oniru.ai6 min read
How to test an automation before you hand it to a client.
Every automation passes its demo. Production is a thousand submissions from strangers against data nobody chose, and that is where client trust is lost.
Notes from systems in production.
Practical writing on automation delivery, APIs and the operational details that make systems reliable.
Articles
oniru.ai6 min read
How to price ongoing automation maintenance.
Maintenance is a separate commercial product from the build, because you are selling availability rather than output. Price it against response, not hours.
oniru.ai6 min read
How to integrate a system that has no API.
There is no API, or it costs more than the project. Five workable approaches, and how to choose the one that matches what the client can tolerate breaking.
oniru.ai6 min read
How to handle GDPR when an automation moves client data.
Most agency automation work is data protection work, and it usually gets treated as though it is not. Controllers, processors and where the data actually goes.
oniru.ai8 min read
Build an LLM step that returns structured JSON you can trust.
A model in the middle of a workflow returns whatever it decided to write. Build the step so the node after it always receives the shape it was expecting.
oniru.ai7 min read
Build a document extraction pipeline with a confidence gate.
A pipeline that extracts fields at ninety percent accuracy and writes all of them has not saved anybody time. It has created a data problem for later.
oniru.ai8 min read
Build a two-way sync that does not loop.
One-way sync is solved. Two-way sync is a different problem, and the first failure appears within minutes: two systems updating each other forever.
oniru.ai7 min read
What clients actually mean when they ask for AI.
A request for AI is a budget and an expectation, not a requirement. Behind almost every one there is a specific, boring, buildable job worth finding first.
oniru.ai6 min read
The automation nobody owns.
A workflow runs every night and nobody fully understands it. Working is not the same as owned, and the difference only becomes visible when it stops.
oniru.ai6 min read
When not to automate.
Agencies that build automation are badly placed to advise against it, which is why the advice carries weight when it comes from them. Six clear signals.
oniru.ai5 min read
The EU AI Act transparency rules, and what agencies must do.
Enforcement began on 2 August 2026 and the rules reach further into ordinary agency work than the coverage suggested. What is in scope, and what is not.
oniru.ai6 min read
White-label automation delivery without losing the client relationship.
Subcontracting technical work does not have to put the client relationship at risk. The protections are contractual and operational, and every one of them can be written down in advance.
Have a client asking for something you can’t easily build?
Send us the requirement. We’ll tell you how we’d approach it, what it would require and whether it makes sense to build.
No pitch deck required. A rough description is enough.
Or write to [email protected]