Engineering Notes
Thoughts and Ideas on AI by Muthukrishnan
Tag: Tool-Use
Code Writing Agents and Program Synthesis Teaching AI to Build Its Own Tools
How AI agents generate, execute, and refine code as a reasoning medium, from classical program synthesis to modern REPL-based agent loops and SWE-bench architecturesTool Composition and Chaining for Complex Agent Capabilities
Master the art of combining simple tools into sophisticated agent capabilities through composition patterns, chaining strategies, and intelligent orchestration.Constrained Decoding and Structured Output for Agent Reliability
Master how modern AI agents ensure reliability through controlled generation—from JSON schemas to grammar constraints and finite-state machines.How AI Agents Use Tools with Function Calling
## Concept Introduction **Tool Use** is the mechanism that allows a language model to interact with and affect the out...Fusing Reasoning and Action in LLM Agents with ReAct
### Concept Introduction **ReAct** (Reason + Act) is a prompting framework where the LLM generates output in a specifi...