Case ledger
Where AI spend pays off
Most companies can tell you how much they spend on AI. Far fewer can tell you what that spend is doing. Each row is a case note: the finding, and nothing invented to fill a gap.
- 01 Why AI ROI Beats Another Dashboard A dashboard shows that activity happened. It does not say whether the spend was worth paying for.
- 02 The true cost of reasoning models vs cheap models Expensive reasoning is often overkill, and cheap or open-weight models carry costs too: retries, review time, failure handling. How to weigh both.
- 03 Agent loops vs long-running work worth paying for Long agent runs aren't always waste, and short ones aren't always fine. How to separate loops from justified long work with session evidence.
- 04 Tool errors, handoffs, and when an AI agent should stop Failed tool calls and missed handoffs quietly add spend. What to inspect to find where agents break, hand off, or should stop.
- 05 Repeated context and caching: paying for the same tokens Resending the same context on every call adds up. How to spot repeated context in your usage and check whether caching applies.
- 06 AI prompting best practices: structure one prompt well How to word and structure a single prompt: goal, context, constraints, output format, examples. Practical habits, checked against your own results.
- 07 Requirements and task decomposition for AI agents Vague asks turn into long, costly agent runs. How clearer requirements and smaller tasks show up in your usage evidence.
- 08 Unused AI plans, overlap, and limit-driven routing Seats nobody uses, plans that overlap, and work routed by limits not fit. What to check in your seat, plan, and spend records.
- 09 When an existing tool beats an AI agent Some agent work is a job a script, query, or tool you already own does fine. What to check to spot those tasks.
- 10 Before and after: measuring AI quality, cost, and time A change only counts if you can show it. How to compare quality, cost, and time before and after, from your own records.
How a note is built
- 01 Diagnose. Name where the spend is weak.
- 02 Plan. Order what to address first.
- 03 Guide. Start the next review from what was done.