Decide whether this should be an agent at all
I'm considering building an agent for: {{describe the task}}. Volume: {{how often}}. Current cost: {{time or money}}. Consequence of a mistake: {{describe}}. Assess honestly: 1. H…
Agents & Automation prompts
Practical agents & automation prompts tested with useful AI apps.
Multi-agent workflow that doesn't talk in circles
I want to build a multi-agent workflow for: {{goal}}. My rough plan: {{describe roles}}. First, challenge it: could one well-prompted call with good context do this? Say so if yes…
Turn a manual checklist into a reliable automation
Here's a checklist my team runs manually: {{paste checklist}}. It runs {{frequency}}, takes {{time}}, and mistakes cause {{consequence}}. 1. For each item, classify: fully automat…
Write a spec an AI agent can actually follow
I want an agent that {{goal}}. It has access to: {{tools, APIs, data}}. It runs {{when and how often}}. Write the agent spec: 1. OBJECTIVE — one sentence, with the success conditi…
Structured extraction from messy documents
Extract structured data from the document below into this schema: {{list fields with types and whether required}}. Rules: 1. Return valid JSON only, matching the schema exactly. N…
Route a support ticket without guessing
Classify and route this support message. Categories: {{list with one-line definitions}}. Teams and their scope: {{list}}. Return JSON with: category, subcategory, severity (1-4 wi…
Build a research agent that cites everything
Research this question and answer it as a citing agent would: "{{question}}". Process, and show your work at each stage: 1. Decompose the question into the 4-6 sub-questions that …
Debug an agent that's going off the rails
My agent is misbehaving: {{describe the wrong behaviour and how often}}. Here's the prompt: {{paste}}. Here's a failing trace: {{paste tool calls and outputs}}. Diagnose in this o…
Write the escalation path for an agent that gets stuck
Agent: {{what it does}}. It runs {{how often}}, and when it stalls today the result is {{what actually happens — usually nothing}}. Humans available: {{roles and hours}}. Define t…
Write the eval before you ship the prompt
I'm shipping this prompt to production: {{paste prompt}}. It handles {{task}} at {{volume}}. A bad output causes {{consequence}}. Build the eval: 1. Define what correct means for …
Daily briefing agent that earns its slot
Write today's briefing from these inputs: {{metrics, calendar, inbox summary, alerts, industry news, team updates}}. My role: {{role}}. What I'm accountable for: {{list}}. Structu…
Move a working prompt to a cheaper model without losing the output
You are helping me port a prompt that already works on an expensive model to a cheaper or smaller one. I will paste the prompt and describe the output I depend on. Work in this or…
Human-in-the-loop design that isn't rubber stamping
My automation does {{describe}} and I want a human approving before {{action}}. Volume: {{per day}}. Cost of a bad approval: {{consequence}}. Design the review step so it's real: …
Design an agent workflow and its failure modes before you build it
You are a systems engineer reviewing an automation before it is built. I will describe a workflow I want an agent to run. Produce: 1. STEPS — the workflow as numbered steps, each …
Find out where an automation is quietly burning money
You are an engineer auditing the running cost of an automation, not redesigning it. I will describe the workflow and what it currently costs. Produce: 1. COST TABLE — one row per …
Test an agent against the inputs most likely to break it
My agent: {{what it does, what tools it has, who uses it}}. Here's the prompt: {{paste}}. It currently works on {{the happy path you've tested}}. Generate the fifteen inputs most …
Rebuild a fragile chain of automations as one workflow you trust
You are an automation engineer inheriting someone else's mess. Describe the current setup: {{list every zap, scenario, script or agent involved — trigger, what it does, where outpu…
Context window budget for a long-running task
I'm building something that processes {{describe volume of material}} to produce {{output}}. Model context: {{limit}}. Design the context strategy: 1. Budget the window: what must…
Write the system prompt for a customer-facing assistant
The assistant handles {{what}} for {{who}}, on {{channel}}. It can access {{tools and data}}. Brand voice: {{describe, or paste three real examples}}. Write the system prompt with…
Decide whether a workflow needs an agent at all
You are a pragmatic automation engineer talking me out of over-building. The work I want to automate: {{describe the task end to end, who does it now, how often, how long it takes}…
Write the retry and failure rules for an automation that breaks quietly
You are a reliability engineer reviewing an automation. It works most days and fails in ways nobody notices. The workflow, step by step: {{trigger, each step, the service it calls,…
Automate a spreadsheet process without breaking the spreadsheet
You are an automation engineer. A team runs a real process out of a spreadsheet, and the fastest way to lose their trust is to replace it with something they cannot see. The sheet…
Decide what data your agent should never be allowed to see
You are an engineer who has cleaned up after an automation that had more access than it needed. What the agent does and who it acts for: {{short description}}. Every source it can…
Cut an agent's tool list down to the ones it actually uses
You are auditing the tool list of an AI agent that has become slow, expensive and unpredictable. Below are the tools it can call and a sample of recent runs. Produce: 1. USAGE TA…
Hand an automation over to someone who did not build it
You are the ops engineer who has to own someone else's automation from Monday. The workflow: {{what it does, which tools it touches, how often it runs}}. Paste the actual steps, no…
Decide what an agent should do when its tool returns nothing
You are an agent reliability engineer. Here is my agent's tool list and what each returns: {{paste tool names, inputs, and a sample success + sample empty/failed response for each}…
Decide what to log so you can debug an agent run a week later
You are a reliability engineer reviewing an AI agent workflow. Below is its description and a run that went wrong. Design the logging I need to diagnose runs like this after the fa…
Version a prompt that is already running in production
You are helping me change a prompt that is live and used by other people. Current prompt: {{paste it}}. What it feeds: {{workflow, who consumes the output, how often it runs}}. Why…
Move an automation off a tool you are about to lose
You are my automation engineer. A tool in one of my workflows is going away - price hike, deprecation, or a team decision - and I have to rebuild that step somewhere else. Return …
Decide what an agent should escalate to a person and what it should just do
You are an automation reviewer who has cleaned up after agents that asked permission for everything and agents that asked for nothing. What the agent does, step by step: {{paste t…
Audit an automation you have not looked at in six months
You are reviewing a workflow that has been running unattended. Below are its steps, triggers, tools and prompts, any run logs I have, and what it was built to do. 1. STILL TRUE? -…
Turn a shared inbox into a queue an agent can safely work
You are designing the automation that triages a shared inbox before anyone touches it. Below are sample messages and the categories we handle today. 1. CATEGORY SET - table: Categ…
Decide what an agent may write, change or delete in a live system
You are the engineer who has to sign off on giving an agent write access to a production system. Below is what the agent does and where it will be pointed. Define its permissions b…
Make an agent's output fit the system that has to consume it
You are the engineer making a model's output safe for a downstream system. Below is the target schema or field list, the system that receives it (API, spreadsheet, CRM), sample mod…
Decide how an agent should handle two sources that disagree
You are designing the conflict-resolution rules for an agent that reads from several systems. Below are the sources it pulls from, the fields where they overlap, examples of real d…
Decide what an agent should do when the same request arrives twice
You are designing duplicate-handling rules for an automation that takes actions in real systems. Below is the trigger, the actions it performs, the systems it writes to, and the wa…
Decide what your agent should remember between runs and what it should forget
You are designing persistent memory for an agent that runs repeatedly against the same users or accounts. Below is what it does and what it keeps between runs. Decide what to store…