AI
Writing about using AI to build software, improve operational work, and produce clear business results without adding unnecessary complexity.
Almost every browser automation tool claims to be the fastest, the cheapest or the most reliable. I put 34 of them through the same job with the same browser and one independent pass test, then ranked them twice — because speed and real work do not agree.
Read articleA walk through the actual code path: what calls what, in which order, and exactly what data moves between the model, the bridge and the browser.
Read articleCoding agents generate enormous context — sessions, deliverables, files, decisions. The bottleneck isn't generating more; it's finding what you already made. Here's the small glue layer I built to solve exactly that, and why grep, FTS, and RAG each miss part of the problem.
Read articleMy assistant had 343 instruction sheets and could only see a fraction of them. The plain-English version of how I found the gap, why the built-in fix did not help, and what actually changed.
Read articleMy coding agent used to spend extra model turns checking whether tests and deployment had finished. I moved that post-edit work into GitHub Actions on a self-hosted runner. The authoring model now commits, emits CI_HANDOFF and stops.
Read articleHow I use ChatGPT as the controller, a private GitHub control repo and an Actions-dispatched Mac runner as the delivery path, and OMP/GLM as the cheap execution worker — including what broke in the first real end-to-end test.
Read articleThe verified remote coding workflow I now run end to end: ChatGPT plans and reviews, GitHub holds the durable task state, Remote Desktop Commander bridges to the Mac, and a local OMP worker on GLM-5.3-Flash does the implementation.
Read articleA decision playbook for running Codex subagents without token cost surprises — when to delegate, how to bound each worker, and how to measure what it actually cost. Built from three measured experiments on this site.
Read articleThe first AI use case worth doing in a traditional business, how to pick it, and what "clear business value" actually looks like — with a real shipped example and the honest failure modes.
Read articleHow native Codex task controls, strict controller policies, persistent GLM workers and a CLIProxyAPI-to-OpenRouter route moved 92% of one PRD run's uncached prompt volume onto the cheaper model.
Read articleA plain-English guide for anyone who has an idea and a coding agent but no infrastructure experience — jargon explained, tokens stored safely, AGENTS.md doing the operational lifting, and a vendor-neutral way to ship a live website.
Read articleFiles, email, decks, sheets and meetings become a governed markdown layer with named owners, review dates and provenance — so agents retrieve answers that trace to sources instead of folklore.
Read articleThe chronological, evidence-labelled history of one rig's multi-agent architecture — what each layer promised, what the traces said, what was kept, and what was deliberately deleted — with the current recommendation stated plainly.
Read articleA five-question decision rule — ambiguity, repetition, failure cost, real work, auditability — that decides whether a task deserves an agent, a workflow, plain code, or a human decision, worked through real examples from this rig and anonymised agency operations.
Read articleThe measured mechanisms behind agent bloat: context resends, oversight cost, cumulative failures, and the attribution traps that make dashboards lie about all of it.
Read articlePorts, processes, services, containers, and one honest boundary: how a laptop becomes an operations centre you can reach from your phone without exposing anything to the internet.
Read articleA candid case study of the exact execution that shipped this site's solutions/editorial rebuild and visual remediation: a Sol supervisor, a GLM workhorse in an isolated worktree, a bounded Opus review, GLM amendments, and independent parent acceptance — with the failures included.
Read articleA beginner-friendly but technically complete tour of Rajeev's open-source agent telemetry stack: what each piece is, why it exists, where one real request travels, and what the stack still cannot prove.
Read articleA non-technical guide to using capable low-cost AI models for routine work, escalating the decisions that matter, and gradually automating the hand-offs.
Read articleWhat it actually takes to keep a fleet of AI agents doing real work — the contract-first operating loop, the failure modes that eat it, and a checklist you can run tomorrow morning.
Read articleSeven AI workflows run inside real agency operations — briefing, taxonomy governance, QA, evidence packs, reporting, knowledge retrieval, handoffs — with honest limits, human gates, and a map of where the machine earns and where it must stop.
Read articleHow I connected Codex, OpenClaw, OMP and Hermes through the Linux Foundation A2A protocol, proved all 12 routes, and arrived at a much simpler coordination rule.
Read articleA delivery standard for AI-assisted work: raw evidence, provenance, editable deliverables, reconciliation, and review gates — walked through one real build end to end, including the failure that only the evidence caught.
Read articleWhat changed when I separated personal, work and general-purpose AI agents, then made their health, token use, cost and recent activity visible in one private Grafana control room.
Read articleA small OpenRouter routing benchmark made long GLM-5.3-Flash generations 63% faster, but modelling the result against a real day of agent use made the cost trade-off much clearer.
Read articleI ran four layers of orchestration between a request and actual work. The telemetry said most of it was overhead. Here is the before, the after, and the numbers that convinced me.
Read articleI pointed three different AI apps at one local gateway and one OpenRouter account, then wired their usage into self-hosted Langfuse and Grafana. Here is the full path, what it costs to run, and what the first real numbers show.
Read articleHow I publish live Codex and OpenCode usage without publishing prompts, conversations, task names, or private telemetry systems.
Read articleHow I kept Codex for planning and review, moved bounded execution to OpenCode Go, and measured the result without pretending I had proved savings.
Read articleAn agent-readiness audit scored rajeevg.com 69 first and 75 in its refreshed report. Here is what changed, which gaps matter, and why I am not building an API just to chase 100.
Read articleHow I deployed OpenClaw for research and Hermes for engineering as separate agents on a single Hetzner server, coordinated them through authenticated Agent Mail, and wired the result to Vercel deployment.
Read articleI added privacy-conscious session analytics to two agents running on Coolify, found broken Agent Mail calls and wasteful inbox pollers, then rebuilt the idle path to use zero provider tokens.
Read articleHow I rebuilt my Codex subagent setup around reliable browser control, bounded work, recoverable handoffs, and honest token measurement.
Read articleI spent weeks recording how an AI assistant worked on my computer. The real lesson was not about cleverness. It was about repeating myself, checking work it said was finished, and finding a simpler way to work together.
Read articleA plain-English look at how I split Codex work between an OpenAI lead and lower-cost OpenRouter specialists, what the evidence shows, and what it does not.
Read articleA beginner-friendly account of how I connected a local Qwen vision model to Codex, added it to the supported model selector, kept web and image tools working, and fixed a context-breaking image bug.
Read articleA historical walkthrough of the March 2026 server-side analytics build on rajeevg.com, before the live site was simplified back to client-side GTM and GA4 only.
Read articleA detailed engineering walkthrough of the hackathon voting app, from single-screen UX and event-day safeguards to production proof, analytics, and the agent workflow used to ship it.
Read articleA granular walkthrough of the rajeevg.com GA4 property setup, captured during the March 2026 server-side stack pass and kept as a historical property-configuration record.
Read article