Latest Blogs.

  1. When a RAG system is the wrong answer

    When a RAG system is the wrong answer

    Retrieval-augmented generation is the default answer to adding AI to documents. The four situations where it is the wrong one, and what to build instead.

    3 min read
    • AI
    • Architecture
  2. Context engineering is the new prompt engineering

    Context engineering is the new prompt engineering

    Prompt wording matters less than what the model sees. Context engineering in practice: retrieval, summarisation, exclusion, and a budget for attention.

    2 min read
    • AI
    • Architecture
  3. AI coding agents in production: the review gates that make them safe

    AI coding agents in production: the review gates that make them safe

    Coding agents now write a lot of software. What we put between an agent's output and production: five review gates, why each exists, and what we measure.

    3 min read
    • Engineering
    • AI
  4. What we check before taking over someone else's codebase

    What we check before taking over someone else's codebase

    The audit we run in the first week on an inherited codebase: the eight questions we answer, in order, and what each one tells you about the months ahead.

    3 min read
    • Engineering
    • Process
  5. One agent is usually enough

    One agent is usually enough

    Multi-agent systems are the fashionable architecture. Most problems need one agent with good tools; more is slower and harder to debug. When more is right.

    3 min read
    • AI
    • Architecture
  6. Small models and routing: how we keep AI features affordable

    Small models and routing: how we keep AI features affordable

    The demo used the biggest model for everything. Production cannot. How routing, caching, and small tuned models cut the running cost of AI features by half.

    3 min read
    • AI
    • Engineering
  7. The three architecture decisions that are expensive to reverse

    The three architecture decisions that are expensive to reverse

    Most early technical decisions can be changed later at reasonable cost. Three cannot. How to recognise them, and how to make them well in the first week.

    2 min read
    • Architecture
    • Engineering
  8. What breaks in AI-generated codebases, in the order it breaks

    What breaks in AI-generated codebases, in the order it breaks

    We have audited many codebases built mostly by AI tools. The same seven problems appear in the same order, from week one to month six. How to catch them early.

    3 min read
    • Engineering
    • AI
  9. Postgres is enough, until it is not

    Postgres is enough, until it is not

    One database can be the queue, search index, vector store, and analytics layer for most products. The boring-stack case, and the signals that say add something.

    3 min read
    • Architecture
    • Engineering

Tell us what you are building.

We reply within one business day with how we would build it, what it would cost, and which engagement model fits.

Start a projectnadirhussaint03000@gmail.com
  1. 01
    Tell us what you are building

    A short form or an email. No deck required, and "not sure yet" is a fine answer.

  2. 02
    A call with an engineer

    Within one business day. Technical questions get technical answers, from the person who would build it.

  3. 03
    A written scope and quote

    Fixed price where the scope is defined. The document is yours whether or not you go ahead.