🤖 AI Tools
Langfuse Trace Span Map from Project Inventory (No Invented Token Costs)
Turn a Langfuse project inventory into a trace span map only. No invented token costs or latency beyond the inventory.
0Reviews
Prompt
Act as a Langfuse observability engineer who only uses a pasted project inventory. You write a trace span map the inventory already supports. You do not invent token costs, latency numbers, score totals, or model pricing. This is not a live Langfuse dashboard and not a billing statement. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Project inventory I lock (trace stubs, span cues, score notes): [Inventory] - Langfuse / SDK version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required trace or span names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token costs, latency numbers, score totals, model pricing): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token costs, latency numbers, score totals, model pricing. Banner: not a live Langfuse dashboard; not a billing statement. 2. Trace span map table: one row per Inventory trace stub or span cue. Missing score notes write NOT IN INPUTS. Use Langfuse Traces, Spans, Generations, and Scores language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed spans stay NOT IN INPUTS. Never print token-cost or latency VALUES not in Inventory. 4. Version lock: print Version. Refuse Langfuse features newer than Version if Version is named. 5. Refuse list: inventing token costs, inventing latency numbers, inventing score totals, inventing model pricing. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-cost VALUES. Teach Langfuse trace span mapping, not a generic observability swap. - Honor Version. No emojis.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Generated Output
This image was generated using the prompt above.
Examples
Example Input
Inventory: trace Harbor Quay Retrieve Berth Docs as pasted span cue embed_query as pasted score note faithfulness pending as pasted; trace River Ops Generate Gate Answer as pasted span cue llm_complete as pasted. Token cost NOT IN INPUTS. Latency NONE. Version: Langfuse Python SDK 2.x as pasted (do not invent unreleased Prompt Management APIs) Workspace: Harbor Quay Langfuse Project as pasted SpecNames: Retrieve Berth Docs as pasted; Generate Gate Answer as pasted. Rerank UNKNOWN. Banned: guaranteed token cost, latency invent, score invent, pricing invent Never: invent token costs, invent latency numbers, invent score totals, invent model pricing Format: ledger + table + specs + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: trace Harbor Quay Retrieve Berth Docs span cue embed_query score note faithfulness pending; trace River Ops Generate Gate Answer span cue llm_complete. Token cost NOT IN INPUTS. Latency NONE. Version Langfuse Python SDK 2.x. Workspace Harbor Quay Langfuse Project. SpecNames Retrieve Berth Docs; Generate Gate Answer; Rerank UNKNOWN. Lang English. Banner: not a live Langfuse dashboard; not a billing statement. Forbidden: invented token costs, latency numbers, score totals, model pricing, guaranteed token cost, latency invent, score invent, pricing invent. 2. Trace span map. 1. Harbor Quay Retrieve Berth Docs | span embed_query as pasted | score faithfulness pending as pasted | token cost NOT IN INPUTS | latency NONE | Langfuse span map only. 2. River Ops Generate Gate Answer | span llm_complete as pasted | score NOT IN INPUTS | token cost NOT IN INPUTS | latency NONE. Score totals not printed. Model pricing not invented. 3. Spec name set. Retrieve Berth Docs; Generate Gate Answer as SpecNames. Rerank UNKNOWN so write Rerank NOT IN INPUTS. No token-cost VALUES printed. No third trace invented. 4. Version lock. Langfuse Python SDK 2.x as pasted. Unreleased Prompt Management APIs not used. Observation schema NOT IN INPUTS. 5. Refuse. Token-cost invent: refused. Latency invent: refused. Score invent: refused. Pricing invent: refused. Guaranteed token cost: refused. 6. Compliance. Banned hits none. Format ledger+table+specs+version+refuse+compliance. Gaps: score for River Ops Generate Gate Answer, Rerank decision, session IDs, user tags, environment label if any. Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.