To prevent an AI agent from repeating mistakes across coding sessions, create 'agents.md' files in your codebase. These act as a persistent memory, providing context and instructions specific to a folder or the entire repo. The agent reads these files before working, allowing it to learn from past iterations and improve over time.

To build a useful multi-agent AI system, model the agents after your existing human team. Create specialized agents for distinct roles like 'approvals,' 'document drafting,' or 'administration' to replicate and automate a proven workflow, rather than designing a monolithic, abstract AI.

A major hurdle for enterprise AI is messy, siloed data. A synergistic solution is emerging where AI software agents are used for the data engineering tasks of cleansing, normalization, and linking. This creates a powerful feedback loop where AI helps prepare the very data it needs to function effectively.

The 'Claudie' AI project manager reads a core markdown file every time it runs, which acts as a permanent job description. This file defines its role, key principles, and context. This provides the agent with a stable identity, similar to a human employee, ensuring consistent and reliable work.

To avoid common pitfalls in AI development, treat building an agent like making a burger. Ensure you have all core components: a model (patty), tools (condiments), knowledge/memory (vegetables), and guardrails (bun). While the specific 'ingredients' can change, omitting any component results in an incomplete or broken agent.

Don't view AI tools as just software; treat them like junior team members. Apply management principles: 'hire' the right model for the job (People), define how it should work through structured prompts (Process), and give it a clear, narrow goal (Purpose). This mental model maximizes their effectiveness.

Instead of holding context for multiple projects in their heads, PMs create separate, fully-loaded AI agents (in Claude or ChatGPT) for each initiative. These "brains" are fed with all relevant files and instructions, allowing the PM to instantly get up to speed and work more efficiently.

AI agents are simply 'context and actions.' To prevent hallucination and failure, they must be grounded in rich context. This is best provided by a knowledge graph built from the unique data and metadata collected across a platform, creating a powerful, defensible moat.

The skills of setting clear goals, understanding resource (model) strengths, and defining processes are the same for managing people and AI agents. Being a great manager makes you a great AI user, as both require clarifying outcomes and marshalling resources to achieve them.