//Topics
Articles tagged #observability
#token-economy 8#finops 4#observability 4#prompt-injection 4#tokenization 3#agents 2#ai-cost 2#anthropic 2#cache 2#cfo 2#cost 2#mcp 2#multi-agent 2#opentelemetry 2#orchestration 2#prompt-caching 2#tra 2#adoption 1#agent 1#agent-debt 1#agentes 1#agentic 1#agentic-security 1#alfa 1#amplificacao-agentica 1#autonomy 1#avaliacao 1#calibracao 1#claude-opus 1#community 1#crise-dos-tokens 1#culture 1#custo-de-agentes 1#e-cache 1#echoleak 1#economics 1#finops-de-ia 1#gmail 1#interpretability 1#j-lens 1#lethal-trifecta 1#llm 1#llms-txt 1#mindset 1#model-routing 1#model-upgrade 1#n8n 1#observabilidade 1#organization 1#owasp 1#pricing 1#product 1#prompt 1#prompt-engineering 1#qwen 1#reasoning 1#state-machine 1#subagentes 1#supply-chain 1#token 1#token-crunch 1#token-resilience-architecture 1#tokenizer 1#tokens 1#tool-use 1
- Agents and orchestration
Multi-agent workflows in production: who is actually running thousands of agents (and who is pretending)
49 independent publications in three days say everyone wants multi-agent. The real question: when does it work, and how much does the supervisor cost that nobody measures.
- AI Ops Sec
OWASP Agentic Top 10 mapped to a real stack: what each ASI demands from those who run agents
I took the ten OWASP risks for agentic applications and mapped each one to a concrete piece of a production stack. The table, the incidents, and the config that is missing.
- AI Ops Sec
J-Lens: reading what the agent thinks before it acts, and what that changes in observability
Anthropic showed an internal space where the model keeps what it has in mind. I ran the lens on four synthetic prompts against a 27B Qwen and designed the third lane of agent observability.
- AI Ops Sec
The danger is not the connector. It is what gets into the model, and what it can do next
'Is this MCP secure?' has an answer. The missing question is another: what did I just authorise into a model that can also act? Two attack chains, what is at stake, and observability over MCPs.