Skip to main content
// series

Agent reliability

Most agent demos stop at "it worked once." This series is the other half: permissions, undo, traces, handoffs, evals — the reliability work you do before autonomy is safe to ship.

7 posts · oldest first

  1. 2026.066 min

    Agents Fail Quietly

    A passing test and a working workflow are not the same thing. The gap between them is where production breaks.

  2. 2026.076 min

    Give Your Agent an Undo Button

    You can bound what an agent touches and measure when it fails. Neither one saves you if the mistake it makes cannot be taken back.

  3. 2026.076 min

    Teach Your Agent to Ask for Help

    Full autonomy is the wrong goal. The best agents know exactly when to stop and hand the decision back to you.

  4. 2026.076 min

    Trust Comes From the Trace

    You bounded what your agent can touch, gave it an undo button, and taught it when to ask. But when it does something surprising, can you reconstruct exactly why? That is the observability gap.

  5. 2026.077 min

    Your Second Agent Is the Hard One

    Going from one agent to many does not multiply what you can do. It moves every failure into the space between them.

  6. 2026.087 min

    The Handoff Is Where Agents Break

    You debug the agent that produced the bad output. The bug was in the message it got handed.

  7. 2026.088 min

    Your Eval Suite Measures the Wrong Thing

    Nearly a quarter of what goes wrong in multi-agent systems is a verification failure. The most common one is a check that ran, and said yes.

back to /blog/