Our insights.
Field notes, benchmarks, points of view on AI in production. Written by the team, for teams that build.
- Technical guide · 012026
n8n workflows + AI agents: the combo replacing 80% of RPA projects
n8n handles the deterministic steps, the AI agent handles what's ambiguous and needs judgment. For most B2B automations that used to end up as brittle RPA projects, this duo genuinely changes the equation.
June 23, 2026·Anthony Cohen→ - Point of view · 022026
B2B Voice Agents: Why 2026 Is the Tipping Point
The voice agent technology stack shifted in 18 months. Accurate STT, natural TTS, sub-second latency: for N1 support, lead qualification, and appointment booking, the conditions are finally in place.
June 16, 2026·Anthony Cohen→ - Analysis · 032026
The real cost of an AI agent in 2026: a line-by-line breakdown
A concrete case study: a 200-person manufacturing company, a contract analysis agent, 50 active users. We break down every cost line, from API inference to monitoring, and compare year 1 to year 2.
June 9, 2026·Anthony Cohen→ - Technical guide · 042026
Evaluating AI agents in production: eval sets, drift, and monitoring
The agent works in the demo. Six months into production, how do you know it still works? The answer is structured evaluation, not infrastructure logs.
May 26, 2026·Anthony Cohen→ - Buyer's guide · 052026
Sovereign cloud or on-premise: the decision matrix for hosting your LLMs
SecNumCloud, public cloud, on-premise GPU: three options to host your LLMs, three very different levels of protection. Here is how to tell real data sovereignty from a sovereignty facade, and a decision matrix to guide your choice.
May 19, 2026·Anthony Cohen→ - Point of view · 062026
Why Your AI POC Never Made It to Production
The POC works, the demo convinces, yet the project never reaches production. It's not a model problem. These are three organizational blockers that most teams failed to anticipate.
May 12, 2026·Anthony Cohen→ - Technical guide · 072026
RAG on Internal Documents: Why Most Projects Stall
RAG promises an assistant that knows your documents. In production, it misses the mark, users disengage, and the project stalls. The root cause is not the model. It is a data quality problem.
May 5, 2026·Anthony Cohen→ - Regulatory analysis · 082026
EU AI Act: What Actually Applies to Your AI Deployments in 2026
August 2, 2026 is when high-risk obligations under the EU AI Act become binding. Here is what it means in practice for companies deploying AI agents, HR tools, or credit scoring systems.
April 28, 2026·Anthony Cohen→ - Point of view · 092026
Multi-agents: when it's useful, when it's pure overhead
Everyone is orchestrating agent swarms in 2026. Research shows it often makes things worse. Concrete criteria and a decision tree to get the architecture right.
April 27, 2026·Anthony Cohen→ - Security analysis · 102026
AI agent security: the real attack surface in 2026
Prompt injection, tool poisoning, silent exfiltration, RAG poisoning. What can break an AI agent in production today, and the layered defense framework we apply on every engagement.
April 27, 2026·Anthony Cohen→ - Buyer's guide · 112026
Local LLMs in 2026: which open-source model to pick for your enterprise
Mistral, Llama, Qwen, DeepSeek, Gemma: the local LLM landscape is rich but tricky to navigate. Our pragmatic buyer's guide for enterprises planning an on-premise deployment.
April 23, 2026·Anthony Cohen→ - Point of view · 122026
Sovereign note-takers: why big enterprises want 100% local
Large enterprises refuse consumer SaaS note-takers that ship their sensitive meetings to public LLMs. We build custom, fully local alternatives.
April 23, 2026·Anthony Cohen→