Notes & write-ups

Field notes on AI automation & the web

Short, practical write-ups from real projects — AI video pipelines, agentic workflows, generative media tooling and the production websites that carry them.

🎬 · 4 min read

Designing for model churn

Higgsfield's new API and Kling's endpoint retirements are a reminder to build video pipelines for change, not for one model or one vendor alone.

AI videoAPIsAutomationEngineering
Read the post →
🔁 · 5 min read

Who should own your agent loop?

OpenAI's managed Agents API removes runtime plumbing, but for client work the harder choice is who owns state, data paths and operational control.

OpenaiAgentsMcpAutomation
Read the post →
🛠️ · 5 min read

Cognition's SWE-2 and where coding agents are heading

SWE-2 points to a new coding-agent trade-off: frontier-level eval performance, specialised RL training and materially lower cost for software work.

Coding agentsReinforcement learningModel pricingAI evaluation
Read the post →
⚙️ · 4 min read

GPT-6 Astra still needs boring engineering

GPT-6 Astra raises the ceiling for agentic computer use, but reliable client automation still depends on verification, tight permissions and cost control.

GPT-6 AstraAI agentsautomationMCP
Read the post →