# Maxim AI Resources Portal

## Docs

- [What is Prompt Engineering?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/what-is-prompt-engineering.md): Prompt engineering is the practice of writing clear and effective instructions that guide LLMs to produce outputs that meet your requirements. Models are non-deterministic and may return different results for the same input. Carefully crafting and iterating on prompts is essential to ensure that res…
- [How does Maxim Streamline the Prompt Engineering Lifecycle?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-does-maxim-streamline-the-prompt-engineering-lifecycle.md): Maxim supports the entire prompt engineering lifecycle, from experimentation through evaluation to deployment, enabling cross-functional teams to collaborate and iterate faster without engineering bottlenecks.
- [How do I Version and Manage Prompts?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-do-I-version-and-manage-prompts.md): Maxim's Prompt Playground provides a complete environment for creating, versioning, comparing, and deploying prompts, all without making any changes to the existing code base.
- [How do I Test, Evaluate, and Optimize Prompts?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-to-test-evaluate-and-optimize-prompts.md): Maxim lets you test prompts interactively, run automated evaluations against datasets, compare versions side by side, measure tool call accuracy, evaluate RAG retrieval quality, and automatically optimize prompts based on evaluation results.
- [How can I Evaluate the Performance of Prompts with Maxim AI?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-can-I-evaluate-the-performance-of-the-prompts-with-Maxim-AI.md): Learn how to evaluate AI prompt performance with Maxim AI. Compare prompts, models & agents using custom datasets, automated evaluators, and human-in-the-loop workflows for optimal results.
- [Can I Build No-Code Agents and Chain Multiple Prompts for Exerimentation with Maxim?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/Can-I-build-no-code-agents-for-experimentation-with-Maxim-AI.md): Yes, Maxim enables you to build and experiment with complex agentic workflows using its [No-Code Agent Builder](https://www.getmaxim.ai/docs/offline-evals/via-ui/agents-via-no-code-builder/quickstart). This visual interface allows you to orchestrate multi-step logic without writing code by leveragin…
- [Does Maxim Support Multimodal Inputs for Prompt Evaluation?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/does-Maxim-support-multimodal-inputs-for-prompt-evaluation.md): Yes, Maxim AI supports [evaluating prompts](https://www.getmaxim.ai/docs/offline-evals/via-ui/prompts/prompt-evals) with multimodal inputs across both the Prompt Playground for interactive experimentation and Evaluation Runs for batch testing. You can iterate on prompts using diverse data types (inc…
- [Can I Reuse Common Instructions Across Multiple Prompts?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/can-I-reuse-common-instructions-across-multiple-prompts.md): Yes, you can leverage [Prompt Partials](https://www.getmaxim.ai/docs/library/prompt-partials#creating-prompt-partials) on Maxim. They are reusable snippets of prompt content such as tone guidelines, safety rules, or formatting instructions that can be created once and used across multiple prompts. I…
- [How can I Evaluate the Context Retrieved by the Prompt?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-can-I-evaluate-context-retrieved-by-prompts.md): Evaluating the context retrieved by your prompt is critical for ensuring your Retrieval-Augmented Generation (RAG) system delivers accurate, relevant responses. [Context evaluation](https://www.getmaxim.ai/docs/offline-evals/via-ui/prompts/retrieval) helps you measure whether your retrieval mechanis…
- [ How can I Compare and Evaluate Prompts Across Various Models?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-can-I-compare-and-evaluate-prompts-across-various-models.md): Different language models have unique strengths, weaknesses, and behaviors. What works perfectly with one model might underperform with another. Cross-model comparison helps you choose the right model for your use case and optimize prompts for each model's characteristics.
- [How can I Evaluate Prompts Across Various Scenarios?](https://maxim-gtm.mintlify.app/faqs/prompt-engineering/how-can-I-evaluate-prompts-across-various-scenarios.md): Prompts that work perfectly for one use case often fail spectacularly in others. A prompt optimized for technical documentation might produce inappropriate responses for customer support. Scenario-based evaluation ensures your prompts perform well across the full range of situations your users will…
- [How do I Evaluate AI Agents and Agentic Workflows?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-to-evaluate-ai-agents-and-agentic-workflows.md): Maxim AI provides a comprehensive framework for evaluating AI agents across their entire development lifecycle. You can evaluate agents using **Offline Evaluation** (pre-deployment testing via simulations and test runs) and **Online Evaluation** (real-time monitoring of production traces). This dual…
- [How do I Create a Custom Evaluator?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-do-I-create-a-custom-evaluator.md): Maxim AI allows you to create Custom Evaluators to enforce domain-specific business logic, compliance rules, or subjective quality standards that pre-built evaluators cannot cover. You can create four distinct types of custom evaluators: AI Evaluators, Programmatic Evaluators, API-Based Evaluators,…
- [How does Agent Simulation Help Evaluate AI Agents?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-does-agent-simulation-help-evaluate-ai-agents.md): Maxim AI's Agent Simulation allows you to automate the testing of conversational AI by generating realistic, multi-turn interactions. Instead of relying solely on static datasets or manual testing, simulations create dynamic dialogues between your agent and a simulated user to stress-test behavior,…
- [How can I Evaluate Voice AI Agents?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-can-I-evaluate-voice-ai-agents.md): Maxim AI's Voice Simulation extends evaluation capabilities beyond text-based chats to fully interactive voice conversations. It allows you to test how your AI agent handles real-time speech, accents, interruptions, and latency by simulating a phone call from a user persona.
- [How can I Evaluate Local AI Agents?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-can-I-evaluate-local-ai-agents.md): Maxim allows you to evaluate AI agents running on your local machine (including those built with frameworks like CrewAI or LangChain) without needing to deploy them to an HTTP endpoint first. This is achieved using the yields_output function in the Maxim SDK, which enables you to pass a local Python…
- [What is AI Agent Evaluation?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/what-is-AI-agent-evaluation.md): Evaluation is how you systematically measure and improve the quality and performance of your AI agents.  <br/> <br/> Maxim AI provides end-to-end evaluation across the entire agent development lifecycle, from prototype to production.
- [How does Maxim AI Evaluate Multi-Turn Agent Trajectories Before Deployment?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-does-Maxim-AI-evaluate-multi-turn-agent-trajectories-before-deployment.md): Maxim AI evaluates multi-turn agent trajectories offline using partial traces and AI-powered simulations. Test conversations, identify failures, and validate performance before deployment.
- [What Types of Evaluators does Maxim Provide?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/what-type-of-evaluators-does-Maxim-provide.md): Maxim's unified evaluation framework supports both pre-built evaluators and custom evaluators. Custom evaluators are quality metrics tuned to your specific outcomes and can be created across multiple types:
- [How do I Integrate Evaluations into my CI/CD Pipeline? ](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-can-I-integrate-evaluations-into-myci-cd-pipeline.md): Maxim enables teams to build automated evaluation pipelines that integrate directly into CI/CD workflows to validate quality on every code or prompt change. The integration is powered by Maxim's SDKs (Python, TypeScript, Java, and Go) and REST APIs, allowing teams to programmatically trigger test ru…
- [Can I Curate and Evolve Datasets for Agent Evals in Maxim?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/can-I-curate-and-evolve-datasets-for-agent-evals-in-Maxim-AI.md): With Maxim, you can curate AI evaluation datasets from production logs, generate synthetic test data, or import from CSV and external sources. You can build datasets that reflect real usage patterns.
- [Does Maxim Support Human-in-the-Loop Evaluation for Agents?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/does-Maxim-support-human-in-loop-evaluation-for-agents.md): Maxim provides comprehensive support for human-in-the-loop workflows across the AI development lifecycle. You can leverage internal or external domain experts seamlessly on the platform to:
- [What is Agent Simulation?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/what-is-agent-simulation.md): AI Agent Simulation is a testing methodology that programmatically creates and runs synthetic user interactions to evaluate how your AI agent or application performs across diverse scenarios. Instead of waiting for real users to encounter edge cases or testing manually, simulation generates realisti…
- [What is LLM-as-a-Judge Evaluation?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/what-is-LLM-as-a-judge-evaluation.md): LLM as a Judge is an evaluation methodology where a language model assesses the quality, accuracy, or appropriateness of outputs from another AI system.
- [How can I Detect Hallucinations in My AI Applications?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-can-i-detect-hallucinations-in-my-AI-applications.md): RAG (Retrieval-Augmented Generation) evaluation measures the quality of both the retrieved context and the generated output in a RAG system. It uses metrics like answer correctness, relevance, semantic similarity, context recall, and faithfulness to assess how well the system retrieves and uses info…
- [How can I Evaluate My RAG Application?](https://maxim-gtm.mintlify.app/faqs/simulation-and-evaluation/how-can-I-evaluate-my-RAG-application.md): RAG (Retrieval-Augmented Generation) evaluation measures the quality of both the retrieved context and the generated output in a RAG system. It uses metrics like answer correctness, relevance, semantic similarity, context recall, and faithfulness to assess how well the system retrieves and uses info…
- [How can I Track Token Usage and Cost Across Different LLM Models?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-I-track-token-usage-and-cost-across-different-LLM-models.md): Maxim provides multiple ways to track token usage and calculate costs across your LLM models, from automatic tracking through SDK integrations to custom metric logging and configurable pricing structures.
- [How can I Monitor Complex AI Agent Workflows in Production?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-I-monitor-complex-ai-agent-workflows-in-production.md): Maxim provides SDK integrations for popular agent frameworks that automatically trace multi-agent workflows, tool calls, LLM invocations, errors, and metrics like token usage and latency, all visualized in the Maxim dashboard for analysis and debugging.
- [How do I Monitor Tool Calls in My AI Agents?](https://maxim-gtm.mintlify.app/faqs/observability/how-do-I-monitor-tool-calls-in-my-AI-agents.md): Maxim's SDK allows you to monitor tool calls (external APIs, internal functions, or any callable operations in your AI application) by capturing the complete lifecycle including arguments, results, timing, and errors.
- [Is Maxim AI Compatible with OpenTelemetry (OTel)?](https://maxim-gtm.mintlify.app/faqs/observability/is-maxim-ai-otel-compatible.md): Yes, Maxim AI is fully compatible with OpenTelemetry. You can send OTLP traces directly to Maxim for AI and LLM observability, or use Maxim as a central hub to forward enriched traces to other observability platforms.
- [What is Agent Observability and Why do I Need It?](https://maxim-gtm.mintlify.app/faqs/observability/what-is-agent-observability-and-why-do-iI-need-it.md): Observability is the practice of monitoring, tracing, and analyzing the internal states, decision-making processes, and outputs of AI agents in real-time.  <br/> <br/> Maxim AI provides end-to-end visibility into your AI agent's performance by [tracing](https://www.getmaxim.ai/docs/tracing/overview)…
- [Can I Get Alerted for Any Regressions In Cost, Latency, or Any Other Evaluation Metrics?](https://maxim-gtm.mintlify.app/faqs/observability/can-I-get-alerted-for-any-regressions-in-cost-latency-or-any-other-evaluation-metrics.md): Yes. Maxim AI allows you to track and log comprehensive metrics, including token usage, latency, cost per request, and other performance and quality scores. You can define custom thresholds and receive real-time alerts via Slack or PagerDuty whenever a monitored metric exceeds your specified limits.…
- [How can I Observe and Evaluate Multi-Turn Trajectories with Maxim AI?](https://maxim-gtm.mintlify.app/faqs/observability/how_can_I_observe_and_evaluate_multi-turn-trajectories-with-Maxim-AI.md): Maxim lets you observe and evaluate multi-turn agent behavior using [Sessions](https://www.getmaxim.ai/docs/tracing/tracing-via-sdk/sessions), which represent end-to-end task executions. <br/> <br/> Each session groups together all traces generated across multiple turns, giving you a complete view o…
- [How can I Collect And Add User Feedback To A Trace?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-I-collect-and-add-user-feedback-to-a-trace.md): Collecting user feedback is essential for understanding how well your AI application meets user expectations and identifying opportunities for improvement. Maxim's observability platform includes a built-in Feedback entity that allows you to capture structured user ratings and comments directly with…
- [How can I Evaluate Voice Agents with Realistic Voice Simulations?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-I-evaluate-voice-agents-with-realistic-voice-simulations.md): Voice agent evaluation requires testing real-world conversation scenarios to ensure your AI handles voice interactions naturally and appropriately. Maxim's Voice Simulation feature enables comprehensive testing of your voice agent's capabilities across different speech patterns, accents, and convers…
- [How can I Integrate Maxim to Trace and Evaluate My Voice Agents?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-i-integrate-maxim-to-trace-and-evaluate-my-voice-agents.md): Maxim provides native integrations for popular voice agent frameworks, enabling comprehensive tracing and evaluation of your voice AI applications through simple one-line integrations.
- [ What are Traces and Spans in Agent Observability?](https://maxim-gtm.mintlify.app/faqs/observability/what-are-traces-and-spans-in-agent-observability.md): Understanding traces and spans is fundamental to effective AI application observability. These concepts, borrowed from distributed tracing in traditional software systems, have been adapted by Maxim to provide comprehensive visibility into complex AI workflows involving LLM calls, retrieval operatio…
- [ How can I Curate Datasets From My Production Logs?](https://maxim-gtm.mintlify.app/faqs/observability/how-can-I-curate-datasets-from-my-production-logs.md): Building high-quality evaluation datasets is critical for maintaining AI application quality as your system evolves. Maxim enables you to curate datasets directly from production logs and human annotations, ensuring your test cases reflect real-world usage patterns, edge cases, and user expectations…
- [ Can I Track Evaluation Costs and Token Usage at the Eval and Repository Levels?](https://maxim-gtm.mintlify.app/faqs/observability/can-I-track-evaluation-costs-and-token-usage-at-the-eval-and-repository-levels.md): Maxim provides comprehensive cost and token usage tracking across both individual evaluation runs and entire log repositories, giving you complete visibility into your AI application's resource consumption.
- [A-Z](https://maxim-gtm.mintlify.app/glossary/glossary.md)

## OpenAPI Specs

- [openapi](https://maxim-gtm.mintlify.app/api-reference/openapi.json)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.