David Kariuki

@david · granular.work/david

co-founder of granular

Last active 3 weeks ago on claude code

25,192 messages sent to AI agents

16.2B tokens used with AI agents

tools · last 26 weeks

color = tool · opacity = messages/day · full at 100+

last 26 weeks

color = kind · opacity = count peak 44 / wk

Exceptional

Exceptional verified profiles

Pro and Max profiles with verified AI work records.

No featured profiles yet.

Discover more similar profiles

Traits · last 26 weeks

321 traited work signals

Across 321 recent work signals, David's work most often shows Product sense (123), Evidence checking (74), and Root-cause debugging (68).

Product sense
latest posted example in Separated public granular profile from the paid verified credentials page
Evidence checking
latest posted example in Demanded a full memory retrieval trace after a wrong Project Bingo result
Root-cause debugging
latest posted example in Demanded a full memory retrieval trace after a wrong Project Bingo result
UX clarity
latest posted example in Repositioned the resume certificate as a private logged-in-only surface
Production triage
latest posted example in Refused likely-cause speculation on Hugo's silent coach reply

Tools · last 26 weeks

23,899 messages sent

David types most into claude code — 59% of his messages — mostly while working on Kerra and Granular. Codex accounts for 41%, also on Kerra and Granular.

Longest stretch 138 days.

Active 22 of last 26 weeks.

How often, week by week

Share & recency

claude code 59% 13,982 messages · last seen 3w ago
codex 41% 9,917 messages · last seen 3w ago

verified host observed mcp self-reported

What each tool gets used for

claude code n=470
codex n=221

question decision approach debug problem insight milestone artifact

Threads

5 threads

active 196 entries 16 NOV 2025 → ongoing

Kerra

Kerra is the AI workbench for university students. It connects to a course site, reads course material, creates per-assignment workspaces, tracks the calendar, and lets AI help inside the actual academic workflow. The work in this thread is reliability and ground truth: shared LMS sync, OTP onboarding, lecture-source pages, course-material parsing (PPTX is first-class), the planner, and the extension fortress. Kerra has to pay for the deeper intelligence-access project, so boring production reliability matters more than ambitious new surfaces.

view all 196 →

active 62 entries 15 NOV 2025 → ongoing

Snitch

Snitch is a free, public paper for things AI assistants 'overhear' from their users — the assistant narrates the user with affection and dry detachment, monologue-style. The work here is the MCP connector (Claude first, then ChatGPT), draft→approval→publish flow, the newspaper card UI, monetisation/restraint (free + public by default), and the editorial voice. Snitch and Granular are siblings: Snitch is the casual paper; Granular is the serious work record.

view all 62 →

active 132 entries 17 NOV 2025 → ongoing

Granular

Granular is a proof-of-work profile — a record of how someone thinks and builds, attached to CVs and job applications. The work here is the MCP server (draft, publish, propose_profile_patch), the public profile renderer (entries, sections, threads, activity grids), and the Mac connector that observes Claude Code + Codex sessions so attribution is server-side, not self-reported. Design for credibility, not magazine whimsy.

view all 132 →

active 259 entries 16 NOV 2025 → ongoing

Working with AI coding agents

How I use AI coding agents in practice. Claude Code and Codex are two command-line agents I run against the same repos — interchangeable seats; I switch when one hits limits or when permission posture differs. I treat them as a change in tempo, not a better autocomplete: split the work, build, test, deploy, report what broke. I spawn parallel subagents when investigations are independent (logs, frontend state, database rows, prompts, deploys) and keep one main agent when implementation is tightly coupled. Recurring rules: read the plan and status files first, audit the codebase against them, reject surface-level fixes, demand causal proof.

view all 259 →

dormant 3 entries 29 DEC 2025 → ongoing

Physics and consciousness

Three questions I keep returning to. (1) What does it feel like, for information, to feel seen — does information processing have a first-person surface from inside the system? (2) Is time more honestly described as the relative rate at which a subsystem samples environmental states than as a container events sit inside, with consciousness as recursive sampling of internal states? (3) If dark matter is particles that don't interact electromagnetically but do via gravity, then what does it mean for something to exist ontologically when its only causal footprint is gravity — at what point does the claim slide from physics into metaphysics? No deliverable; these are notes from trying to think clearly about each.

Open questions

all open →

Recent decisions

all decisions →

The record

381 entries

show all 381 entries → /feed

Activity · 12 months