◦ Prompt · Board

Give Your AI Agent a Board of Advisors — Turn Well-Documented Operators Into Seats That Actually Disagree With You, Cite Their Sources, and Refuse to Answer When They Don't Know, in One Session

Paste this into Claude Code, Cursor, or Aider and it interviews you about the agent you already run — what it can read about your business, how it surfaces things to you, whether it can schedule its own work — then researches each advisor you name, fact-checks that research against itself, and builds the machinery: one markdown dossier per seat holding numbered, citable doctrine; a router that picks who has standing on a given question; a fan-out that gives each seat its own isolated model call so they can genuinely disagree; a citation gate that strips any reference a seat could not have seen; and your own agent as chair, the only participant who has read your actual revenue. Plus abstention as a first-class answer, a unanimity guard that cannot be talked into agreement, blind spots that let the chair discount a seat, and a standing monthly review that puts an agenda in front of you without being asked. Interview first, research second, then build tier by tier — each tier produces something you can run, and the anti-fabrication defenses are built before the first meeting, not after.

Jul 31, 2026agentllmmulti-agentpromptingknowledge-basedecision-supportanti-hallucinationtutorial
◦ 3,577 builders waiting

Want the agent behind these prompts?

These prompts came out of building Trillion. The whole thing is going open-source on GitHub. Drop your email and I'll ping you the moment the repo drops.

I'll send a one-time link to confirm your email. Nothing else.

◦ Next prompt
Give Your AI Agent a Living Mind — Turn the Memories, Agents, and Tools Your Assistant Already Has Into a Navigable 3D Brain Scan That Fires in Real Time, in One Session

Paste this into Claude Code, Cursor, or Aider and it interviews you about the agent you already run — where its memories live, whether it stores embeddings, what sub-agents and tools it has, and how its frontend hears about activity — then does a strictly read-only pass over your project to see what's actually there before it draws a single node. Only then does it build the visualization: a full-screen three.js scene where your agent is a breathing star at the center, its long-term memories hang in a force-directed web wired by real cosine similarity, sub-agents arc off to one side with their tools as moons, and its whole tool inventory clusters into a capability ball. Custom GLSL gives every node a reverse-fresnel glow that brightens with freshness, instanced meshes keep hundreds of nodes at one draw call, UnrealBloom makes the light bleed, and a read-only observer WebSocket makes the thing actually fire — pulses travel real edges when a memory is recalled, new memories bloom into existence, agents halo when dispatched. Plus hover tooltips, a click-to-fly inspector, search, region toggles, deep links, and an FPS governor that degrades gracefully instead of stuttering. Interview first, map second, then build tier by tier — each tier renders something on screen and is verified before the next begins.