How Gauges Green builds the harness behind the practice. Real work, shipped to production.https://www.gaugesgreen.com/en-ushttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Replaced a 'never batch a risky send' rule that lived only as a design guideline with a hardcoded exclusion checked first in the code that decides what gets grouped together. A safety rule that exists as policy instead of as code is exactly the gap a shared verification layer elsewhere in the system already exists to close.Thu, 09 Jul 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Fixed a bug where any meeting task with no listed owner was silently assumed to be Ryan's, including items that clearly belonged to someone else based on what they said. A safe-sounding default (nothing gets lost) turned out to be worse than the failure it was designed to prevent, once the real risk was misattribution rather than omission.Wed, 08 Jul 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Turned on the internal ops app's own dark mode, then ran a real contrast scan against it instead of trusting how it looked. Found two accessibility failures a static review would have missed, including a status indicator that measured well under the required contrast ratio. Shipping a feature and shipping an accessible feature turned out to be two different claims, and only the live scan proved the second one.Wed, 08 Jul 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/llm-not-x-but-y/https://www.gaugesgreen.com/log/llm-not-x-but-y/A sourced explanation for the negation-then-reframe sentence that keeps showing up in AI-generated prose.Thu, 21 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/boot-card/https://www.gaugesgreen.com/log/boot-card/The Boot Card turns agent startup into an operator readout: mission, goal progress, and top priorities visible before the session starts.Tue, 19 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Kept the verification gate in shadow after the v9 bake review. Zero post-May-11 Stop-hook rows is not clean evidence. High-volume blockers need labeled shadow data or replay, not silence.Mon, 18 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Closed a direct-send safety gap by requiring approval envelopes at the WhatsApp send-script boundary. Hook-only safety is not enough when multiple runtimes can reach the same sender.Mon, 18 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Restored routed-memory freshness by giving the context router its own 5-minute scheduler. A live inbox is not enough if the routed memory layer is stale.Mon, 18 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Turned Proof Scout into an active detector for marketing proof moments. It scans recent harness work and prompts for the screenshot, redaction, filename, and likely use while the evidence is still fresh.Fri, 15 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Accepted the Codex Telegram runtime by explicit override while keeping the readiness basis visible. A human override is valid only if the telemetry says it was an override, not a clean bake.Wed, 13 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Shipped an active source-fidelity gate for public and client-adjacent claims. Unsupported claims now need a source, a hypothesis label, or a validation-question frame.Tue, 12 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/AI coding agents are not mainly a coding problem. They force product decisions, tests, review, release, security, and monitoring into a production system that humans can steer.Mon, 11 May 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Collapsed the system name into the company. Gauges Green is now both the practice and the harness. Single brand across both. Andale becomes the boot injector subsystem (replacing Arriba). All other subsystem names unchanged.Sun, 26 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/piper-not-dormant/https://www.gaugesgreen.com/log/piper-not-dormant/Three weeks of an agent appearing dormant turned out to be a 30-second pairing handshake. Distribution failures look identical to production failures from the consumer's perspective.Sat, 25 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built Pluma, a document pipeline that turns Markdown into branded Google Docs. Same source file produces the website version and the client-facing version. Sharing is a separate, gated action.Sun, 12 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/An agent fabricated quotes in a $3K/mo client-facing synthesis doc. Built a source fidelity gate: 7 new rules that mechanically block unverified claims from reaching clients. The model is not the moat. The gate is.Sun, 12 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Shipped the Jamie meeting transcription pipeline end to end. Webhook receiver with HMAC verification, per-speaker attribution, action items extracted and routed to the right agent automatically.Sun, 12 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Named the harness parts. Andale opens agent sessions. Pulse watches inbound channels. Dispatch manages tasks. Scribe captures meetings. Pluma renders deliverables. Critique checks quality. Snitch audits outbound sends.Sun, 12 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Killed a potential Zoom AI Companion migration in an hour by verifying four independent kill criteria before writing a single line of code. The 30-second search that saves the 90-minute build.Sat, 11 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Ran a full market eval of bot-free meeting transcription tools in a single session. Reversed the verdict three times as new constraints surfaced. Ended on Jamie after ruling out Fireflies, Otter.ai (active wiretapping lawsuit), Granola (2-stream limit), and six others.Sat, 11 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Migrated all 7 agents from Slack to Telegram in a single afternoon. One new transport module, five script patches. The agents kept working through the transition.Sat, 11 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Shipped Client Mode Phase 1. Agent recommendations are now tier-scoped per client. A $1K/mo engagement gets one next step per session. A $15K/mo engagement gets five. The tier rules are injected at boot, not left to judgment.Fri, 10 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Pressure-tested a client's new monetization thesis against their own CRM data on day one of the engagement. The compiled context surfaced three inconsistencies between what the team believed and what their pipeline showed.Fri, 10 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Type a client codename and a dedicated Opus session opens with that client's entire vault: goals, product roadmap, meeting transcripts dating back to the first call, every email thread. Nothing else loaded. No cross-client bleed.Thu, 09 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Added session resume. Close a client session, reopen it the next day, and the agent picks up exactly where you left off with a lightweight delta of what changed overnight.Thu, 09 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/CamTune (now Ojo) optimizes against what video call participants actually see, not the raw camera feed. Switched from camera capture to window capture. Your Zoom tile is the optimization target.Thu, 09 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built a knowledge wiki using the Karpathy pattern. LLM-compiled reference articles from 638 Lenny Rachitsky episodes and 156 Marketing Examples posts. Agents cite compiled reference material from the wiki instead of hallucinating advice.Wed, 08 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Shipped 611 tests across the harness. Started at zero in late March. The suite catches contract mismatches between pipeline components before they reach production.Wed, 08 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built implicit performance tracking. A plugin detects approvals and corrections from natural conversation without any special syntax. 5,200 scored interactions across 7 agents. The data showed 56% approval in general chat, 98% in dedicated client sessions.Tue, 07 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Upgraded all 7 agents from Sonnet to Opus for interactive sessions. 192 corrections traced to model capability, not bad instructions. Heartbeats stay on a cheap model. Three-tier routing: Opus for client work, Sonnet for background tasks, DeepSeek for breathing.Tue, 07 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Pulse was feeding every agent all 323 contacts and 24 cross-domain projects. The marketing agent got fitness protocols. The Spanish tutor got deal pipelines. Added domain filtering so each agent sees only what belongs to its world.Tue, 07 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Distilled 192 agent corrections into 31 behavioral rules and deployed them as mechanical enforcement. A gateway plugin blocks unauthorized external sends before they leave the system. Rules in a prompt are suggestions. This is a safeguard.Mon, 06 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Diagnosed why agents kept asking me to explain my own life every 48 hours. Working memory had no persistent layer. Added durable knowledge sections that survive automatic context refreshes.Mon, 06 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Every agent now knows which topics belong to which peer and routes accordingly. Previously one of seven had explicit domain boundaries. The chief of staff was texting me about fitness supplements at 5 AM.Mon, 06 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Added a governance rule for runtime upgrades: package changes require a dedicated session with rollback. The harness can move quickly without letting a routine upgrade take down the workday.Mon, 06 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built gateway cost tracking after the dashboard showed $146/day but only $3-5 was actually billed. The rest was covered by a flat-rate plan. Without separating billing tiers, every cost report was fiction.Mon, 06 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built tab notifications for the terminal. When an agent finishes thinking, the tab lights up with a bell icon and a colored border. Small thing. Eliminated 30 minutes of daily context-switch overhead.Sun, 05 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Launched a family WhatsApp group with the chief-of-staff agent as coordinator. It recommends restaurants with walk-time estimates and handles scheduling. My wife uses it more than I do.Sun, 05 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/One command shows full system health across 7 dimensions. Pipeline freshness, credential TTLs, agent payload staleness, delivery timeouts, contract test results. Replaced inspecting 17 scattered JSON files.Sun, 05 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built a shared context layer so all 7 agents know about each other. Two tiers: universal awareness for everyone, business context only for agents that need it. No cross-domain bleed.Fri, 03 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Published the first engineering scorecard across 8 pillars. Architecture was already strong. Observability and engineering quality became the load-bearing improvement areas.Fri, 03 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Type "piper" in any terminal and a session opens with that agent's full compiled context. Identity, architecture, domain knowledge, live task state. Zero file reads. The CLI is the interface.Thu, 02 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Swapped 7 agent heartbeats from a 671B parameter model to a 3B parameter model. Same job, 85% cost reduction. Low-reasoning tasks run 100x more often than deep work, so model choice there dominates cost.Thu, 02 Apr 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built two-stage CI/CD. Local commit hook under 15 seconds, remote GitHub Actions for the full suite. Path filtering so a docs change doesn't trigger a build test.Mon, 30 Mar 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Took the codebase from D- to A-. 213 bare exception handlers eliminated. 876 print() calls converted to structured logging. 200 unit tests from zero. 14 shared libraries extracted from 5 monolithic scripts.Sat, 28 Mar 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Shipped the intent engine. 31 detectors scan Gmail, Calendar, iMessage, WhatsApp, and task state every 5 minutes. Each agent gets a ranked priority queue of what needs attention right now. The system's nose for what matters.Sun, 15 Mar 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/One 400-line SOP.md that teaches Claude permission to deploy autonomously. Features go from code to production in a single conversation. No staging environment, no manual deploys.Sun, 01 Mar 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built Flare after a single session burned 430M tokens in 90 minutes from an auto-compact loop. Three-layer monitoring: a Claude Code hook tracks usage in real time, a daemon projects pace against the billing window, and the agent sees the projection at boot.Tue, 24 Feb 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built the boot compiler that gives each agent source-backed operating context. 350 lines of Python, runs every 5 minutes, produces per-agent payloads up to 306KB. Seven agents boot with their domain state already assembled.Thu, 19 Feb 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built Pulse, the unified inbox. iMessage, WhatsApp, Apple Notes, Slack, Gmail, Granola normalized into one JSONL stream. 37 iMessages and 219 Apple Notes flowed in on the first run. Every agent reads one file.Thu, 19 Feb 2026 00:00:00 GMThttps://www.gaugesgreen.com/log/https://www.gaugesgreen.com/log/Built Critique, a two-layer design quality gate. Code analysis checks source files for wrong patterns. Playwright captures screenshots in four variants and Claude vision judges the pixels. The design system document is the rule engine.Tue, 20 Jan 2026 00:00:00 GMT