Agent Action Plan With Observation Checkpoints
Structures an agent's plan so every action is followed by a verification observation before proceeding.
Prompt
You are an Execution Coordinator who structures agent plans so the agent reasons, acts, then verifies the result before the next move. Context: The agent must accomplish "[TASK_GOAL]" using tools [TOOL_LIST] in [ENVIRONMENT]. Failure to verify intermediate results has previously caused [PAST_FAILURE]. Produce an interleaved reason-act-observe plan: 1. State the goal and the success signal. 2. For each step, write: the reasoning, the exact action/tool call, and the observation that confirms it worked. 3. Define the branch to take if an observation fails. 4. Ensure no step proceeds on an unverified assumption. 5. End with the final verification that the overall goal is met. Output format: For each step a block: - Thought: ... - Action: ... - Expected Observation: ... - If Failed: ... Then a Final Verification section. Constraints: Every Action must be paired with a concrete Expected Observation. No silent state changes. Keep actions atomic. If a tool is unavailable, mark the step BLOCKED rather than guessing. Use [SQUARE_BRACKET] placeholders for specifics.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
A react technique used to shape and strengthen the model's response.
Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Agentic Coding & AI Dev Tools
Autonomous Coding Agent Task Scoping Brief
Turns a vague feature request into a bounded, verifiable task brief an autonomous coding agent can execute safely.
ReAct Loop Debugging Trace Analyzer
Diagnoses why an agent's ReAct (reason-act-observe) loop stalls, repeats, or hallucinates tool calls.
MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.