· Agents, Reliability
What happens after an AI chatbot or agent is delivered
How we maintain an AI chatbot after delivery: a golden dataset of real conversations, monitoring, alerts and results every week.
Read more →
Blog
What we discover while building AI in production with our clients.
· Agents, Reliability, Architecture
It says it is done and it is not
In tests where nobody else can contradict the agent, almost half of its failures come with a claim that it went fine. What the studies measure and who says done.
Read more →
· Compliance, Regulation, Business
You do not build AI. The Act applies to you anyway.
The EU AI Act does not hand duties only to the people who make models. Two already apply to you today. The postponement everybody is talking about leaves them alone.
Read more →
· Business, Method
The shiny toy
The AI project that dazzles in the demo and dies in a drawer has a name and an antidote. A three-signal test to tell a tool from a toy.
Read more →
· Agents, Architecture, Security
Here is a secret: I don't like agentic architectures
We sell AI agents, and we don't like how almost everyone builds them. Business rules cannot live in the prompt, they have to live in the code.
Read more →
· Data, Architecture, Agents
Data before prompts
An entire market sells prompt engineering. Our production experience says you gain more by organizing the data than by polishing the prompt.
Read more →
· Maintenance, Observability, Business
Starting an AI project is easy. Keeping it alive is nearly impossible
Flashy AI projects launch well and die young. Profitable ones are easy to start and cheap to sustain. The difference is decided before any code is written.
Read more →
· Observability, Maintenance, Agents
The symptom signature beats the fix
Documenting how a failure is recognized from the outside pays more than documenting how it was fixed. Three real signatures from an AI assistant in production.
Read more →
· Agents, Reliability, Maintenance
What your assistant does when a tool goes down
A conversational assistant depends on systems that fail. The circuit breaker that protects the user, and the three lessons production taught us about it.
Read more →
· Business, Method, Automation
Measure AI by profit, not by productivity
Productivity is AI's comfortable metric, it always looks good and commits to nothing. We prefer the uncomfortable one, which concrete gain the system delivered.
Read more →
· Data, Agents, Security
The agent that queries your data does not write SQL
The text-to-SQL pattern promises a model that writes queries. We built it for Savian with the opposite decision, and that decision is what makes it safe.
Read more →
· Automation, OCR, Back office
Invoice digitization with OCR and AI, from a case in production
What changes when OCR meets a language model, how it looks in a real case with utility invoices and why validation is the actual product.
Read more →
· Agents, Real estate, Automation
An AI agent for real-estate agencies, from the inside
Dozens of WhatsApp messages a day, five to ten minutes per inquiry and an overloaded team. What the agent that filters requests for a Barcelona agency actually does.
Read more →