Mihail Eric's Stanford class on AI-native engineering reveals why multi-agent workflows fail without test contracts, consistent codebases, and incremental scaling—and why managing agents is really just managing people, with less forgiveness.

Emergent hit 7 million apps in 8 months by betting that the moat in AI coding isn't generation—it's verification, deployment, and the full software lifecycle. 80% of their users have zero programming knowledge.

As AI agents gain tool access and long-horizon autonomy, the bottleneck shifts from model intelligence to governance—permissions, guardrails, monitoring, and liability. That's where job displacement becomes real.

YC's latest Light Cone episode argues that agents are becoming the primary selectors of developer tools, making documentation the new distribution channel. The companies optimizing for agent-parsable APIs and docs—like Resend and Supabase—are already seeing outsized growth, while legacy tools with human-first UX get skipped entirely.

Anthropic's interpretability team can now peer inside Claude's internal reasoning and catch it thinking something different from what it writes. For enterprise teams relying on chain-of-thought explanations as evidence, this changes the trust equation entirely.

The creator of a popular AI coding tool explains why they build for the model six months ahead—and why productivity measured by pull requests might be the 'simplest stupidest measure' of what's actually happening.

OpenClaw's creator argues that 80% of apps will disappear once personal agents run locally with full desktop access. The demo is compelling. The missing guardrails are the real story.

Coding agents aren't winning because of better models — they're winning because CLI-based tools like Claude Code manage context better than any IDE. The real productivity unlock comes from sub-agent architecture, aggressive context clearing, and treating tests as the verification loop that lets agents run fast without breaking everything.

Most MCP servers expose raw REST endpoints to agents that can't afford to browse them. Designing agent-native tool surfaces — curated, outcome-oriented, token-aware — separates production-grade integrations from expensive handshake failures.

Amazon Kiro replaces ad-hoc prompting with a spec-driven workflow: structured EARS requirements, correctness properties, and property-based tests. The result is AI-generated code you can actually verify against its original intent.