Suraj LabProduction systems and local-first AI tools.

Writing

Writing, in reading order.

Two tracks: systems that carry state over time, and agent workflows that can be verified end to end.

Essays

10

Tracks

2

Systems With Continuity

Essays on memory, governed state, adaptation, and why useful software should compound over time.

4 essays
  1. 01

    Software Is Shifting From Tools to Systems

    The real change is not that models can answer better. It is that useful software now needs loops for observation, correction, and carried state.

    3 min
  2. 02

    The Demo Works. The Fifth Run Doesn’t.

    First-run output is the easiest benchmark. Repeated work is where weak continuity shows up.

    3 min
  3. 03

    Most AI Agents Don’t Improve Over Time

    Repeated work should compound. Most agents still recompute.

    3 min
  4. 04

    Context Is Not Memory

    Memory that affects behavior needs status, provenance, correction, contradiction handling, and revocation.

    3 min

Reliable Agent Systems

Essays on coding agents, verification, orchestration, and the structure required to ship working software.

6 essays
  1. 05

    Why Most Coding Agents Still Don’t Ship Working Software

    Plausible code is local success. Shipping software requires design, verification, runtime checks, and carry-forward knowledge.

    3 min
  2. 06

    Deterministic Gates Beat Prompt-Only Control

    If a rule matters, move it out of the prompt and into the harness.

    3 min
  3. 07

    The Goal Is Not Multi-Agent. The Goal Is Reliable Software

    Extra agents only earn their place when they isolate a recurring failure mode.

    3 min
  4. 08

    Building a Coding Agent That Actually Ships

    A Claude Code plugin for turning vague software ideas into reviewed, tested, committed code.

    10 min
  5. 09

    What Building This Taught Me About Diagnosis, Not Retries

    Repeated failure usually means the system needs a different model of the problem, not another attempt.

    3 min
  6. 10

    Using coding-agent to Build a Local-First Knowledge Base

    The repo tells two separate stories: a markdown-first knowledge base with one shared core, and a coding-agent workflow whose rules and artifacts stayed visible in the tree.

    4 min