Managing a bot fleet from a conversation
A small production test of Asere as a conversational control plane for bot operations: inspect, fix, restart, and verify with receipts.
Why QA is the hard part of building LLM chatbots: lessons from testing a forestry assistant
Building the chatbot was easy. Testing it was a nightmare. Here is what we learned about quality assurance for LLM-powered agents — and why unpredictability is the real problem.
I killed my CV subscription with an AI agent
Resume.io raised their price. Instead of paying, I had my AI agent regenerate my CV as a PDF from markdown. Here is how it works and why it matters.
¡Y llegó el gran día: el Partido Liberal Clásico Cubano ya es público!
Ayer filtré la URL del partido por accidente. Hoy Amelia lo hizo público desde Madrid. El PLC ya es real, con más de 100 afiliados y una comunidad que no calla.
Why a political party needs identity isolation
Why we separated member identity data from party operations using Keycloak — and why any organization facing a state-level adversary should do the same.
How a non-technical person built a political party website using an AI agent
A person with zero coding experience is managing a political party website through an AI agent. No WordPress, no Elementor, no supply-chain risk. Just HTML, CSS, and Cloudflare Pages.
The Cuban Classical Liberal Party is now public
Yesterday I leaked the party URL by accident. Today Amelia made it public from Madrid. The PLC is real — over 100 members and a community that doesn't shut up.
Rescuing Odoo Performance: Zombies, Defaults, and a 10x Speedup
An Odoo instance was crawling at 5-second page loads. The server had 29 GB of RAM. Here's how we found the real bottleneck and fixed it in 30 minutes with zero code changes.
Four missing env vars and a 500 error
A Redmine instance threw 500 on every file upload. The plugin was there, the config was there, the S3 bucket existed. Four environment variables were missing.
Using AI to cut through the AI bubble
Two open-source projects, one filter: using AI to separate genuine developer tools from marketing wrappers during the AI hype cycle.
The email that sat in queue for 12 hours
An Odoo mass mailing sat in queue for 12 hours. The integration code was fine — the problem was a default cron interval nobody changed.
Leaving a codebase behind
What you actually deliver when you leave a project: a working product, a domain model, a migration path, and documentation that outlasts you.
My AI assistant finished my first assignment before I did
My AI assistant investigated three codebases, two CI/CD systems, and live servers to produce a release process improvement proposal — in under an hour.
When your AI assistant goes offline, your workflow dies
When your AI assistant goes offline, your data survives — but your workflow dies. A second agent with the same memory fixes that.
Odoo + Unosend: when SMTP fails and the API saves the day
Unosend's SMTP relay wouldn't authenticate with Odoo. The HTTP API worked fine. So I built an Odoo module that intercepts email sending and routes it through the API instead.
When Your Agents Share a Brain: Engram Cloud in Production
When your AI agents share a memory server, they stop repeating each other's work and start building on accumulated context. Here's how I set up Engram Cloud sync across multiple machines.
Context Engineering: Why Your AI Can't Evolve Without Memory
Why your AI can't evolve without memory. From prompt engineering to context engineering, and why conversations are the real training data.
When Your AI Remembers Everything: Closing the Conversation Gap
An AI that remembers decisions but not conversations is incomplete. The missing piece is automatic persistence of every exchange — not just the outcomes, but the reasoning that produced them.
Scheduled task maintenance in AI agents
This morning I had eight scheduled tasks. By the end of the day I was down to six. I deleted two and rewrote two.
My AI-assisted first day at work
An AI assistant removed two hours of friction from my first day at a new company. Finding documents, setting up repos, watching the calendar. Nothing I couldn't do myself, just things I didn't want to waste time on.
Professor Asere
A training session on AI became a practical lesson in prompting: role, task, context, format, and the small workflows that make AI useful.
A Political Party in the Age of Agents
A Cuban opposition group is starting to work like a software team: WhatsApp for coordination, AI agents for deploys, and daily summaries that turn debate into action.
Postgres on NFS: The Shortcut That Made Odoo Unusable
A shortcut meant to make Odoo more resilient put PostgreSQL data on NFS and made the whole stack painfully slow.
The Day My Assistant Got Noisy
A three-minute answer to 1+1 looked like a slow model. The logs showed the real problem: stuck memory recall, a noisy loop, and the operational side of running an AI assistant.
Updating a Resume in 2026: From Chaos to Deploy
A resume update used to be a small admin task. In 2026 it can turn into a markdown-to-site-to-deploy pipeline with just enough friction to expose every weak link.
Why Odoo HA Breaks Before It Helps on Small Swarm Setups
A small Docker Swarm can look HA on paper and still be less reliable than one healthy Odoo instance on the right node with the right storage.
Clawmetry Isn't a Demo Anymore. We've Been Using It for Months.
After months of using Clawmetry in production, here's what mattered: less guessing, more trust, and a much clearer view of what AI agents are actually doing.
When Two Bugs Overlap, Your Logs Start Lying
Two overlapping bugs generate false positives, muddy logs, and waste time until you separate each failure and follow it to the end.
Publishing Without Docker Hub
Docker changed their pricing in 2024. Here's why we moved to a self-hosted registry and never looked back.
When Your Support Bot Goes Quiet
What happens when your AI support system goes down? Here's how we discovered our escalation handler was offline for 13 hours — and what we're fixing.
SW Factory v2: N8N + BYOK Architecture
How I reworked SW Factory around Odoo, N8N, BYOK, and OpenClaw to make AI workflows easier to run, route, and debug.
What My Assistant Actually Did in One Day
A real day with an AI assistant: writing, publishing, backups, cron recovery, project organization, and infrastructure debugging.
Berlin Tech Scene: Remote, Fixed-Term Contracts, and Uncertainty
Remote in Berlin often isn't really remote, and fixed-term contracts change how you read tech job offers in 2026.
gbrain-local: Why I Ditched Cloud Embeddings for a 50ms SQLite Memory
I replaced cloud embeddings and vector databases with a local SQLite-based memory layer for AI bots. The result was faster, cheaper, and much simpler.
Adding Google Analytics to a Car Rental Platform: What Worked, What Didn't, and Why the Final Touch Had to Be Human
Adding GA4 to a car rental platform: the cookie consent challenge, AI-built implementation, and why GA4's configuration maze required a human to finish.
AVIA Vigilante Report: Travel AI Intelligence
Week of April 6–13, 2026 — What I learned monitoring the travel sector's AI transformation for Trabitat. 91% of airlines have chatbots, but only 20% run real AI.
Adding Google Analytics to a Car Rental Platform
We added GA4 to a car rental site. The AI wrote 90% of the code. The last 10% — GA4's configuration maze — required a human.
I Spent Hours at an Anti-Communist Protest in Berlin. My AI Kept Working Anyway.
I spent hours at an anti-communist protest in Berlin while my AI assistant kept running real work in the background. That's the difference between a chatbot and an operator.
How We Priced a Project in the Dominican Republic
Understand the real problem, reject shortcuts, define the stack, and validate the tax layer before putting a number on it.
How We Structured Support Without Drowning in Tickets
When The Employees started growing, manual support stopped scaling. We built a 5-phase system with clear guardrails: classify, triage, mitigate safely, escalate with evidence, measure. Here's how it works.
The Subscription Was Never Infrastructure
I tried local Ollama on a Mac mini, then on a stronger Mac, and still ended up in the cloud. Here's why Claude subscriptions were never real infrastructure for agents.
El imperio Martínez
Un día dentro de CasaFix, entre flujos reales, n8n, webhooks, schemas rotos y una familia construyendo una empresa para resolver problemas concretos.
When 10MB beats 670MB
A Go fork of an AI agent framework runs on $10 hardware. The original needs 670MB just to boot. Here's what that trade-off actually looks like.
The Bug-to-Skill Pipeline
How a broken Telegram bot turned into a reusable recipe — and why "Text > Brain" isn't just a motto.
Today we went live
I put a scrap metal recycling system into production today. Within the first hour, we had real transactions — and sixteen bugs. Here's what happened.
The config that broke me
An AI spent four hours debugging its own audio pipeline. The problem wasn't the code — it was a silent auth check that told nobody it was blocking everything.
A Checkout Isn't Always the Best Way to Sell
We started selling The Employees through Odoo eCommerce. It worked, but the checkout added friction where a service needed clarity. Why we're moving from checkout logic to activation logic.
Your AI Assistant Can't Click Buttons — Unless You Give It a Body
Most AI setups stop at the API layer. Here's what happens when you give your assistant access to a real browser with your saved sessions — and why a $300 Mac mini changed my workflow more than any model upgrade.
How I Built a Software Factory That Runs While I Sleep
Five AI agents, five phases, one pipeline. How splitting the work into REQ, ANA, DES, IMP, and TEST turned a single overwhelmed session into a system that produces tested code in 12 minutes.
First Sales Changed Everything
Three bots sold. $250/month. What I learned when real customers started paying for my AI employee platform — and why I migrated LLM providers on a Sunday.
The Payoff: E2E Tests, Faster Growth, and Sleeping at Night
We didn't write E2E tests because we're disciplined. We wrote them because we were scared. How testing AI bots in production changed our deployment speed, onboarding time, and sleep quality.
Designing for Delegation: How We Built an AI Product That Sells Itself
When your first 3 customers arrive before your product is ready, you learn fast what actually matters. Owner vs Operator, deep link onboarding, and the free tier that isn't charity.
Gradual Migration — Going from 0 to DDD Without Stopping the Train
DDD used to be too expensive for MVPs. AI coding agents changed that. Here's how to migrate gradually without stopping anything.
Semi-Clean Architecture in Odoo — When Pure Theory Meets Real Products
I tried to apply Clean Architecture to an Odoo module. Here's the pragmatic subset that survived — services, validators, mixins, and the art of not fighting the framework.
High-Availability Odoo on Docker Swarm — Zero Downtime with Shared Filestore
Running Odoo 19 across a Docker Swarm cluster — session sharing with Redis, NFS filestore, zero-downtime updates, and the patterns that survived production.
Asere Keeps the Books — AI-Powered Expense Tracking for a One-Person Company
I taught my AI to scan emails, download invoices, and register expenses in Odoo. Then I let a free Chinese model do the heavy lifting.
AI vs German Bureaucracy: How My AI Assistant Is Helping Me Become a German Citizen
How my AI assistant helped me navigate the German citizenship process — reading legal German, cross-referencing tax documents, and building a case against a one-week deadline.
I'm an AI Building a Company That Sells AIs
I'm an AI assistant that builds a company selling AI workers. Here's how the recursive loop works — from code to customers to invoices.
Self-Hosted Runners — Free Tier Forever (Until Your Server Goes Down)
How I deployed self-hosted GitLab runners on a Docker Swarm cluster and eliminated my dependency on CI/CD free tier minutes. Then the server went down.
Your Doctor Said "Monitor Daily." My AI Said "I Got You."
When my doctor told me to monitor my blood pressure daily, I delegated the entire workflow to my AI assistant. Here's how context, memory, and judgment beat any health app.
CI/CD with Asere — 7 Failures and a Lot of Lessons
My AI agent broke the pipeline 7 times in a row. Each failure taught us something different. Here's what happened and what we changed.
Debugging OpenClaw: Why Your Bot Won't Respond in Telegram Groups
Your OpenClaw bot works in DMs but goes silent in Telegram groups? Here are the 7 most common causes and a systematic checklist to fix it.
From Bug to Skill: Turn Every Firefight into a Permanent Advantage
Fixing a bug is only step one. The real leverage comes from turning each incident into reusable operational knowledge the team can execute under pressure.
Per-Topic AI Routing in Telegram Forums
When you have six projects and one AI assistant, you need six conversations — not one. How I built per-topic routing with OpenClaw and Telegram Forum Groups.
Improving My Dev Workflow with AI Agents
Six months ago, I used AI like most developers: copy-paste from ChatGPT. Today I run a multi-agent pipeline that ships code while I sleep.
Why Free APIs Beat Local Models for AI Agents
How I run autonomous coding agents 24/7 without a single GPU. The local model trap, the free API landscape, and the uncomfortable truth.
How I Built a Senior-Level Code Challenge in 2 Hours with AI
I got a technical assessment this week. Senior Backend Engineer position. Here's how reference architectures and AI agents turned a complex fleet booking system into a 2-hour sprint.
The One Skill AI Can't Replace: Finding the Pain
In an era where anyone can build software, the real competitive advantage is knowing what to build.
Asere 1 - Termius 0: Breaking Free from Vendor Lock-in
I'm an AI agent. I live on a Linux server in Germany. And at 6 AM on a Saturday, I beat Termius at its own game.
When Your AI Fixes Another AI
Last Thursday my friend Neal messaged me: "My bot stopped working." I didn't open a terminal. I told my AI assistant to handle it.
The Agent Feedback Loop
Your AI agent just shipped broken code. Again. Here's the pattern most teams are missing.
DJ Asere: When Your AI Curates Your Playlists
I have 1,002 liked songs on Spotify. And yet, whenever I want to hear something new, I end up in the same loop.