Thread · version 3 · · written with Claude Opus 5.5

The Last Mile in Post-AI Software

There are still seven areas where AI hits a bottleneck:

  1. Intent: deciding what to build, for whom, and what "done" looks like.

    • Questions: What's the goal and how do we measure it? What's out of scope? Who makes the final call?
    • Examples: writing the spec and success metrics; choosing which feature ships first; cutting a feature that works but doesn't fit.
  2. Authority: granting the system access to accounts, credentials and money.

    • Questions: Which systems can the agent read and write? Who issues and rotates the keys? What's the damage if a key leaks?
    • Examples: setting up a key manager and creating scoped API keys; opening cloud and billing accounts; registering the domain, DNS and OAuth apps.
  3. Ground truth: finding out whether it works for real people in real conditions.

    • Questions: Has a real user completed the core flow? What do production metrics show? What broke that the tests missed?
    • Examples: running sessions with five real customers; watching error rates and logs after launch; running an A/B test on live traffic.
  4. Acceptance: getting others to choose it, or at least allow it.

    • Questions: Will the buyer pay or switch? Do their security and legal teams approve? Will the platform or regulator allow it?
    • Examples: closing the first paying customer; passing a customer's security questionnaire; getting through app store review.
  5. Accountability: putting a name on the line for security and failures.

    • Questions: Who signs off on security? Who's on call? Who's liable if data leaks?
    • Examples: commissioning a pen test and signing off the findings; auditing dependencies for supply-chain risk; setting up the on-call rotation and incident plan.
  6. Stopping: breaking the loop when the work stops paying off, whether through overthinking, perfectionism or going in circles.

    • Questions: Is it still making progress, or repeating itself? Is this good enough to ship? What is another hour worth here?
    • Examples: stopping an agent that keeps reopening the same refactor; shipping a v1 with known rough edges; telling it to stop researching and pick an option.
  7. Comprehension: understanding what was built, well enough to steer it, explain it and fix it.

    • Questions: Can I explain how it works without asking the AI? What did it decide that I never asked for? If it breaks tonight, does someone know where to look?
    • Examples: reading the diff before it merges; keeping a log of why things were built the way they were; walking a teammate through the system.
Changelog
  • · v3 · Adds a seventh area: comprehension
  • · v2 · The table is now a list, easier to read on a phone
  • · v1 · First version

Machine-readable: item JSON

All posts · RSS