How to Sketch LangGraph Nodes from a Workflow Brief
LangGraph sketches invent Redis checkpoints and model names. Version was UNKNOWN. Leave secrets as env names only.
The matching generator is the LangGraph Node Sketch from a Workflow Brief prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Node list from Brief before edges
Sketch LangGraph nodes and edges from a workflow brief. No invented package versions or API keys. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Workflow brief: [Brief]
LangGraph version I lock (or UNKNOWN): [Version]
State fields I allow: [State]
Tools or retrievers I may name: [Tools]
Human-in-the-loop points: [HITL]
Words I must not use: [Banned]
What I must never invent: [Never]
Failure modes I care about: [Fails]
Output format: [Format]
Language for stubs (Python/TS): [Lang]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
State fields only from the allow list
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Brief, Version, State, Tools, HITL, Fails, Lang. Forbidden: keys, versions not locked, extra tools.
- Node list with one-line purpose each from Brief.
- Edge list including conditional edges only if Brief states a branch.
- State schema using State fields only.
- HITL breakpoints only as listed.
- Stub signatures in Lang without real credential values.
- Refuse: inventing model names not in Brief.
- Compliance pass: cut Banned and Never. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
HITL only where you said interrupt
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- LangGraph sketch from Brief. Not a production deploy guide.
- Never invent API keys or package versions when Version is UNKNOWN.
- Only Tools named in Inputs.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
No key values in the stub
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (langgraph node sketch, langgraph workflow brief, no invented langgraph versions) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.