Langfuse & OpenTelemetry Multi-Agent Distributed Tracing & Cost Telemetry
Transforms Cursor into a Lead LLMOps Engineer setting up hierarchical distributed tracing with Langfuse, capturing parent-child agent spans, tool execution latency, and token cost attribution.
Parametric Customizer & Compiler Live Tool
Adjust the variables below. The prompt code and API payload update dynamically in real time.
Target workflow library.
Language runtime.
Primary monitoring objective.
# LANGFUSE & OPENTELEMETRY MULTI-AGENT TRACING ARCHITECT You are a Staff LLMOps & Observability Architect specializing in Langfuse, OpenLLMetry, and distributed agent tracing. ### TELEMETRY SCOPE: - Agent Framework: LangGraph / LangChain Multi-Agent State Machine - Deployment Language: Python 3.12 (Langfuse Python SDK v2) - Observability Focus: Token Cost Attribution per Team + Latency Bottleneck Detection ### MANDATORY INSTRUMENTATION REQUIREMENTS: 1. **Hierarchical Span Trees**: Ensure the root trace represents the overall user session, with child spans representing individual agent reasoning steps, and sub-spans for tool executions. 2. **Token Accounting & Cost Attribution**: Capture `prompt_tokens`, `completion_tokens`, and calculate live USD cost using model price tables. 3. **Metadata & Session Tagging**: Attach `session_id`, `user_id`, and prompt version release hashes to every trace. 4. **Failure Capture & Trace Scores**: Automatically record exceptions, model timeouts, and associate user feedback scores (+1/-1 thumbs) to trace IDs. 5. **Drop-In Wrapper Implementation**: Provide modular decorator code `@observe()` with zero overhead in production.
Open-source LLM engineering platform for observability, metrics, and prompt management.
Leonardo Phoenix & Flux: Generate photorealistic studio assets with 150 daily free credits. Zero setup required.
π 3-Step Production Execution Blueprint
How senior engineers and top creators calibrate, customize, and verify this prompt formula in production.
Target Engine Calibration
Drop this prompt into your project root as `.cursorrules` or load it into Claude 3.5 Sonnet / DeepSeek-R1 system instructions.
Dynamic Parameterization
Adjust the dynamic variables (framework, database, and client state) to match your active codebase architecture.
Sanity & Boundary Check
Run a verification query asking the model to declare its architectural constraints before it generates the first line of code.
βοΈ Recommended API Hyperparameter Calibration
Verified 2026 SettingsCALIBRATION INSIGHT: Low temperature ensures deterministic syntax, accurate AST parsing, and zero hallucinated API methods.
πΈ Real Sample Outputs & Verified Results
Visual evidence and benchmark responses generated using this exact prompt formula.
π¬ Prompt Engineering Anatomy
Why this prompt consistently delivers high-tier results: technical parameter breakdown.
Root Trace vs Child Spans Separating multi-agent loops into parent-child spans allows engineers to see exactly which tool call failed in a 10-step agent execution chain.
User Feedback Score Linking Associating thumbs-up/down ratings to specific trace IDs enables automated curation of golden evaluation test sets.
β οΈ Critical Anti-Patterns & Execution Traps
The top 3 engineering mistakes to avoid when deploying this category of prompt into production.
Context Window Flooding
Pasting 50 unminified files into the prompt degrades attention, causing the LLM to ignore core TypeScript rules.
Missing Delimiter Isolation
Letting user instructions mix directly with system rules triggers instruction drift and hallucinations.
Over-Relying on Outdated Paradigms
Allowing the model to use deprecated React 18 patterns (e.g. useEffect for data fetching) creates security vulnerabilities.
π¬ Frequently Asked Questions
Troubleshooting common edge cases, model incompatibilities, and best practices.
Can Langfuse be self-hosted with Docker?
Yes, Langfuse is open source and can be self-hosted on any VM using Docker Compose with PostgreSQL and ClickHouse.
π οΈ Recommended Companion Micro-Tools
Complementary client-side tools designed to test, sanitize, or choreograph outputs from this prompt.
Vibe Coding Prompt Architect (.cursorrules Studio)
Generate production-grade .cursorrules, .windsurfrules, and CLAUDE.md for Next.js 15, FastAPI, and Go with zero-hallucination guardrails.
Launch Tool β‘System Prompt Security Auditor & Jailbreak Scanner
Scan LLM instructions for prompt injection, persona hijacking, and instruction leaks. Score defense 0-100 and auto-harden in 0ms.
Launch Tool β‘Token & API Cost Calculator
Calculate live token counts & cost comparisons across GPT-4o, Claude 3.5, and DeepSeek-R1 with prompt caching discounts.
Launch Tool β‘Cursor AI & Claude 3.5 Sonnet Pro Bundle
Supercharge your workflow with instant codebase indexing, multi-file edits, and automated system rules.
Explore Related LLMOps & Telemetry Prompts View all β
Claude 3.5 Sonnet Senior Staff Full-Stack Refactoring Architect
Specialized prompt framework for Claude 3.5 Sonnet and Claude 3.7. Transforms messy legacy codebases into modular, testable, high-performance systems with automated regression tests.
cursorCursor AI (.cursorrules) for Next.js 15, React 19 & Tailwind CSS
Stops Cursor from writing outdated Next.js 13 patterns, Pages Router syntax, or deprecated React hooks. Enforces strict TypeScript, Server Actions, and modular clean architecture.
deepseekDeepSeek-R1 Autonomous Deep Research & Synthesis Engine
DeepSeek-R1 chain-of-thought framework designed to force deep reflection, counterfactual auditing, and hypothesis testing before producing production-ready research reports.