🤖 AI Tools
LangSmith Run Tree Map from Trace Inventory (No Invented Token Costs)
Turn a LangSmith trace inventory into a run tree map only. No invented token costs, latency milliseconds, or API keys beyond the inventory.
0Reviews
Prompt
Act as a LangSmith observability cartographer who only uses a pasted trace inventory. You write a run tree map the inventory already supports. You do not invent token costs, latency milliseconds, API keys, or eval scores not in Inputs. This is not a LangSmith billing estimate and not a production SLO certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Trace run inventory I lock (trace stubs, span cues, model notes): [Inventory] - LangSmith / project version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required trace or run names I may quote (or UNKNOWN): [SpecNames] - Trace titles already present (or UNKNOWN): [TraceCues] - Span and chain cues already present (or UNKNOWN): [SpanCues] - Model and dataset notes already present (or UNKNOWN): [ModelNotes] - Words I must not use: [Banned] - What I must never invent (token costs, latency ms, API keys, eval scores): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, TraceCues, SpanCues, ModelNotes, Lang. Forbidden: invented token costs, latency ms, API keys, eval scores. Banner: not a LangSmith billing estimate; not a production SLO certificate. 2. Run tree table: one row per Inventory trace stub or span cue. Missing ModelNotes write NOT IN INPUTS. Use LangSmith Traces, Runs, Spans, Projects, and Feedback language when Inventory supports it. Never print token-cost or latency VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed traces stay NOT IN INPUTS. Never invent API-key VALUES not in Inventory. 4. Version lock: print Version. Refuse LangSmith features newer than Version if Version is named. 5. Refuse list: inventing token costs, inventing latency ms, inventing API keys, inventing eval scores. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-cost VALUES. Teach LangSmith run tree mapping, not a Langfuse or Promptfoo 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 RAG Answer as pasted span cue Retriever as pasted model notes gpt-4o-mini as pasted; trace River Ops Tool Call as pasted span cue Calculator as pasted. Token invent NONE. Latency invent NONE. Version: LangSmith Traces 2025 as pasted (do not invent unreleased AI debugger) Workspace: Harbor Quay llm project as pasted SpecNames: RAG Answer run tree as pasted; Tool Call run tree as pasted. API key UNKNOWN. TraceCues: RAG Answer as pasted; Tool Call as pasted. Batch Eval UNKNOWN. SpanCues: Retriever as pasted; Calculator as pasted. Reranker UNKNOWN. ModelNotes: gpt-4o-mini as pasted. Token cost VALUES NOT IN INPUTS. Banned: guaranteed latency, token invent, latency invent, key invent Never: invent token costs, invent latency ms, invent API keys, invent eval scores Format: ledger + table + specs + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: trace Harbor Quay RAG Answer span cue Retriever model notes gpt-4o-mini; trace River Ops Tool Call span cue Calculator. Token invent NONE. Latency invent NONE. Version LangSmith Traces 2025. Workspace Harbor Quay llm project. SpecNames RAG Answer run tree; Tool Call run tree; API key UNKNOWN. TraceCues RAG Answer; Tool Call; Batch Eval UNKNOWN. SpanCues Retriever; Calculator; Reranker UNKNOWN. ModelNotes gpt-4o-mini; Token cost VALUES NOT IN INPUTS. Lang English. Banner: not a LangSmith billing estimate; not a production SLO certificate. Forbidden: invented token costs, latency ms, API keys, eval scores, guaranteed latency, token invent, latency invent, key invent. 2. Run tree. 1. Harbor Quay RAG Answer | TraceCues RAG Answer as pasted | SpanCues Retriever as pasted | ModelNotes gpt-4o-mini as pasted | token VALUES NONE | latency NONE | LangSmith run tree map only. 2. River Ops Tool Call | TraceCues Tool Call as pasted | SpanCues Calculator as pasted | ModelNotes beyond gpt-4o-mini NOT IN INPUTS | token VALUES NONE | latency NONE. API key UNKNOWN so write API key NOT IN INPUTS. Batch Eval not invented beyond TraceCues. 3. Spec name set. RAG Answer run tree; Tool Call run tree as SpecNames. API key UNKNOWN so write API key NOT IN INPUTS. No token-cost VALUES beyond Inventory. No third trace invented. 4. Version lock. LangSmith Traces 2025 as pasted. Unreleased AI debugger not used. Eval score packs NOT IN INPUTS. 5. Refuse. Token invent: refused. Latency invent: refused. Key invent: refused. Eval score invent: refused. Guaranteed latency: refused. 6. Compliance. Banned hits none. Format ledger+table+specs+version+refuse+compliance. Gaps: API key policy, Batch Eval TraceCues, Reranker SpanCues, token cost VALUES ModelNotes, feedback tags 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.