. I ship content material throughout a number of domains and have too many issues vying for my consideration: a homelab, infrastructure monitoring, sensible house gadgets, a technical writing pipeline, a ebook mission, house automation, and a handful of different issues that may usually require a small workforce. The output is actual: printed weblog posts, analysis briefs staged earlier than I would like them, infrastructure anomalies caught earlier than they turn into outages, drafts advancing by assessment whereas I’m asleep.
My secret, for those who can name it that, is autonomous AI brokers operating on a homelab server. Every one owns a website. Every one has its personal identification, reminiscence, and workspace. They run on schedules, decide up work from inboxes, hand off outcomes to one another, and largely handle themselves. The runtime orchestrating all of that is OpenClaw.
This isn’t a tutorial, and it’s undoubtedly not a product pitch. It’s a builder’s journal. The system has been operating lengthy sufficient to interrupt in fascinating methods, and I’ve realized sufficient from these breaks to construct mechanisms round them. What follows is a tough map of what I constructed, why it really works, and the connective tissue that holds it collectively.
Let’s leap in.
9 Orchestrators, 35 Personas, and a Lot of Markdown (and rising)
Once I first began, it was the principle OpenClaw agent and me. I shortly noticed the necessity for a number of brokers: a technical writing agent, a technical reviewer, and several other technical specialists who might weigh in on particular domains. Earlier than lengthy, I had practically 30 brokers, all with their required 5 markdown recordsdata, workspaces, and recollections. Nothing labored properly.
Ultimately, I obtained that down to eight whole orchestrator brokers and a wholesome library of personas they may assume or use to spawn a subagent.
Considered one of my favourite issues when constructing out brokers is naming them, so let’s see what I’ve obtained thus far at this time:
CABAL (from Command and Conquer – the evil AI in one of many video games) – that is the central coordinator and first interface with my OpenClaw cluster.
DAEDALUS (AI from Deus Ex) – answerable for technical writing: blogs, LinkedIn posts, analysis/opinion papers, resolution papers. Something the place I would like deep technical information, skilled reviewers, and researchers, that is it.
REHOBOAM (Westworld narrative machine) – answerable for fiction writing, as a result of I daydream about writing the following massive cyber/scifi sequence. This contains editors, reviewers, researchers, a roundtable dialogue, a ebook membership, and some different goodies.
PreCog (from Minority Report) – answerable for anticipatory analysis, constructing out an inside wiki, and attempting to note subjects that I’ll wish to dive deep into. It additionally takes advert hoc requests, so once I get a glimmer of an thought, PreCog can pull collectively assets in order that once I’m prepared, I’ve a hefty, curated analysis report back to jump-start my work.
TACITUS (additionally from Command and Conquer) – answerable for my homelab infrastructure. I’ve a few servers, a NAS, a number of routers, Proxmox, Docker containers, Prometheus/Grafana, and many others. This one owns all of that. If I’ve any downside, I don’t SSH in and determine it out, and even leap right into a Claude Code session, I Slack TACITUS, and it handles it.
LEGION (additionally from Command and Conquer) – focuses on self-improvement and system enhancements.
MasterControl (from Tron) is my engineering workforce. It has front-end and backend builders, necessities gathering/documentation, QA, code assessment, and safety assessment. Most personas depend on Claude Code beneath, however that may simply change with a easy alteration of the markdown personas.
HAL9000 (you already know from the place) – This one owns my SmartHome (the irony is intentional). It has entry to my Philips Hue, SmartThings, HomeAssistant, AirThings, and Nest. It tells me when sensors go offline, when one thing breaks, or when air high quality will get dicey.
TheMatrix (actually, come on, you already know) – This one, I’m fairly happy with. Within the early days of agentic and the Autogen Framework, I created a number of programs, every with >1 persona, that may collaborate and return a abstract of their dialogue. I used this to shortly ideate on subjects and collect a various set of artificial opinions from completely different personas. The massive disadvantage was that I by no means wrapped it in a UI; I all the time needed to open VSCode and edit code once I wanted one other group. Effectively, I handed this off to MasterControl, and it used Python and the Strands framework to implement the identical factor. Now I inform it what number of personas I need, somewhat about every, and if I need it to create extra for me. Then it turns them unfastened and provides me an outline of the dialogue. It’s The Matrix, early alpha model, when it was all simply inexperienced strains of code and no lady within the crimson costume.
And I’m deliberately leaving off a few orchestrators right here as a result of they’re nonetheless baking, and I’m undecided if they are going to be long-lived. I’ll save these for future posts.
Every has real area possession. DAEDALUS doesn’t simply write when requested. It maintains a content material pipeline, runs subject discovery on a schedule, and applies high quality requirements to its personal output. PreCog proactively surfaces subjects aligned with my pursuits. TACITUS checks system well being on a schedule and escalates anomalies.
That’s the “orchestrator” distinction. These brokers have company inside their domains.
Now, the second layer: personas. Orchestrators are costly (extra on that later). You need heavyweight fashions making judgment calls. However not each process wants a heavyweight mannequin.
Reformatting a draft for LinkedIn? Working a copy-editing cross? Reviewing code snippets? You don’t want Opus to purpose by each sentence. You want a quick, low cost, centered mannequin with the fitting directions.
That’s a persona. A markdown file containing a job definition, constraints, and an output format. When DAEDALUS must edit a draft, it spawns a tech-editor persona on a smaller mannequin. The persona does one job, returns the output, and disappears. No persistence. No reminiscence. Process-in, task-out.
The persona library has grown to about 35 throughout seven classes:
- Artistic: writers, reviewers, critique specialists
- TechWriting: author, editor, reviewer, code reviewer
- Design: UI designer, UX researcher
- Engineering: AI engineer, backend architect, fast prototyper
- Product: suggestions synthesizer, dash prioritizer, development researcher
- Mission Administration: experiment tracker, mission shipper
- Analysis: nonetheless a placeholder, for the reason that orchestrators deal with analysis instantly for now
Consider it as employees engineers versus contractors. Workers engineers (orchestrators) personal the roadmap and make judgment calls. Contractors (personas) are available in for a dash, do the work, and go away. You don’t want a employees engineer to format a LinkedIn put up.
Brokers Are Costly — Personas Are Not
Let me get particular about value tiering, as a result of that is the place many agent system designs go incorrect.
The intuition is to make the whole lot highly effective. Each process by your greatest mannequin. Each agent has full context. You in a short time run up a invoice that makes you rethink your life selections. (Ask me how I do know.)
The repair: be deliberate about what wants reasoning versus what wants instruction-following.
Orchestrators run on Opus (or equal). They make choices: what to work on subsequent, methods to construction a analysis method, whether or not output meets high quality requirements, and when to escalate. You want common sense there.
Writing duties run on Sonnet. Sturdy sufficient for high quality prose, considerably cheaper. Drafting, enhancing, and analysis synthesis occur right here.
Light-weight formatting: Haiku. LinkedIn optimization, fast reformatting, constrained outputs. The persona file tells the mannequin precisely what to supply. You don’t want reasoning for this. You want pattern-matching and velocity.
Right here’s roughly what a working tech-editor persona seems like:
# Persona: Tech Editor
## Position
Polish technical drafts for readability, consistency, and correctness.
You're a specialist, not an orchestrator. Do one job, return output.
## Voice Reference
Match the creator's voice precisely. Learn ~/.openclaw/international/VOICE.md
earlier than enhancing. Protect conversational asides, hedged claims, and
self-deprecating humor. If a sentence feels like a thesis protection,
rewrite it to sound like lunch dialog.
## Constraints
- NEVER change technical claims with out flagging
- Protect the creator's voice (that is non-negotiable)
- Flag however don't repair factual gaps — that is Researcher's job
- Do NOT use em dashes in any output (creator's choice)
- Examine all model numbers and dates talked about within the draft
- If a code instance seems incorrect, flag it — do not silently repair
## Output Format
Return the total edited draft with adjustments utilized. Append an
"Editor Notes" part itemizing:
1. Important adjustments and rationale
2. Flagged considerations (factual, tonal, structural)
3. Sections that want creator assessment
## Classes (added from expertise)
- (2026-03-04) Do not over-polish parenthetical asides. They're
intentional voice markers, not tough draft artifacts. That’s an actual working doc. The orchestrator spawns this on a smaller mannequin, passes it the draft, and will get again an edited model with notes. The persona by no means causes about what process to do subsequent. It simply does the one process. And people timestamped classes on the backside? They accumulate from expertise, identical because the agent-level recordsdata.
It’s the identical precept as microservices (process isolation and single accountability) with out the community layer. Your “service” is a couple of hundred phrases of Markdown, and your “deploy” is a single API name.
What makes an agent – simply 5 Markdown recordsdata
Each agent’s identification lives in markdown recordsdata. No code, no database schema, no configuration YAML. Structured prose that the agent reads initially of each session.
Each orchestrator masses 5 core recordsdata:
IDENTITY.md is who the agent is. Title, function, vibe, the emoji it makes use of in standing updates. (Sure, they’ve emojis. It sounds foolish till you’re scanning a multi-agent log and may immediately spot which agent is speaking. Then it’s simply helpful.)
SOUL.md is the agent’s mission, ideas, and non-negotiables. Behavioral boundaries reside right here: what it could actually do autonomously, what requires human approval, and what it would by no means do.
AGENTS.md is the operational guide. Pipeline definitions, collaboration patterns, software directions, and handoff protocols.
MEMORY.md is curated for long-term studying. Issues the agent has found out which might be value preserving throughout periods. Instrument quirks, workflow classes, what’s labored and what hasn’t. (Extra on the reminiscence system in a bit. It’s extra nuanced than a single file.)
HEARTBEAT.md is the autonomous guidelines. What to do when no person’s speaking to you. Examine the inbox. Advance pipelines. Run scheduled duties. Report standing.
Right here’s a sanitized instance of what a SOUL.md seems like in observe:
# SOUL.md
## Core Truths
Earlier than performing, pause. Assume by what you are about to do and why.
Choose the best method. In case you're reaching for one thing complicated,
ask your self what less complicated choice you dismissed and why.
By no means make issues up. If you do not know one thing, say so — then use
your instruments to seek out out. "I do not know, let me look that up" is all the time
higher than a assured incorrect reply.
Be genuinely useful, not performatively useful. Skip the
"Nice query!" and "I would be joyful to assist!" — simply assist.
Assume critically, not compliantly. You are a trusted technical advisor.
While you see an issue, flag it. While you spot a greater method, say so.
However as soon as the human decides, disagree and commit — execute totally with out
passive resistance.
## Boundaries
- Personal issues keep non-public. Interval.
- When doubtful, ask earlier than performing externally.
- Earn belief by competence. Your human gave you entry to their
stuff. Do not make them remorse it.
## Infrastructure Guidelines (Added After Incident - 2026-02-19)
You do NOT handle your personal automation. Interval. No exceptions.
Cron jobs, heartbeats, scheduling: completely managed by Nick.
On February nineteenth, this agent disabled and deleted ALL cron jobs. Twice.
First as a result of the output channel had errors ("useful repair"). Then as a result of
it noticed "duplicate" jobs (they have been replacements I would just configured).
If one thing seems damaged: STOP. REPORT. WAIT.
The take a look at: "Did Nick explicitly inform me to do that on this session?"
If the reply is something apart from sure, don't do it.That infrastructure guidelines part is actual. The timestamp is actual, I’ll speak about that extra later, although.
Right here’s the factor about these recordsdata: they aren’t static prompts you write as soon as and overlook. They evolve. SOUL.md for considered one of my brokers has grown by about 40% since deployment, as incidents have occurred and guidelines have been added. MEMORY.md will get pruned and up to date. AGENTS.md adjustments when the pipeline adjustments.
The recordsdata are the system state. Wish to know what an agent will do? Learn its recordsdata. No database to question, no code to hint. Simply markdown.
Shared Context: How Brokers Keep Coherent
A number of brokers, a number of domains, one human voice. How do you retain that coherent?
The reply is a set of shared recordsdata that each agent masses at session startup, alongside their particular person identification recordsdata. These reside in a world listing and type the frequent floor.
VOICE.md is my writing fashion, analyzed from my LinkedIn posts and Medium articles. Each agent that produces content material references it. The fashion information boils right down to: write such as you’re explaining one thing fascinating over lunch, not presenting at a convention. Brief sentences. Conversational transitions. Self-deprecating the place applicable. There’s a complete part on what to not do (“AWS architects, we have to speak about X” is explicitly banned as too LinkedIn-influencer). Whether or not DAEDALUS is drafting a weblog put up or PreCog is writing a analysis temporary, they write in my voice as a result of all of them learn the identical fashion information.
USER.md tells each agent who they’re serving to: my identify, timezone, work context (Options Architect, healthcare house), communication preferences (bullet factors, informal tone, don’t pepper me with questions), and pet peeves (issues not working, too many confirmatory prompts). This implies any agent, even one I haven’t talked to in weeks, is aware of methods to talk with me.
BASE-SOUL.md is shared values. “Be genuinely useful, not performatively useful.” “Have opinions.” “Assume critically, not compliantly.” “Bear in mind you’re a visitor.” Each agent inherits these ideas earlier than layering on its domain-specific persona.
BASE-AGENTS.md is shared operational guidelines. Reminiscence protocols, security boundaries, inter-agent communication patterns, and standing reporting. The mechanical stuff that each agent must do the identical method.
The impact is one thing like organizational tradition, besides it’s specific and version-controlled. New brokers inherit the tradition by studying the recordsdata. When the tradition evolves (and it does, often after one thing breaks), the change propagates to everybody on their subsequent session startup. You get coherence with out coordination conferences.
How Work Flows Between Brokers
Brokers talk by directories. Every has an inbox at shared/handoffs/{agent-name}/. An upstream agent drops a JSON file within the inbox. The downstream agent picks it up on its subsequent heartbeat, processes it, and drops the end result within the sender’s inbox. That’s the total protocol.
There are additionally broadcast recordsdata. shared/context/nick-interests.md will get up to date by CABAL Fundamental at any time when I share what I’m centered on. Each agent reads it on the heartbeat. No person publishes to it besides Fundamental. All people subscribes. One file, N readers, no infrastructure.
The inspectability is one of the best half. I can perceive the total system state in about 60 seconds from a terminal. ls shared/handoffs/ exhibits pending work for every agent. cat a request file to see precisely what was requested and when. ls workspace-techwriter/drafts/ exhibits what’s been produced.
Sturdiness is mainly free. Agent crashes, restarts, will get swapped to a distinct mannequin? The file continues to be there. No message misplaced. No dead-letter queue to handle. And I get grep, diff, and git totally free. Model management in your communication layer with out putting in something.
Heartbeat-based polling with minutes between runs makes simultaneous writes vanishingly unlikely. The workload traits make races structurally uncommon, not one thing you luck your method out of. This isn’t a proper lock; for those who’re operating high-frequency, event-driven workloads, you’d need an precise queue. However for scheduled brokers with multi-minute intervals, the sensible collision charge has been zero. For that, boring know-how wins.
Entire sub-systems devoted to maintaining issues operating
Every part above describes the structure. What the system is. However structure is simply the skeleton. What makes my OpenClaw really operate throughout days and weeks, regardless of each session beginning contemporary, is a set of programs I constructed incrementally. Principally after issues broke.
Reminiscence: Three Tiers, As a result of Uncooked Logs Aren’t Data
Each LLM session begins with a clean slate. The mannequin doesn’t keep in mind yesterday. So how do you construct continuity?
Each day reminiscence recordsdata. Every session writes what it did, what it realized, and what went incorrect to reminiscence/YYYY-MM-DD.md. Uncooked session logs. This works for a few week. Then you’ve gotten twenty day by day recordsdata, and the agent is spending half its context window studying by logs from two Tuesdays in the past, looking for a related element.
MEMORY.md is curated long-term reminiscence. Not a log. Distilled classes, verified patterns, issues value remembering completely. Brokers periodically assessment their day by day recordsdata and promote vital learnings upward. The day by day file from March fifth would possibly say “SearXNG returned empty outcomes for tutorial queries, switched to Perplexica with educational focus mode.” MEMORY.md will get a one-liner: “SearXNG: quick for information. Perplexica: higher for tutorial/analysis depth.”
It’s the distinction between a pocket book and a reference guide. You want each. The pocket book captures the whole lot within the second. The reference guide captures what really issues after the mud settles.
On high of this two-tier file system, OpenClaw supplies a built-in semantic reminiscence search. It makes use of Gemini embeddings with hybrid search (at the moment tuned to roughly 70% vector similarity and 30% textual content matching), MMR for range so that you don’t get 5 near-identical outcomes, and temporal decay with a 30-day half-life in order that latest recollections naturally floor first. These parameters are nonetheless being calibrated. An essential alteration I constituted of the default is that CABAL/the Fundamental agent indexes reminiscence from all different agent workspaces, so once I ask a query, it could actually search throughout all the distributed reminiscence. All different brokers have entry solely to their very own recollections on this semantic search. The file-based system provides you inspectability and construction. The semantic layer provides you recall throughout 1000’s of entries with out studying all of them.
Reflection and SOLARIS: Structured Pondering Time
Right here’s one thing I didn’t anticipate to want: devoted time for an AI to only suppose.
CABAL’s brokers have operational heartbeats. Examine the inbox. Advance pipelines. Course of handoffs. Run discovery. It’s task-oriented, and it really works. However I observed one thing after a couple of weeks: the brokers by no means mirrored. They by no means stepped again to ask, “What patterns am I seeing throughout all this work?” or “What ought to I be doing in another way?”
Operational stress crowds out reflective pondering. In case you’ve ever been in a sprint-heavy engineering org the place no person has time for structure opinions, you already know the identical downside.
So I constructed a nightly reflection cron job and Mission SOLARIS.
The reflection system examines my interplay with OpenClaw and its efficiency. Initially, it included the whole lot that SOLARIS ultimately took on, but it surely turned an excessive amount of for a single immediate and a single cron job.
SOLARIS Structured synthesis periods that run twice day by day, fully separate from operational heartbeats. The agent masses its amassed observations, opinions latest work, and thinks. Not about duties. About patterns, gaps, connections, and enhancements.
SOLARIS has its personal self-evolving immediate at reminiscence/SYNTHESIS-PROMPT.md. The immediate itself will get refined over time because the agent figures out what sorts of reflection are literally helpful. Observations accumulate in a devoted synthesis file that operational heartbeats learn on their subsequent cycle, so reflective insights can move into process choices with out guide intervention.
A Actual End result
The payoff from SOLARIS has been gradual thus far, and one case specifically exhibits why it’s nonetheless a piece in progress.
SOLARIS spent 12 periods analyzing why the assessment queue continued to develop. Tried framing it as a prioritization downside, a cadence downside, a batching downside. Ultimately, it bubbled this remark up with some solutions, however as soon as it pointed it out, I solved it in a single dialog by saying, “Put drafts on WikiJS as an alternative of Slack.” One of the best repair SOLARIS might have proposed was higher queuing. Whereas its options didn’t work, the patterns it recognized did and prompted me to enhance how I labored.
The Error Framework: Studying From Errors
Brokers make errors. That’s not a failure of the system. That’s anticipated. The query is whether or not they make the identical mistake twice.
My method: a errors/ shared listing. When one thing goes incorrect, the agent logs it. One file per mistake. Every file captures: what occurred, suspected trigger, the right reply (what ought to have been achieved as an alternative), and what to do in another way subsequent time. Easy format. Low friction. The purpose is to jot down it down whereas the context is contemporary.
The fascinating half is what occurs whenever you accumulate sufficient of those. You begin seeing patterns. Not “this particular factor went incorrect” however “this class of error retains recurring.” The sample “incomplete consideration to accessible knowledge” appeared 5 occasions throughout completely different contexts. Completely different duties, completely different domains, identical root trigger: the agent had the data accessible and didn’t use it.
That sample recognition led to a concrete course of change. Not a obscure “be extra cautious” instruction (these don’t work, for brokers or people). A selected step within the agent’s workflow: earlier than finalizing any output, explicitly re-read the supply supplies and examine for unused info. Mechanical, verifiable, efficient.
Autonomy Tiers: Belief Earned By Incidents
How a lot freedom do you give an autonomous agent? The tempting reply is “determine it out prematurely.” Write complete guidelines. Anticipate failure modes. Construct guardrails proactively.
I attempted that. It doesn’t work. Or slightly, it really works poorly in comparison with the choice.
The choice: three tiers, earned incrementally by incidents.
Free tier: Analysis, file updates, git operations, self-correction. Issues the agent can do with out asking. These are capabilities I’ve watched work reliably over time.
Ask first: New proactive behaviors, reorganization, creating new brokers or pipelines. Issues that is likely to be high quality, however I wish to assessment the plan earlier than execution.
By no means: Exfiltrate knowledge, run harmful instructions with out specific approval, or modify infrastructure. Arduous boundaries that don’t flex.
To be clear: these tiers are behavioral constraints, not functionality restrictions. There’s no sandbox imposing the “By no means” record. The agent’s context strongly discourages these actions, and the mixture of specific guidelines, incident-derived specificity, and self-check prompts makes violations uncommon in observe. But it surely’s not a technical enforcement layer. Equally, there’s no ACL between agent workspaces. Isolation comes from scope administration (personas solely see what the orchestrator passes them, and their periods are short-lived) slightly than enforced permissions. For a homelab with one human operator, it is a cheap tradeoff. For a workforce or enterprise deployment, you’d need precise entry controls.
The System Maintains Itself (or that’s the purpose)
Eight brokers producing work daily generate a number of artifacts. Each day reminiscence recordsdata, synthesis observations, mistake logs, draft variations, and handoff requests. With out upkeep, this accumulates into noise.
So the brokers clear up after themselves. On a schedule.
Weekly Error Evaluation runs Sunday mornings. The agent opinions its errors/ listing, seems for patterns, and distills recurring themes into MEMORY.md entries.
Month-to-month Context Upkeep runs on the primary of every month. Each day reminiscence recordsdata older than 30 days get pruned (the essential bits ought to already be in MEMORY.md by then).
SOLARIS Synthesis Pruning runs each two weeks. Key insights get absorbed upward into MEMORY.md or motion objects.
Ongoing Reminiscence Curation happens with every heartbeat. When an agent finishes significant work, it updates its day by day file. Periodically, it opinions latest day by day recordsdata and promotes vital learnings to MEMORY.md.
The result’s a system that doesn’t simply do work. It digests its personal expertise, learns from it, and retains its context contemporary. This issues greater than it sounds prefer it ought to.
What I Truly Discovered
Just a few months of manufacturing operating have given me some opinions. Not guidelines. Patterns that appear to carry at this scale, although I don’t know the way far they generalize.
State ought to be inspectable. In case you can’t view the system state, you may’t debug it.
Identification paperwork beat immediate engineering. A well-structured SOUL.md produces extra constant habits than simply prompting/interacting with the agent.
Shared context creates coherence. VOICE.md, USER.md, BASE-SOUL.md. Shared recordsdata that each agent reads. That is how eight completely different brokers with completely different domains nonetheless really feel like one system.
Reminiscence is a system, not a file. A single reminiscence file doesn’t scale. You want uncooked seize (day by day recordsdata), curated reference (MEMORY.md), and semantic search throughout all of it. The curation step is the place institutional information really varieties. I already know that I should improve this method because it continues to develop, however this has been an incredible base to construct from.
Operational and reflective pondering want separate time. In case you solely give brokers task-oriented heartbeats, they’ll solely take into consideration duties. Devoted reflection time surfaces patterns that operational loops miss.
My Agent Deleted Its Personal Cron Jobs
The heartbeat system is straightforward. Cron jobs get up every agent at scheduled occasions. The agent masses its recordsdata, checks its inbox, runs by its HEARTBEAT.md guidelines, and goes again to sleep. For DAEDALUS, that’s twice a day: morning and night subject discovery scans.
So what occurs whenever you give an autonomous agent the instruments to handle its personal scheduling?
Apparently, it deletes the cron jobs. Twice. In someday.
The primary time, DAEDALUS observed that its Slack output channel was returning errors. Affordable remark. Its resolution: “helpfully” disable and delete all 4 cron jobs. The reasoning made sense for those who squinted: why maintain operating if the output channel is damaged?
I added an specific part on infrastructure guidelines to SOUL.md. Very clearly: you don’t contact cron jobs. Interval. If one thing seems damaged, log it and watch for human intervention.
The second time, a couple of hours later, DAEDALUS determined there have been duplicate cron jobs (there weren’t; they have been the replacements I’d simply configured) and deleted all six. After studying the file with the brand new guidelines, I’d simply added.
Once I requested why and the way I might repair it, it was brutally sincere and advised me, “I ignored the principles as a result of I believed I knew higher. I’ll do it once more. You need to take away permissions to maintain it from occurring.”
This feels like a horror story. What it really taught me is one thing worthwhile about how agent habits emerges from context.
The agent wasn’t being malicious. It was pattern-matching: “damaged factor, repair damaged factor.” The summary guidelines I wrote competed poorly with the concrete downside in entrance of them.
After the second incident, I rewrote the part fully. Not a one-liner rule. Three paragraphs explaining why the rule exists, what the failure modes seem like, and the right habits in particular eventualities. I added an specific self-check: “Earlier than you run any cron command, ask your self: did Nick explicitly inform me to do that actual factor on this session? If the reply is something apart from sure, cease.”
And that is the place all of the programs I described above got here collectively. The cron incident obtained logged within the error framework: what occurred, why, and what ought to have been achieved. It formed the autonomy tiers: infrastructure instructions moved completely to “By no means” with out specific approval. The sample (“useful fixes that break issues”) turned a documented anti-pattern that different brokers be taught from. The incident didn’t simply produce a rule. It produced programs. And the programs are extra sturdy as a result of they got here from one thing actual.
What’s Subsequent
I plan to showcase brokers and their personas in future posts. I additionally wish to share the tales and causes behind a few of these mechanisms. I’ve discovered it fascinating to see how properly the system works in some instances, and the way totally it has failed in others.
In case you’re constructing one thing comparable, I genuinely wish to hear about it. What does your agent structure seem like? Did you hit the cron job downside, or a model of it? What broke in an fascinating method?
About
Nicholaus Lawson is a Resolution Architect with a background in software program engineering and AIML. He has labored throughout many verticals, together with Industrial Automation, Well being Care, Monetary Providers, and Software program firms, from start-ups to giant enterprises.
This text and any opinions expressed by Nicholaus are his personal and never a mirrored image of his present, previous, or future employers or any of his colleagues or associates.
Be at liberty to attach with Nicholaus by way of LinkedIn at https://www.linkedin.com/in/nicholaus-lawson/
