Posts

Previous article: Day 5 | Tools as Interface: Built-in, Extensions, Services. Now that you know the three kinds of tools and how to pick a layer, this exercise walks you through installing a new tool with your own hands. This is an L3 exercise article. Navigation for subsequent articles: Day Type Topic Day 7 Backbone Meta-Architecture: Everything is a Plugin Day 8 Backbone Memory, Traces, and Observability Day 9 Exercise Graduation Project: Build a Team-Level CI/CD Automation Harness Day 10 Phase Summary L3 Graduation Assessment + Harness Future Trends The Third Time You Repeat It, Make It a Tool Think about your daily routine for a second. In your agent sessions, do you keep piecing together the same bash command? Checking logs, searching rules, exporting data. Every time, the agent has to guess the parameters all over again and hit the same pitfalls. ...

Previous article: Day 4 | Rewrite Your AGENTS.md and Add Your First Interception Hook. Now that you’ve got constraints locked down, we turn to another core question: how should an Agent’s tools be designed? This is an L3 backbone article. Navigation for subsequent articles: Day Type Topic Day 6 Exercise Add a New Tool to Your Agent Day 7 Backbone Meta-Architecture: Everything is a Plugin Day 8 Backbone Memory, Traces, and Observability Day 9 Exercise Graduation Project: Build a Team-Level CI/CD Automation Harness Day 10 Phase Summary L3 Graduation Assessment + Harness Future Trends A Neglected Fact Over the first four posts we finished two phases: Day 0 built our overall understanding of Harness; Day 1 dissected the essence of the Agent Loop. Then we entered the constraint phase—Day 2 cut away what we didn’t need, Day 3 used contracts and Hooks to keep the Agent in check, and Day 4 had us actually restructure a real project. We constrained the Agent thoroughly. It stopped running wild. ...

Previous article: Day 3 | Harness Hard Constraints: Static Contracts and Lifecycle Hooks. Now that we understand the principles of static contracts and Hooks, this practice session will have us apply these concepts to transform a real project. This is the L3 practice article. Navigation for subsequent articles: Day Type Topic Day 5 Backbone Tools as Interfaces: Three Extension Paths Day 6 Practice Add a new tool to your Agent Day 7 Backbone Meta-Architecture: Everything is a Plugin Day 8 Backbone Memory, Traces, and Observability Day 9 Practice Graduation project: Build a team-level CI/CD automation Harness Day 10 Phase summary L3 graduation assessment + Harness future trends Have You Encountered This? On Day 3, we broke down the two-layer hard constraint mechanism of Harness: static contracts (AGENTS.md defines permission boundaries) and Hook interception (runtime inspection of every tool call). You know what an AGENTS.md looks like and why permission popups are performative security. The concepts are clear, but the moment you apply them to your own project, problems surface. ...

Previous article: Day 2 | Minimalism and Hard Isolation: The Pi Paradigm. Now that we understand why Pi strips features, we now address a more specific question: after the cuts, how should the remaining capabilities be managed? This is the backbone article of L3. Navigation for subsequent articles: Day Type Topic Day 4 Practice Rewrite your AGENTS.md + add an interception Hook Day 5 Backbone Tools as Interfaces: Three Extension Paths Day 6 Practice Add a new tool to your Agent Day 7 Backbone Meta-Architecture: Everything is a Plugin Day 8 Backbone Memory, Traces, and Observability Day 9 Practice Graduation project: Build a team-level CI/CD automation Harness Day 10 Phase summary L3 graduation assessment + Harness future trends The Problem with “Allow Everything” Day 1’s miniharness had 7 tools; Day 2’s Pi cut it down to 4. Regardless of the count, they share a common premise: all tools are available by default. ...

If you use AI to write embedded firmware—specifically bootloader hooks, flashing routines, and signature verification—and then discover that your device behaves completely incorrectly, host tests pass while the real device fails, or the online deployment is still running an old version, this post is for you. Over the last six days, I analyzed the thirteen detours we took during meta-pass v1.0 development. Most were not core technical failures, but rather the same root cause resurfacing in different forms: the task description did not specify what “done” means. ...

Previous post: Day 1 | 120 Lines to Understand the Agent Loop: miniharness Teardown and 3 Counterintuitive Findings. Now that we understand the loop’s core structure, let’s ask a more fundamental question: of the remaining thousands of lines, what belongs and what doesn’t? This is an L3 core lesson. Upcoming navigation: Day Type Topic Day 3 Core Hard constraints in the Harness: static contracts and lifecycle hooks Day 4 Exercise Rewrite your AGENTS.md + add an interception hook Day 5 Core Tools as interface: three extension paths Day 6 Exercise Give your Agent a new tool Day 7 Core Meta-architecture: Everything is a Plugin Day 8 Core Memory, traces, and observability Day 9 Exercise Capstone: build a team-level CI/CD automated Harness Day 10 Wrap-up L3 graduation assessment + Harness future trends Why “More Features” Is a Reverse Optimization In Day 1 we dismantled the loop, showing that the core logic takes only about a hundred lines; the remaining thousands consist of structure, constraints, tools, permissions, and planning modes—all the extra capabilities designed to let Agents “do more things.” ...

meta-pass is a multi-firmware launcher I wrote for AI Passport. A persistent launcher sits on the device, firmware images are installed into Flash slots and you select which one to boot from a startup list instead of reflashing the whole device every time. The two-day MVP process is documented in the previous post. Not useful. This thing takes up 3MB, leaving only two 2MB slots. Anything slightly practical won’t fit. The comment was mostly right. Over the next six days, I submitted 90 commits, working through eight comments one by one and iterated meta-pass from MVP to v1.0: three slots, signature badges, backup and restore, single-file firmware, data-safe upgrades, bootloader hardening and a USB speedup. Most of the v1.0 changes were directly driven by those comments. ...

Last week I got a FoloToy AI Passport, an AI conversation toy driven by an ESP32. It has a plays marketplace with quite a few firmware toys[1]. A couple caught my eye: one turns the device into a walkie-talkie over Bluetooth, another uses BLE for a radar treasure hunt. Plenty of community work worth trying too. Lots of toys, but one awkward reality: the device runs only one firmware at a time. Switching from the walkie-talkie to the treasure hunt means opening a laptop, plugging in a cable, and reflashing the entire chip. Once you reflash, the previous toy is gone. Out in the park with my kid, one minute it’s the walkie-talkie; if the next minute calls for the radar game, too bad. That has to wait until we get home. ...

Previous post: Day 0 | L3 Kickoff: A Short History of Harnesses, From Your Batch Script to Pi and DeepSeek Harness. Make sure you understand the Harness concept from Day 0 and the API calls from L2 Days 0-3, and let’s start dismantling the loop. This is an L3 exercise post. Upcoming navigation: Day Type Topic Day 2 Core Constraints and interception: hooks and permissions Day 3 Exercise Adding an approval gate with hooks Day 4 Core Extensions vs plugins: Pi vs DSH Day 5 Exercise Writing a Pi extension Day 6 Exercise Composing DSH Cordis plugin modes Day 7 Core Agent Teams and task DAGs Day 8 Core Memory and learning: Hermes, Nowledge Mem, EvoMap Day 9 Exercise Designing your own skill system Day 10 Wrap-up L3 graduation check Why This Is an Exercise Post The previous post traced the evolution of Harnesses. From Anthropic’s controlled experiment to the Pi and DeepSeek Harness routes, we learned one thing. Beyond the model, that guiding structure is what actually decides success. ...

Previous post: Day 16: L2 Complete! Next Stop: Harness Engineering Evolution and the L3 Blueprint. Make sure you have understood or mastered the skills Day 16 covered, and let’s start L3 from here. This is the L3 entry point. Upcoming posts: Day Type Topic Day 1 Exercise Reading the Agent Loop in 120 lines Day 2 Core Constraints and interception: hooks and permissions Day 3 Exercise Adding an approval gate with hooks Day 4 Core Extensions vs plugins: Pi vs DSH Day 5 Exercise Writing a Pi extension Day 6 Exercise Composing DSH Cordis plugin modes Day 7 Core Agent Teams and task DAGs Day 8 Core Memory and learning: Hermes, Nowledge Mem, EvoMap Day 9 Exercise Designing your own skill system Day 10 Wrap-up L3 graduation check Start by Remembering Your Day 4 Script Think back to Day 4 of L2. In that lesson we wrote a batch script: read files from a folder, call the API on each one, write the results back, and when a step failed, log the error first, then keep going. ...