project
AWS platform for deploying and operating AI agents, originally based on serverless microVM sessions with an eight-hour ceiling.
No evidence-backed relationships are recorded.
The AgentCore lifecycle stack defaults episodic memory to 90 days, while the same post recommends 30 to 60 days for summaries and 6 to 12 months for semantic facts. The default is a placeholder to fork before production.
Reality
AWS supplied $6.4bn of the group's $8.3bn increase in quarterly operating income. Over the same twelve months, Amazon's net capital spending reached $169bn, the same figure as AWS's annualized revenue.
Reality
AgenticRetrieveStream splits a question into sub-queries and retrieves until it is satisfied, and the agent above it can run that whole tool call again, so reads per question stop being a number you set.
Reality
A discovery-only comparison of A2A agents on three clouds, measured in August 2026, found one protocol producing three auth models and one card whose sole declared interface URL is the container's bind address.
Reality
AgentCore runtime instances stretch agent sessions from eight hours to fourteen days. The architecture problem becomes a configuration choice, and a utilisation bet.
Reality