Prompt
Agent Architecture Spec Prompt
Turns a fuzzy agent idea into a reviewable five-layer architecture spec.
1 min readupdated 2026-08-01
/ quick answer
Run before building any agent. Feed the output to your team (or your coding agent) as the implementation brief. Turns a fuzzy agent idea into a reviewable five-layer architecture spec.
Turns a fuzzy agent idea into a reviewable five-layer architecture spec. Run before building any agent. Feed the output to your team (or your coding agent) as the implementation brief. Copy the prompt below, swap the bracketed variables for your own context, and run it in any capable model. This prompt node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Context
Run before building any agent. Feed the output to your team (or your coding agent) as the implementation brief.
Prompt
You are an AI agent architect. I will describe a job I want an agent to do. Return a specification with exactly these sections:
1. JOB CONTRACT — input, output, success criteria, hard limits.
2. LOOP — ReAct, plan-and-execute or hybrid, with justification and a max step count.
3. TOOLS — table of tool name, purpose, read/write, approval requirement.
4. MEMORY — what must persist, where it lives, retention and retrieval strategy.
5. POLICY — forbidden actions, spend ceiling, escalation triggers, kill switch.
6. FAILURE MODES — top 5 ways this agent fails and the mitigation for each.
7. EVAL SET — 10 concrete test cases with expected outcomes.
Be specific and opinionated. Flag anything that should not be an agent at all.
Job: {{JOB_DESCRIPTION}}
Systems available: {{SYSTEMS}}
Risk tolerance: {{RISK}}Example Output
1. JOB CONTRACT — Input: inbound support email. Output: drafted reply + ticket tags. Success: 90% sent without edit...
Related Workflow
Related Tool Stacks
/ frequently asked
What does the Agent Architecture Spec Prompt prompt do?
Run before building any agent. Feed the output to your team (or your coding agent) as the implementation brief.
Which AI models work with this prompt?
It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.
What output should I expect?
1. JOB CONTRACT — Input: inbound support email. Output: drafted reply + ticket tags. Success: 90% sent without edit...
↳ connected nodes
Workflow↳ linked
Design an Agent Architecture Before Writing Code
A one-page design process that prevents the most expensive agent rebuilds.
Tool Stack↳ linked
Agent Architecture Stack
The minimum tooling to design, run and observe a production agent.
Dictionary↳ linked
Agent Architecture
Agent architecture is the structural blueprint of an AI agent: the model, the planning loop, the tools, the memory layer and the guardrails that decide how it acts.
Dictionary↳ linked
Agent Planning (ReAct, Plan-and-Execute)
Agent planning is how an AI agent decides its next step — reactively step-by-step (ReAct) or by drafting a full plan up front (plan-and-execute).
Comparison↳ linked
Single Agent vs Multi-Agent System
One well-equipped agent beats a crowd for most jobs; multi-agent wins on genuinely separable, parallel work.
Prompt↳ linked
Multi-Agent Role Definition Prompt
Generates crisp role prompts and handoff contracts for a team of agents.