---
okf_version: "0.1"
---

# Radar — Rota Nacional

* [Agent memory: preserve context without accumulating personal data](https://rota-nacional.ia.br/okf/en/radar/memoria-de-agentes-guarde-contexto-sem-576d18.md) - Long context can extend exposure. Separate what an agent needs to remember from the identity of people mentioned in a conversation.
* [Autonomous agents: constrain tools and process incoming data](https://rota-nacional.ia.br/okf/en/radar/agentes-autonomos-limite-ferramentas-e-trate-d8b689.md) - An isolated runtime controls what an agent can do. Privacy also requires controlling the content it sends to AI.
* [Audio and AI: transcripts need a data policy too](https://rota-nacional.ia.br/okf/en/radar/audio-e-ia-a-transcricao-tambem-768193.md) - Turning speech into text changes the format, not the sensitivity. Evaluate every stage before introducing audio into a workflow.
* [Local inference: evaluate performance and exposure in the same test](https://rota-nacional.ia.br/okf/en/radar/inferencia-local-avalie-desempenho-e-exposicao-1670ee.md) - Running a model close to data can change the architecture. It does not replace input processing, access control or real evaluation.
* [Evaluate agents with less context and explicit criteria](https://rota-nacional.ia.br/okf/en/radar/avalie-o-agente-com-menos-contexto-a12bae.md) - A more elaborate workflow does not always improve outcomes. Compare components by task quality, consumption and data exposure.
* [Sharing model context also shares data risk](https://rota-nacional.ia.br/okf/en/radar/compartilhar-contexto-entre-modelos-tambem-compartilha-648b8e.md) - Internal representations do not make information anonymous. Define data boundaries before connecting multiple models.
* [Agent loops: simplify workflows without expanding permissions](https://rota-nacional.ia.br/okf/en/radar/loops-de-agentes-simplifique-o-fluxo-f98b08.md) - Fewer components can ease maintenance. Data and action boundaries must remain explicit at every step.
* [Inference caching: evaluate performance and isolation](https://rota-nacional.ia.br/okf/en/radar/cache-de-inferencia-desempenho-e-isolamento-9d30e4.md) - Efficient memory can improve service capacity. The design must also prevent one session's context from appearing in another session.
* [Document RAG: process data before composing the answer](https://rota-nacional.ia.br/okf/en/radar/rag-com-documentos-trate-os-dados-25a084.md) - Retrieval can combine information from several documents. Privacy must follow retrieval, context assembly and the answer.
* [Encryption and privacy: secure transit and reduce content](https://rota-nacional.ia.br/okf/en/radar/criptografia-e-privacidade-proteja-o-transporte-69314f.md) - An encrypted connection protects transit. The recipient still receives what you send, so policy must act before delivery.
* [Streaming speech: protect personal data before transcription](https://rota-nacional.ia.br/okf/en/radar/streaming-de-fala-proteja-dados-pessoais-c9ffbd.md) - Real-time ASR and translation models can process speech containing personal data; Rota Nacional’s privacy barrier applies the organization’s policy before a model runs.

# Follow

* [RSS](https://rota-nacional.ia.br/en/radar/feed.xml) - Radar
* [HTML](https://rota-nacional.ia.br/en/radar/) - Radar