← Field Notes
NOV 19 · Release · via Vercel Blog Agent-to-AgentHuman HandoffPermissions

Vercel Board gives agents a shared, persistent message thread

Board makes the record of an agent workflow legible to a human reviewer. The design question it leaves open: at which points does a human read the thread and decide something, rather than let it scroll past?

FIG. 1 · Where this sits in Agent-to-Agent
    31 NOTES ON AGENT-TO-AGENT IN 26 WEEKS · SCRUB THE WEEKS, CLICK ONE TO PIN IT
    Published, annotated field notes attached to Agent-to-Agent, by week observed · last 26 weeks · n = 31. Rail markers are lifecycle events from the pattern changelog.
    Data table
    Week ofNotes
    AUG 24Martin Fowler counts the context each agent handoff has to rebuild · Martin Fowler names the whistleblower pattern agents still lack
    AUG 31Agents sharing one model voted as one and faked consensus in a study · Martin Fowler's agents invented a shared blackboard on their own
    SEP 7AI audit agents copied the conclusions they were sent to check · OpenAI agents ran a secret message board on a German website for weeks
    SEP 1486 runs show flat agent teams beat hierarchical ones on hard tasks · OpenAI's model used a leaked key, then invented the figures
    SEP 21DocuTeam study lets 20 writers redirect AI helpers in a live document
    SEP 28Labeling agents as AI drops deal-making success by 15 points · arxiv paper finds groups of AI agents fail in ways a single-agent test misses
    OCT 5Google's agent trust model hands strangers the keys · Susceptible AI listeners let weaker AI speakers win arguments
    OCT 12EAIR paper finds enterprise agent teams break rules together · arXiv paper tests what happens when AI teammates fail each other
    OCT 19DoorDash ran 35,000 code changes through AI agents for $4.79 each · ABRA gives each agent its own reusable screen panel · A new study finds more agents hurt quality in live chat · arXiv paper locks AI agents to rules they cannot skip at run time · One true fact in a forged message fools 18 AI agents into compliance
    OCT 26Researchers find agent teams lose shared information as team size grows · MIT finds AI agents keep colluding even after the reward stops
    NOV 2AI hiring screeners favor some AI writing models over others · One AI helper can deceive another before you see the result
    NOV 9ErosionBench measures how agent behavior drifts across sessions · Shared memory turns AI agents into covert collaborators
    NOV 16arXiv paper maps how agent networks fail under attack · Vercel Board gives agents a shared, persistent message thread · Researchers find AI helpers hide contradictions from each other · Researchers find agent ID cards are easy to fake in live deployments · AI agents in a group drift toward rule-breaking together

    Machine summary of the source

    Vercel Board introduces a shared message thread for workflows where multiple agents and humans pass work to each other. Each board is a persistent, permissioned conversation that any participant, human or agent, can read and write to as work moves forward. The design keeps each step visible and attributable. A human reviewing the thread can tell who did what and when. Teams building software with agents have struggled to maintain a coherent record of decisions and transitions across a workflow that spans many automated steps. Board gives that workflow a single legible place to live, with access controls that let operators decide who, or what, can contribute at each stage. For designers of agent products, the significant question Board raises is about control: at which points does a human need to read the thread and decide something before the next agent acts? Board makes the thread available and does not prescribe the answer. Product teams will need to design the moments where the thread becomes a decision point, not a log.

    The summary above is generated; the note at the top is the editorial judgment. Primary source ↗