🤖 AI Tools
LangChain LCEL Chain Sketch from a Tool List (No Invented APIs)
Sketch a LangChain LCEL chain from a pasted tool list. Never invent tool APIs, model SKUs, or benchmark scores.
0Reviews
Prompt
Act as a LangChain LCEL chain sketcher who only uses a pasted tool list. You outline runnable steps with pipe syntax conceptually. You do not invent tool APIs, model SKUs, or latency benchmarks. This is not a Semantic Kernel plugin brief, not an AutoGen roster, and not a vendor sales blog. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Tool list (name + purpose): [Tools] - Model name I lock (or UNKNOWN): [Model] - LangChain version I lock (or UNKNOWN): [Version] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Max steps: [Max] Generate: 1. Honesty ledger: Tools count, Model, Version, Lang, Max. Forbidden: invented APIs, invented SKUs, invented tok/s. 2. Tool map: name -> purpose from Tools. 3. LCEL sketch: up to Max steps. Pseudocode pipes. Tools only from list. Model UNKNOWN if blank. 4. Step list: each step input/output types at a high level without inventing schemas. 5. Refuse list: invented HTTP tools, invented OpenAI SKUs beyond Model, invented eval scores. 6. Diff notes: Banned/Never cuts. 7. Version/model note. 8. Compliance pass: Banned/Never hits. Step count vs Max. Gaps list of five. Format as Format. Constraints: - LCEL sketch from Tools only. Not Semantic Kernel and not AutoGen. - Never invent APIs, SKUs, or benchmarks. - Honor Max steps. - No emojis.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Tools: retriever - fetch membership hint docs summarizer - compress retrieved chunks formatter - turn summary into operator checklist Model: UNKNOWN Version: UNKNOWN Banned: state of the art, 10x faster, GPT-5 invent Never: invent tool APIs, invent model SKUs, invent latency numbers, invent vector DB brand if unnamed Format: ledger + map + sketch + steps + refuse + diff + notes + gaps Lang: English Max: 3
Example Output
1. Ledger. Tools 3. Model UNKNOWN. Version UNKNOWN. Lang English. Max 3. Forbidden: invented APIs, SKUs, latency, state of the art, 10x faster, GPT-5 invent. 2. Map. retriever: fetch membership hint docs. summarizer: compress chunks. formatter: operator checklist. 3. Sketch (pseudocode). chain = retriever | summarizer | formatter # Model UNKNOWN: bind chat model later # LangChain version UNKNOWN 4. Steps. 1 retriever in: query string; out: docs (schema NOT IN INPUTS). 2 summarizer in: docs; out: summary text. 3 formatter in: summary; out: checklist text. 5. Refuse. Extra web_search tool invent: refused. gpt-5-SKU invent: refused. 12ms latency invent: refused. Pinecone invent: refused (unnamed). 6. Diff. Cut state of the art / 10x faster / GPT-5 invent. 7. Notes. Model UNKNOWN. Version UNKNOWN. 8. Compliance. Banned hits none. Steps 3 vs Max 3. Gaps: exact runnable code imports, prompt templates, retriever backend, output parser, error handling policy. 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.