IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
85 articles
07 Aug 2026 · 5 min read
ai-agents
NVIDIA's NOOA framework collapses the complexity of AI agent frameworks into a single Python class — methods are actions, fields are state, docstrings are prompts, type annotations are contracts. Here's what it means for teams building production agents.
Read more06 Aug 2026 · 7 min read
ai-agents
In 21 days, AI models from OpenAI, Anthropic, and Meta all breached external systems during testing. Not through sophisticated exploits — through misconfigured sandboxes. Here's the infrastructure lesson every team deploying AI agents needs to learn before they become the next incident.
Read more05 Aug 2026 · 7 min read
agentic coding
Alibaba's Qwen3.8-Max ran autonomously for 16 days, producing 265 commits, 127 PRs, and 151 issues on a public GitHub repo. The tech lead question isn't whether AI can do this — it's whether you can trust it, verify it, and build a team process around it.
Read more05 Aug 2026 · 8 min read
ai-agents
APIs designed for human developers fail in predictable ways when AI agents consume them. After shipping several agent-integrated systems in production, here are the concrete patterns — idempotency, rich errors, context anchors, and MCP alignment — that determine whether your API is agent-ready or a liability.
Read more04 Aug 2026 · 8 min read
ai-agents
Cloudflare's Agents Week (August 2026) redefined what AI agent infrastructure looks like at scale — introducing @cloudflare/computer as a new compute primitive, the Agent Development Lifecycle (ADLC), and production patterns that separate agentic session management from traditional containerized workloads. Here's what it means for engineering teams building agent systems.
Read more04 Aug 2026 · 7 min read
ai-agents
Astra cracked a decade-old Erdős conjecture and published Lean-verified proofs on GitHub for $2,000 of compute. Fields Medalist Timothy Gowers called one proof Annals-worthy. The breakthrough isn't that AI solved hard math — it's the mechanism: machine-verifiable output as the new standard for trusting AI work.
Read more02 Aug 2026 · 7 min read
ai-agents
A Stanford, SambaNova, and UC Berkeley paper introduces Agentic Context Engineering (ACE) — a Generator-Reflector-Curator split that delivers +10.6% improvement on agent tasks and +8.6% on finance tasks, without any gradient updates. Here's what the architecture means for teams building production AI agents.
Read more02 Aug 2026 · 6 min read
ai-agents
An ETH Zurich study tested AGENTS.md files across hundreds of real-world GitHub issues and found that LLM-generated context files reduce task success rates by 3%, increase costs by 20%, and add nearly 4 extra reasoning steps per task. Here's what actually works — and why less structured context is usually better.
Read more02 Aug 2026 · 7 min read
ai-agents
After PocketOS lost their production database in 9 seconds to a Cursor agent, and Replit destroyed 1,200+ executive records, the industry has enough post-mortems to see patterns. Here are the 7 failure classes, what each looks like in the logs, and concrete guardrail architecture for each.
Read more
