Multi-agent work needs a contract
Use recent coordination research to compare agent teams under matched budgets and inspect the handoffs that fail.
Read the storyFollow a thread / 8 stories
Make a little room for a new idea. Search the collection or follow a subject that interests you.
8 stories
Use recent coordination research to compare agent teams under matched budgets and inspect the handoffs that fail.
Read the storyInspect current TRELLIS.2 exports, separate geometry from appearance, and measure accepted assets after runtime testing.
Read the storyUse agent research to improve playtesting while keeping the integrated game and human play experience visible.
Read the storyFollow policy through retrieval, memory, and delegated tools, then verify both denied and permitted outcomes.
Read the storyValidate proposed commands, geometric meaning, and the saved configuration rather than trusting a fluent explanation.
Read the storyConnect virtual-agent research to bounded character intentions, authoritative game actions, and reliable interruption handling.
Read the storyTest protective controls through tools, persistent memory, later sessions, and nearby legitimate requests.
Read the storyTest the monitor against false success claims, missing evidence, delegated bypasses, and its own recovery failures.
Read the storyTry a shorter search or choose another topic.
A place in your reading list
Follow SENN in your favorite feed reader. No inbox required.