AI engineering glossary · Agents tools MCP
What is thought-action-observation?
Thought-action-observation: The three-part rhythm used by reasoning-and-acting agents: the model writes a short reasoning note, picks an action, then reads the observation before the next round. Writing the thought first helps the model plan and gives developers a readable trace to debug.
Thought-action-observation: an example
Thought: I need the price. Action: search('iPhone price India'). Observation: 'Rs 79,900'. Thought: I can now answer.
Related terms
More Agents tools MCP terms
- Tool argument validation
- Tool error handling
- Tool overload
- Tool registry
- Tool retrieval
- Tool selection
- Toolformer
- Tracing
Where you learn it
Thought-action-observation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.