Blog

Notes from building Rindo on how software gets made when an assistant or an agent does part of the work, and where people still have to stand. The ten articles are one line of argument; read them in order or pick the one you need.

  1. Prompt, context, loop, harness

    Four words that get used as one. A map of the layers, what each one asks, and why the loop that checks the work is where most agents break.

    2026-10-12 · 6 min read

  2. The bottleneck moved from writing code to checking it

    Generation got cheap and verification did not. The words that grew around that gap, the anti-patterns they name, and the one principle that falls out.

    2026-10-12 · 5 min read

  3. Acceptance criteria that close the intent gap

    An agent fills every silence in a spec with a guess. Six ways to leave less silence, one worked example, and how to keep the spec short anyway.

    2026-10-12 · 6 min read

  4. Ten more ways to narrow the intent gap

    Say it without prose, draw it out by interaction, check the reading before you pay. And how to get an assistant to interview you properly.

    2026-10-12 · 6 min read

  5. Where people belong in a pipeline run by agents

    Six layers, three new bottlenecks, what to measure, and how analysts, testers and product managers move from producing to judging.

    2026-10-12 · 8 min read

  6. After the intent gap

    Three gaps that build up quietly once every feature is understood: comprehension, coherence, continuity. Why going back is wrong, and what to spend instead.

    2026-10-12 · 6 min read

  7. System design when code is cheap

    The price list of design decisions has inverted. Six principles, and a rule for how much to fix before any code is written.

    2026-10-12 · 8 min read

  8. Design docs that are not homework

    A generated design document reads like an assignment handed in: complete, fluent, and useless to the phases after it. The mechanism, and the three kinds of document that fix it.

    2026-10-12 · 5 min read

  9. Decomposition, the task graph and the plan gate

    How to cut work for agents that run in parallel, what happens to the planning phase, and five questions to ask of a plan before a line is written.

    2026-10-12 · 11 min read

  10. A verification stack in four ideas

    Five layers, where each behaviour gets proven, what becomes of test specifications and manual testing, and the loop that keeps the stack alive.

    2026-10-12 · 13 min read

Outside the series

  1. Fixed price, AI-generated code, and the warranty period

    What changes in the arithmetic of a contract when the code is generated: the warranty, the scope, the milestones, and the part of the work that will still be ordered.

    2026-10-12 · 8 min read