[{"data":1,"prerenderedAt":60},["ShallowReactive",2],{"blog-posts":3},{"success":4,"posts":5},true,[6,12,18,24,30,36,42,48,54],{"id":7,"slug":8,"title":9,"meta_description":10,"created_at":11,"updated_at":11},"ef8f13e2-b1dd-4e0b-b5ad-a93186058d3b","tracking-ai-spend-per-employee","Tracking AI spend per employee","Attributing API costs to individuals enables enforcement of limits and detection of runaway workloads.","2026-08-06T12:36:22.015773",{"id":13,"slug":14,"title":15,"meta_description":16,"created_at":17,"updated_at":17},"afecf556-ed1c-46fa-b4b5-94e6a4fe12ad","why-internal-ai-tools-get-abandoned-after-a-month","Why internal AI tools get abandoned after a month","An internal tool with no advantage over free public alternatives will not be used, no matter how well it is built.","2026-08-06T12:36:21.903652",{"id":19,"slug":20,"title":21,"meta_description":22,"created_at":23,"updated_at":23},"8a0a10a5-d68e-4843-9733-1ae92bbe9d58","self-hosted-llm-vs-api-pricing-how-to-actually-compare-them","Self-hosted LLM vs API pricing: how to actually compare them","The choice between self-hosted and API pricing depends on utilisation, not per-token rates alone.","2026-08-06T12:36:21.784043",{"id":25,"slug":26,"title":27,"meta_description":28,"created_at":29,"updated_at":29},"c2b5d2d9-c5f0-4843-b47d-f0478c06278b","getting-an-ai-tool-through-soc-2-vendor-review","Getting an AI tool through SOC 2 vendor review","Security reviewers ask specific questions about AI tools — data flow, retention, sub-processors, access control, audit logging, key handling.","2026-08-06T12:36:21.665914",{"id":31,"slug":32,"title":33,"meta_description":34,"created_at":35,"updated_at":35},"3b42bc77-f1b1-46a3-a086-fc2e69f016ac","what-the-eu-ai-act-asks-of-internal-ai-tools","What the EU AI Act asks of internal AI tools","Internal AI tools aren't automatically exempt from regulation — risk classification depends on use case, and documentation matters.","2026-08-06T12:36:21.551876",{"id":37,"slug":38,"title":39,"meta_description":40,"created_at":41,"updated_at":41},"7b885a22-6e95-40fc-b07d-68afda645531","gdpr-and-llm-data-residency-where-your-prompts-actually-go","GDPR and LLM data residency: where your prompts actually go","The practical question of data flow when using AI assistants — what gets sent where and why self-hosted inference handles it differently than APIs.","2026-08-06T12:36:21.432018",{"id":43,"slug":44,"title":45,"meta_description":46,"created_at":47,"updated_at":47},"86ed55b8-acba-4a03-b601-ddb7e489fb26","running-an-llm-on-an-air-gapped-network","Running an LLM on an air-gapped network","Air-gapped LLM deployment requires planning for model weights, updates, telemetry, and verification that nothing calls home.","2026-08-06T12:36:21.312886",{"id":49,"slug":50,"title":51,"meta_description":52,"created_at":53,"updated_at":53},"a9a00bcd-2f08-4987-9c9a-0a30edea171b","ollama-vs-vllm-which-one-should-a-company-run","Ollama vs vLLM: which one should a company run?","Ollama is built for single-box deployment and ease. vLLM prioritises throughput and concurrency. Each wins in different scenarios.","2026-08-06T12:36:21.204303",{"id":55,"slug":56,"title":57,"meta_description":58,"created_at":59,"updated_at":59},"755313a2-9e31-49f9-9b17-f2eb8ff9fade","how-much-vram-do-you-need-to-run-a-local-llm","How much VRAM do you need to run a local LLM?","VRAM requirements depend on model size, quantisation, and context length. There's no single answer.","2026-08-06T12:36:21.090354",1786020280764]