DeepSeek's API is compatible with the OpenAI SDK — that makes the integration almost trivial. The real problem isn't the plumbing. It's deciding whether the model is actually worth it for your use case, without buying the hype or dismissing it out of fashion. Here's the framework.
Jul 22 2026 · 8′ · Tutorials · TypeScript · nextjs
Running the OWASP LLM Top 10 as a real audit is a completely different experience than reading it as a checklist. I ran it against my TypeScript agent stack with system prompts, MCP tools, and Cline — and the findings were uncomfortable.
Jun 20 2026 · 9′ · Tutorials · TypeScript · LLM
The homelabber community is building local AI dev platforms and the discussion is genuinely interesting. I have some observations that go beyond the initial excitement — and a checklist so you can decide whether the experiment is actually worth it.
Jun 16 2026 · 9′ · Opinion · TypeScript · LLM
A municipality announces its "own" LLM and the technical community discovers it might be a merge of an existing model. My read: the real problem isn't the fraud — it's that almost nobody knows how to verify it. Here's the checklist.
Jun 15 2026 · 9′ · Opinion · LLM · open source
The most common mistake when implementing MCP tools is coupling them to the provider's SDK. The spec exists to prevent exactly that. A practical architecture guide: the input/output contract that makes a tool work across Claude, GPT, and local models without rewriting anything.
Jun 10 2026 · 8′ · Tutorials · TypeScript · LLM
A system prompt isn't documentation for the model — it's a contract. After several redesigns, I landed on a format with fixed sections, explicit limits, and dynamically injected context. Here's what survived and why.
May 29 2026 · 9′ · Tutorials · TypeScript · produccion
A 26M parameter model trained via Gemini distillation for tool calling showed up on HN and made me stop everything. Not to celebrate — to understand what real problem it points at, where the limits actually are, and whether it belongs in a stack like mine.
May 17 2026 · 8′ · Opinion · TypeScript · LLM
The autonomous agent incident forced me to redesign everything — from permissions to observability. This is what ended up running in production after the crisis: the real graph, the real numbers, and what still doesn't sit right with me.
May 08 2026 · 9′ · Experiments · TypeScript · produccion
After an autonomous agent nearly wiped my production database, I built a real guardrails layer. Here are the controls, the code, and the logs that saved my skin.
May 07 2026 · 6′ · Experiments · TypeScript · produccion
Architecture, real systems, product decisions and technical lessons. Everything reviewed with my own judgment before it ships.
213 articles published