdown: append `.md` to its path (the homepage is `/index.md`) or send `Accept: text/markdown`.