To get teams experimenting with AI, leaders should provide an open budget for tokens initially. Being 'profligate' at the start is crucial, as imposing constraints too early leads to unimpressive results, stifles creativity, and hinders true adoption. Efficiency can be optimized later.

The cost of re-validating, QA-ing, and re-training internal apps built on a specific LLM far outweighs potential token savings. Once an application is "dialed in" on a model like Claude Opus, the business has little incentive to switch, creating a durable competitive advantage.

Some large companies are incentivizing employees to use the maximum amount of AI tokens, even ranking them on usage. This seemingly inefficient strategy is a deliberate investment to accelerate adoption. The goal is to retrain employee thinking to be "AI native" before optimizing for cost and efficiency.

Companies like Shopify and Atlassian now require designers to use AI tools like Cursor and Claude in their work, enforced through performance reviews. This top-down mandate aims to accelerate exploration of new workflows, such as stateful prototyping, and overcome the friction of adopting new tools amidst tight deadlines.

To foster breakthrough ideas, companies should initially provide engineers with unrestricted access to the most powerful AI models, ignoring costs. Optimization should only happen after an idea proves its value at scale, as early cost-cutting stifles creativity.

To accelerate company-wide skill development, Shopify's CEO mandated that learning and utilizing AI become a formal component of employee performance evaluations. This top-down directive ensured rapid, broad adoption and transformed the company's culture to be 'AI forward,' giving them a competitive edge.

To optimize AI agent costs and avoid usage limits, adopt a “brain vs. muscles” strategy. Use a high-capability model like Claude Opus for strategic thinking and planning. Then, instruct it to delegate execution-heavy tasks, like writing code, to more specialized and cost-effective models like Codex.

To optimize costs, users configure powerful models like Claude Opus as the 'brain' to strategize and delegate execution tasks (e.g. coding) to cheaper, specialized models like ChatGPT's Codec, treating them as muscles.

To manage non-deterministic AI products, Shopify created an internal tool where PMs grade AI-generated outputs. This creates a "ground truth" dataset of what "good" looks like, which is then used to fine-tune a separate LLM that acts as an automated quality judge for new features and updates.