Today in AI — 28 February 2026 - Mitchell Bryson
Today's top AI news — curated links and commentary on the stories that matter for product builders.
Today's top AI news — curated links and commentary on the stories that matter for product builders.
Google's latest research shows multi-agent coordination can actually reduce performance, challenging the industry's $52 billion bet on orchestrated AI systems and revealing why coordination complexity may be the wrong path forward.
Mastra's open-source memory system replaces retrieval with background compression, scoring highest on LongMemEval at a fraction of the cost. If you're building agents that need to remember, pay attention.
As AI agents become economic actors - negotiating, transacting, and making commitments - they'll need infrastructure we haven't built yet: verifiable identity, earned reputation, and enforceable accountability.
A philosophical but concrete blueprint for how buyer and supplier agents could negotiate terms, compile enforceable contracts, and settle instantly across today's rails.
A practical model for growing AI agent autonomy - levels, controls, and KPIs - grounded in risk frameworks (NIST AI RMF, ISO/IEC 42001) and aligned with EU AI Act oversight.
A blueprint for agentic B2B integrations that generate OpenAPI/AsyncAPI contracts, prove compatibility with contract tests, and self-maintain as systems change.
What changes when agents own strategy and execution? Legal structure, accountability, pricing models, failure modes, and the minimum governance to ship safely.
A production template for WhatsApp support automation: compliant flows, human takeover, full audit trails, and routing that respects SLAs and customer tiers.