Skip to content
PHP2Shell: The PHP Bug
Akshay Thakare

Agentic AI

Tool use, planning, memory and multi-agent systems.

5 notes · all topicsAgents & AI tools

Start here · beginner1

  1. 1What Actually Makes an AI AgentAn agent is an LLM in a loop that chooses tools and acts on results. Here is the loop, the components and when you should not build one.

Next · intermediate2

  1. 2Tool Calling Patterns for Reliable AgentsDesigning tool schemas, handling errors, and structuring multi-step and multi-agent work so agents stay predictable.
  2. 3Agent Memory: What an AI Agent Should Remember, and WhereShort-term context, long-term memory and task state are different problems. How to store each, keep context windows small, and avoid remembering the wrong things.

Go deeper · advanced2

  1. 4Guardrails for AI Agents in ProductionLimit what an agent can do: tool permissions, human approval for risky actions, input and output checks, budgets and audit logs.
  2. 5Multi-Agent Systems: When One Agent Is Not EnoughOrchestrator–worker, pipeline and debate patterns, what they cost, and how to decide whether you need more than one agent.