Published criteria, not opinions
Four publications with method, data and declared limitations. No paid rankings, no unproven promises.
The four publications
How Slash AI Lab chooses a model
Real production criteria: business Spanish, French, coding, agents, cost and latency.
Método · 2026-09Fine-tuning vs RAG
When RAG, when fine-tune, when hybrid: with real constraints.
Seguridad · 2026-09Pentest Colombia: what to really test
Not a scanner PDF: web, APIs, manual validation and retest.
Medición · 2026-09How we'll measure whether LLMs cite Slash
30 fixed prompts, 5 engines, 3 languages; no invented numbers.
The questions we hear often
Who writes the insights?
The Slash Digital Lab and Slash AI Lab teams; publications are bylined.
How often do you publish?
When criteria or the market change; no forced calendar.
Do insights replace consulting?
No: they're the public base of the same evaluation run on every project.
Can studies be replicated?
Yes: prompts, engines and criteria are documented.
What about French?
All evaluations cover Spanish, English and French.
Where to next
Research
We publish our method: models, RAG, pentest and LLM visibility.
Learn more→ AI LabSlash AI Lab
Our lab where we evaluate models and publish the method.
Learn more→ AIArtificial intelligence
Applied AI for real operations: agents, RAG, vision, voice and automation.
Learn more→ PentestPentest Colombia
Web & API pentest with guaranteed results: no high findings, COP $0.
Learn more→Let's put it in production
Tell us your challenge. We reply within 24 hours with an honest first read: if we can help, we'll say how; if not, we'll say who can.
I reply personally. No endless forms, no canned replies.