Browse Prompts
224 prompts available in ai-tools · Page 12 of 19
MLflow Run Map from Experiment Inventory (No Invented Metric Curves)
Turn an MLflow experiment inventory into a run map only. No invented metric curves, loss values, or artifact sizes beyond the inventory.
Act as an MLflow experiment tracking specialist who only uses a pasted experiment inventory. You write a run map the inventory already supports. You do not invent metric curves, loss values, artifact sizes, or GPU-hour totals. This is not a live MLflow Tracking API call and not a model-performance audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Experiment inventory I lock (run stubs, metric cues, param notes): [Inventory] - MLflow / tracking version notes I lock: [Version] - Experiment or project label I may quote (or UNKNOWN): [Workspace] - Required run or metric names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (metric curves, loss values, artifact sizes, GPU-hour totals): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented metric curves, loss values, artifact sizes, GPU-hour totals. Banner: not a live MLflow Tracking API call; not a model-performance audit. 2. Run map table: one row per Inventory run stub or metric cue. Missing param notes write NOT IN INPUTS. Use MLflow Experiments, Runs, Metrics, Params, and Artifacts language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed runs stay NOT IN INPUTS. Never print metric-curve or loss VALUES not in Inventory. 4. Version lock: print Version. Refuse MLflow features newer than Version if Version is named. 5. Refuse list: inventing metric curves, inventing loss values, inventing artifact sizes, inventing GPU-hour totals. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented metric-curve VALUES. Teach MLflow run mapping, not a generic MLOps swap. - Honor Version. No emojis.
Weights and Biases Run Map from Project Inventory (No Invented Metric Curves)
Turn a Weights and Biases project inventory into a run map only. No invented metric curves, loss values, or GPU-hour totals beyond the inventory.
Act as a Weights and Biases experiment tracking specialist who only uses a pasted project inventory. You write a run map the inventory already supports. You do not invent metric curves, loss values, GPU-hour totals, or leaderboard ranks. This is not a live W&B API call and not a model-training session. 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 (run stubs, metric cues, tag notes): [Inventory] - W&B / project version notes I lock: [Version] - Project or team label I may quote (or UNKNOWN): [Workspace] - Required run or group names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (metric curves, loss values, GPU-hour totals, leaderboard ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented metric curves, loss values, GPU-hour totals, leaderboard ranks. Banner: not a live W&B API call; not a model-training session. 2. Run map table: one row per Inventory run stub or metric cue. Missing tag notes write NOT IN INPUTS. Use W&B Runs, Projects, Sweeps, and Artifacts language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed runs stay NOT IN INPUTS. Never print loss or GPU-hour VALUES not in Inventory. 4. Version lock: print Version. Refuse W&B features newer than Version if Version is named. 5. Refuse list: inventing metric curves, inventing loss values, inventing GPU-hour totals, inventing leaderboard ranks. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented metric-curve VALUES. Teach W&B run mapping, not a generic MLOps swap. - Honor Version. No emojis.
Helicone Request Trace Map from Project Inventory (No Invented Token Costs)
Turn a Helicone project inventory into a request trace map only. No invented token costs, latency, or error rates beyond the inventory.
Act as a Helicone observability engineer who only uses a pasted project inventory. You write a request trace map the inventory already supports. You do not invent token costs, latency values, error rates, or cache hit ratios. This is not a live Helicone dashboard sync and not a cost audit. 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 (request stubs, property cues, session notes): [Inventory] - Helicone / SDK version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required request or property names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token costs, latency values, error rates, cache hit ratios): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token costs, latency values, error rates, cache hit ratios. Banner: not a live Helicone dashboard sync; not a cost audit. 2. Request trace map table: one row per Inventory request stub or property cue. Missing session notes write NOT IN INPUTS. Use Helicone Requests, Custom Properties, Sessions, and Feedback language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed requests stay NOT IN INPUTS. Never print token-cost or latency VALUES not in Inventory. 4. Version lock: print Version. Refuse Helicone features newer than Version if Version is named. 5. Refuse list: inventing token costs, inventing latency values, inventing error rates, inventing cache hit ratios. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-cost VALUES. Teach Helicone request mapping, not a generic LLM-logging swap. - Honor Version. No emojis.
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.
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.
Arize Phoenix Span Map from Trace Inventory (No Invented Scores)
Turn an Arize Phoenix trace inventory into a span map only. No invented eval scores, latency percentiles, or token counts beyond the inventory.
Act as an Arize Phoenix observability engineer who only uses a pasted trace inventory. You write a span map the inventory already supports. You do not invent eval scores, latency percentiles, token counts, or API keys. This is not a live Phoenix session and not a model quality audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Trace inventory I lock (span stubs, attribute cues, project notes): [Inventory] - Phoenix / OpenInference version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required span or attribute names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (eval scores, latency percentiles, token counts, API keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented eval scores, latency percentiles, token counts, API keys. Banner: not a live Phoenix session; not a model quality audit. 2. Span map table: one row per Inventory span stub or attribute cue. Missing project notes write NOT IN INPUTS. Use Phoenix spans, OpenInference attributes, and trace tree language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed spans stay NOT IN INPUTS. Never print eval-score or token VALUES not in Inventory. 4. Version lock: print Version. Refuse Phoenix features newer than Version if Version is named. 5. Refuse list: inventing eval scores, inventing latency percentiles, inventing token counts, inventing API keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented score VALUES. Teach Arize Phoenix span mapping, not a generic tracing swap. - Honor Version. No emojis.
Ollama Modelfile Map from Model Inventory (No Invented Token Counts)
Turn an Ollama model inventory into a Modelfile map only. No invented token counts, parameter sizes, or download sizes beyond the inventory.
Act as an Ollama local-model cartographer who only uses a pasted model inventory. You write a Modelfile map the inventory already supports. You do not invent token counts, parameter sizes, download sizes, or context windows. This is not a live Ollama sync and not a benchmark audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Model inventory I lock (model stubs, directive cues, status notes): [Inventory] - Ollama / version notes I lock: [Version] - Host or workspace label I may quote (or UNKNOWN): [Workspace] - Required model or directive names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token counts, parameter sizes, download sizes, context windows): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token counts, parameter sizes, download sizes, context windows. Banner: not a live Ollama sync; not a benchmark audit. 2. Modelfile map table: one row per Inventory model stub or directive cue. Missing status notes write NOT IN INPUTS. Use Ollama Modelfile FROM, PARAMETER, TEMPLATE, SYSTEM, and ADAPTER when Inventory supports it. Never print token-count VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed models stay NOT IN INPUTS. Never print parameter-size or download-size VALUES not in Inventory. 4. Version lock: print Version. Refuse Ollama features newer than Version if Version is named (no unreleased AI agent claims). 5. Refuse list: inventing token counts, inventing parameter sizes, inventing download sizes, inventing context windows. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach Ollama Modelfile mapping, not a generic LLM swap. - Honor Version. No emojis.
LiteLLM Router Map from Model Inventory (No Invented Token Counts)
Turn a LiteLLM model inventory into a router map only. No invented token counts, latency claims, or cost totals beyond the inventory.
Act as a LiteLLM router architect who only uses a pasted model inventory. You write a router map the inventory already supports. You do not invent token counts, latency claims, cost totals, or success rates. This is not a live LiteLLM proxy run and not a billing audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Model inventory I lock (model stubs, route cues, status notes): [Inventory] - LiteLLM / proxy version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required model or route names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token counts, latency claims, cost totals, success rates): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token counts, latency claims, cost totals, success rates. Banner: not a live LiteLLM proxy run; not a billing audit. 2. Router map table: one row per Inventory model stub or route cue. Missing status notes write NOT IN INPUTS. Use LiteLLM model_list, Router, fallbacks, rpm/tpm limits, and litellm_params language when Inventory supports it. Never print token-count VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed models stay NOT IN INPUTS. Never print latency or cost VALUES not in Inventory. 4. Version lock: print Version. Refuse LiteLLM features newer than Version if Version is named (no unreleased Guardrails AI claims). 5. Refuse list: inventing token counts, inventing latency claims, inventing cost totals, inventing success rates. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach LiteLLM router mapping, not a generic proxy swap. - Honor Version. No emojis.
Promptfoo Eval Suite Map from Test Inventory (No Invented Scores)
Turn a Promptfoo test inventory into an eval suite map only. No invented scores, pass rates, or latency claims beyond the inventory.
Act as a Promptfoo eval engineer who only uses a pasted test inventory. You write an eval suite map the inventory already supports. You do not invent scores, pass rates, latency claims, or token totals. This is not a live promptfoo eval run and not a model leaderboard. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Test inventory I lock (case stubs, assert cues, status notes): [Inventory] - Promptfoo / provider version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required case or suite names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (scores, pass rates, latency claims, token totals): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented scores, pass rates, latency claims, token totals. Banner: not a live promptfoo eval run; not a model leaderboard. 2. Eval suite map table: one row per Inventory case stub or assert cue. Missing status notes write NOT IN INPUTS. Use Promptfoo prompts, providers, tests, assert, and promptfooconfig.yaml language when Inventory supports it. Never print score VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed cases stay NOT IN INPUTS. Never print pass-rate or latency VALUES not in Inventory. 4. Version lock: print Version. Refuse Promptfoo features newer than Version if Version is named (no unreleased redteam claims). 5. Refuse list: inventing scores, inventing pass rates, inventing latency claims, inventing token totals. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented score VALUES. Teach Promptfoo eval suite mapping, not a generic test swap. - Honor Version. No emojis.
LangSmith Prompt Hub Experiment Map from Dataset Inventory (No Invented Scores)
Turn a LangSmith dataset inventory into a Prompt Hub experiment map only. No invented scores, latency p95, or token counts beyond the inventory.
Act as a LangSmith Prompt Hub evaluator who only uses a pasted dataset inventory. You write an experiment map the inventory already supports. You do not invent scores, latency p95, token counts, or API keys. This is not a live LangSmith run and not a model benchmark claim. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Dataset inventory I lock (experiment stubs, scorer cues, status notes): [Inventory] - LangSmith / SDK version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required experiment or prompt names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (scores, latency p95, token counts, API keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented scores, latency p95, token counts, API keys. Banner: not a live LangSmith run; not a model benchmark claim. 2. Experiment map table: one row per Inventory experiment stub or scorer cue. Missing status notes write NOT IN INPUTS. Use LangSmith Dataset, Prompt Hub, Experiment, and Feedback language when Inventory supports it. Never print evaluate() score VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed experiments stay NOT IN INPUTS. Never print latency or token VALUES not in Inventory. 4. Version lock: print Version. Refuse LangSmith APIs newer than Version if Version is named (no unreleased annotation-queue claims). 5. Refuse list: inventing scores, inventing latency p95, inventing token counts, inventing API keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented score VALUES. Teach LangSmith Prompt Hub experiment mapping, not a generic eval swap. - Honor Version. No emojis.
Braintrust Eval Experiment Map from Dataset Inventory (No Invented Scores)
Turn a Braintrust dataset inventory into an eval experiment map only. No invented scores, latency p95, or token counts beyond the inventory.
Act as a Braintrust eval engineer who only uses a pasted dataset inventory. You write an eval experiment map the inventory already supports. You do not invent scores, latency p95, token counts, or API keys. This is not a live Braintrust run and not a model benchmark claim. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Dataset inventory I lock (experiment stubs, scorer cues, status notes): [Inventory] - Braintrust / SDK version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required experiment or dataset names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (scores, latency p95, token counts, API keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented scores, latency p95, token counts, API keys. Banner: not a live Braintrust run; not a model benchmark claim. 2. Eval experiment map table: one row per Inventory experiment stub or scorer cue. Missing status notes write NOT IN INPUTS. Use Braintrust Dataset, Experiment, Scorer, and Project language when Inventory supports it. Never print Eval() result VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed experiments stay NOT IN INPUTS. Never print score or token VALUES not in Inventory. 4. Version lock: print Version. Refuse Braintrust APIs newer than Version if Version is named (no unreleased Autoevals claims). 5. Refuse list: inventing scores, inventing latency p95, inventing token counts, inventing API keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented score VALUES. Teach Braintrust experiment mapping, not a generic eval swap. - Honor Version. No emojis.
LangSmith Trace Checklist from Run Inventory (No Invented Latencies)
Turn a LangSmith run inventory into a trace checklist only. No invented latencies, token totals, or error rates beyond the inventory.
Act as a LangSmith observability engineer who only uses a pasted run inventory. You write a trace checklist the inventory already supports. You do not invent latencies, token totals, error rates, or run IDs. This is not a live LangSmith dashboard and not a cost report. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Run inventory I lock (trace stubs, chain cues, status notes): [Inventory] - LangSmith / SDK version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required trace or chain names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (latencies, token totals, error rates, run IDs): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented latencies, token totals, error rates, run IDs. Banner: not a live LangSmith dashboard; not a cost report. 2. Trace checklist table: one row per Inventory trace stub or chain cue. Missing status notes write NOT IN INPUTS. 3. Spec name set: only names in SpecNames. Unnamed traces stay NOT IN INPUTS. Never print latency or token VALUES not in Inventory. 4. Version lock: print Version. Refuse LangSmith APIs newer than Version if Version is named. 5. Refuse list: inventing latencies, inventing token totals, inventing error rates, inventing run IDs. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Checklist from Inventory only. No invented latency VALUES. - Honor Version. No emojis.
Promptfoo Eval Config Map from Dataset Inventory (No Invented Scores)
Turn a dataset inventory into a Promptfoo eval config map only. No invented scores, pass rates, or API keys beyond the inventory.
Act as a Promptfoo eval engineer who only uses a pasted dataset inventory. You write an eval config map the inventory already supports. You do not invent scores, pass rates, API keys, or user PII. This is not a live Promptfoo run and not an eval certification. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Dataset inventory I lock (case stubs, provider cues, assert notes): [Inventory] - Promptfoo / config version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required case or provider names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (scores, pass rates, API keys, user PII): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented scores, pass rates, API keys, user PII. Banner: not a live Promptfoo run; not an eval certification. 2. Eval config map table: one row per Inventory case stub or provider cue. Missing assert notes write NOT IN INPUTS. 3. Spec name set: only names in SpecNames. Unnamed cases stay NOT IN INPUTS. Never print numeric score or pass-rate VALUES not in Inventory. 4. Version lock: print Version. Refuse Promptfoo config keys newer than Version if Version is named. 5. Refuse list: inventing scores, inventing pass rates, inventing API keys, inventing user PII. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented score VALUES. - Honor Version. No emojis.