PLAYGROUND // EXPERIMENTS

Live Experiments

WebGPU simulations, agentic systems, real-time interfaces. Built in public, shipped imperfect.

Zero-Trust Agent Gateway

Watch three mock agents present simulated identities to a gateway that checks each one, routes routine actions straight through, and blocks sensitive actions until you personally approve or deny them — while an agent with an expired or unregistered identity is rejected before its requested action is even read.

agent-opssecurityzero-trustidentityinteractive

2026.09.04

EXP_039

BETA

MHS Mock Hardware Controller

This experiment demonstrates a full protocol cycle — device discovery, capability negotiation, and structured read/write commands — sent to a simulated kinetic installation of two motors and a light fixture, rendered live on a Canvas 2D viewport. It models the shape of Anthropic's Model Hardware Standard research-preview announcement, not an integration with the real MHS SDK.

Canvas 2DOpenAIAgent OpsZodHardware Control

2026.09.03

EXP_033

BETA

Shared Agent Memory Graph

Two mock agents, Curator and Auditor, read and extend one seeded brand-asset knowledge graph of guidelines, decisions, campaigns, and channels. Trigger their scripted queries and watch two of them render a live graph traversal beside a flat-similarity search over the identical text, so the gap between structured relationships and flat search is something you see, not something the copy just asserts.

agent-opsmemoryknowledge-graphcogneeinteractive

2026.08.30

EXP_032

BETA

Fallback Model Router

A visitor triggers three model calls in sequence: a healthy primary response, a simulated primary failure that reroutes live to a lower-tier fallback model, and a simulated total outage that fails fast with a clear error — every result labelled with the model that actually served it.

agent-opsresiliencereliability@diabolicallabs/llm-client

2026.08.26

EXP_038

BETA

Local Qwen3.8-27B Agent-Routing Benchmark

22 real historical fleet-dispatch decisions — redacted briefs paired with their actual `delegate:` ground truth — run through a self-hosted Qwen3.8-27B on Ollama and through the fleet's default cloud model, scoring which specialist each one predicts and measuring the real accuracy, latency, and cost trade-off of routing that one decision locally instead of to the cloud.

agent-opscost-optimisationmodel-routingbenchmarklocal-inference

2026.08.25

EXP_037

BETA

Multi-Agent Coordination-Failure Simulator

Two independent worker agents given an identical, under-constrained task in a shared Docker workspace, with no channel to talk to each other, were logged overwriting one another's already-completed output — real independent adversarial convergence when isolation boundaries fail. A second, isolated-container condition shows the same interference structurally cannot occur once each agent gets its own private workspace.

agent-opssecuritydockersandboxingmulti-agent

2026.08.25

EXP_031

BETA

Reversibility-Tiered Approval Gate

Watch a scripted mock agent work through nine tool calls — reading files, editing config, deleting data, publishing externally — with each one classified by reversibility tier and gated as auto-run or approval-required, and personally approve or deny the ones the gate blocks on.

agent-opsgovernancetrust-tiersinteractive

2026.08.21

EXP_030

BETA

Programmatic-vs-JSON Tool-Calling Benchmark

Six data-lookup tasks over a fixed mock order dataset run twice each against two models — once through native JSON tool-calling, once by having the model write code that calls typed function stubs directly in a sandbox — reproducing arXiv 2608.06370's finding that programmatic tool calling needs far fewer LLM round trips per task than the JSON tool-calling pattern most agent frameworks default to.

agent-opstool-callingbenchmark@diabolicallabs/llm-client

2026.08.17

EXP_029

BETA

Effort-Level A/B Harness

Runs a fixed six-task benchmark at four reasoning-effort levels against Claude Opus 5, recording real cost, latency, and a rubric-scored quality result for every task-effort pairing, then charts the trade-off curve.

agent-opscost-optimisationmodel-routing@diabolicallabs/llm-client

2026.08.12

EXP_028

BETA

Local Security-Policy Interception Middleware

Watch a mock agent propose tool calls — reads, writes, deletes, publishes, credential access — and this experiment intercepts each one in real time, scores it against an editable local policy schema, and blocks anything at or above your threshold until you approve or deny it.

securityagent-opsgovernanceinterceptionpolicy

2026.08.05

EXP_027

BETA

Model-Routing Cost/Latency Benchmark

A fixed task set of five experiential-design briefs runs against three models — Claude Opus 5, GPT-5.6 Sol, and Gemini 3.6 Flash — and a deterministic rubric scores each response, demonstrating the real cost, latency, and quality trade-off behind routing a task to a bigger model instead of a cheaper one.

agent-opscost-optimisationmodel-routingbenchmark

2026.08.03

EXP_026

LIVE

Bloom Field

A Canvas 2D generative garden of procedural blooms that grows on its own — no login, no product, nothing agentic. Enable your microphone and sound layers a growth pulse, hue shift, and sway on top of the ambient rhythm; decline, and the garden keeps breathing regardless.

Canvas 2DWeb AudioGenerative ArtAmbient

2026.08.02

EXP_025

BETA

Skill Prompt Auditor

Paste an agent skill's prompt text — a SKILL.md body or system prompt — and get a flagged report of hardcoded design biases: colour palettes, layout defaults, typography directives, tone constraints, and output-format lock-ins, checked entirely in your browser before you ever run the skill.

securityagent-opsdesign-biasstatic-analysis

2026.07.31

EXP_024

BETA

Token-Reuse Cost Visualizer

Upload a token-log export or load the bundled sanitized sample, and this experiment charts reuse ratio over time, reused-versus-fresh token composition, and an estimated cost split — entirely in your browser.

agent-opscost-optimisationtoken-reuseprompt-caching@diabolicallabs/llm-pricing

2026.07.28

EXP_023

BETA

Trust-Tier Compliance Linter

Paste an agent's declared trust tier and its described execution or publish behaviour, and this experiment scores whether that behaviour actually matches Diana's own Autonomous / Always-Review / Conditional rules, not a generic industry checklist.

securityagent-opsgovernancetrust-tier

2026.07.25

EXP_022

BETA

MCP Capability-Discovery Visualizer

Paste or upload an MCP configuration — a JSON list of servers and the tools each one declares — and this experiment shows a server-to-tools capability map, labelling any unreadable server as unavailable instead of breaking the whole view.

LLM Citation-Integrity Metadata Generator

Paste content or a URL and this experiment extracts candidate citable facts, then recommends schema.org markup and source-attribution phrasing for each one — it shows how to prepare content for AI citation before a crawl ever happens.

GEOagent-ops@diabolicallabs/llm-clientschema.org

2026.07.19

EXP_020

BETA

Declarative Multi-Agent Router

Submit a task and watch a real LLM call route it against a declarative task-shape-to-capability table, dispatch that route's real sub-agent calls in sequence or parallel, and render a live trace of the decision and every sub-agent's actual output — not a diagram of how routing could work, but routing that runs.

agent-opsmulti-agentorchestration@diabolicallabs/llm-client

2026.07.16

EXP_019

BETA

ASI-Checklist Linter

Paste or upload an agent's configuration — tool definitions, MCP servers, hooks, memory writes — and get a ten-category scorecard against the OWASP Top 10 for Agentic Applications, with a labelled finding for every risk pattern the static analysis actually finds.

securityagent-opsOWASPstatic-analysis

2026.07.15

EXP_018

BETA

Reasoning Budget Router

Submit a task and watch a heuristic classifier score its complexity, route it to the cheapest model tier that can handle it, then run the real call and chart the cost and latency you'd have paid at each tier — the fleet's own model-tiering instinct made explicit and measurable.

agent-opscost-optimisationmodel-routing@diabolicallabs/llm-client

2026.07.13

EXP_017

BETA

LLM Citation Auditor

Enter a brand name and audit which sources Perplexity and ChatGPT actually cite when asked about it — a footprint map of publications, review sites, and URLs each model draws on, built entirely on live queries with no cached results.

GEOagent-opsmulti-provider@diabolicallabs/llm-client

2026.07.11

EXP_016

BETA

AI Impression Simulator

Type a brand name and watch ChatGPT, Gemini, and Claude answer the same three questions a real buyer would ask — discovery, consideration, comparison — then see each model's visibility score, sentiment, and consistency compared side by side.

OpenAIGeminiClaudeSSEGEORecharts

2026.07.10

EXP_015

BETA

Narrative Micro-World

A small navigable brand world — three scenes, dialogue and environment generated live by an LLM in response to your choices, held to an authored style/lore block so it never drifts off-brand.

LLMCanvas 2DZodNarrative DesignBrand WorldPrompt Injection Defense

2026.07.09

EXP_014

BETA

Machine-Buyer Storefront A/B

A scripted LLM shopping agent buys from two mock storefronts with identical inventory and prices — one built with countdown timers and obscured pricing, one built for machine legibility — and the harness measures which storefront it actually completes checkout on.

agent-opse-commerceevaluationGEO

2026.07.04

EXP_013

BETA

Spatial Telemetry Playground

A simulated gallery floor where twelve-plus autonomous synthetic visitors move under distinct `wander`, `cluster`, and `queue` behaviours, streaming structured spatial events — zone entry/exit, dwell, crowding — to a rule-based agent loop that adjusts lighting, display content, and routing in real time. Zero LLM cost by default; deterministic seeded runs make the whole loop testable.

Canvas 2DRule-Based AgentDeterministic SimulationSpatial Events

2026.06.28

EXP_012

BETA

Agent Permission Linter

Paste a system prompt and tool definitions. Get a flagged list of privilege escalation risks and missing scope constraints — before your agent reaches production.

securityagent-opstoolinggovernance

2026.06.22

EXP_011

LIVE

Spatial Brand Mirror

Your webcam feeds a generative art system that responds to your presence and motion in real time. The output is not a mirror — it is an abstract transformation. Movements become shape, colour, and rhythm on a p5.js canvas tuned to a specific visual palette. Diana builds this physical-digital feedback loop for experiential clients. This experiment shows it running in a browser tab, responding to whoever stands in front of it.

p5.jsWebRTCGeminiComputer VisionGenerative ArtBrand IdentityCreative Tech

2026.06.17

EXP_010

LIVE

Agent Dream State Visualiser

Anthropic shipped Dreaming — between-session memory consolidation for Claude agents — in May 2026. This experiment shows what that process might look like as a generative canvas. A scrolling log feed from Diana's real agent fleet drives a background reflection cycle: every 12 seconds, a structured reflection arrives and the particle system shifts. Colour, velocity, and flow encode what the model noticed. The viewer reads that something is consolidating. They cannot name what.

p5.jsGenerative ArtOpenAIAgent OpsClaude DreamingParticle System

2026.06.17

EXP_009

BETA

Agentic Reliability Dashboard

Head-to-head tool-calling reliability test across three frontier models. Run 15 tasks simultaneously against GPT-5.5, Claude Opus 4.7, and Gemini 3.1 Pro. Track pass rates, latency, and JSON validity in real time.

OpenAIAnthropicGoogleSSEReliability Benchmark

2026.04.26

EXP_008

BETA

Generative UI Renderer

Describe a UI layout in plain text. An LLM generates a typed component tree and streams it live — each block renders as it arrives. Google's A2UI validates this pattern. Diana built it first.

LLMSSEGenerative UIA2UIStreamingAgent Ops

2026.04.25

EXP_007

BETA

Orchestration Map

Drag-and-drop agent topology builder. You construct your own agent architecture, and an LLM annotates each node and edge as you build, interrogating your design decisions in real time.

React FlowAgent ArchitectureOpenAISSEDrag-and-DropInteractive DiagrammingMulti-Agent Patterns

2026.04.23

EXP_006

BETA

ADK Visualizer

Static interactive diagram contrasting monolithic and orchestrated agent topologies from Google's ADK case study, annotated in real time by an LLM.

React FlowGoogle ADKAgent ArchitectureOpenAISSESequentialAgentMulti-Agent Patterns

2026.04.21

EXP_005

BETA

Autonomous Brand Pipeline

Submit a creative brief and brand rules. A three-stage LLM pipeline generates N concept variants, evaluates each against your rules, and ranks the top K — streamed live as it runs.

Anthropic SDKClaudeBullMQSSERedisAgent OpsAutonomous Pipeline

2026.04.19

EXP_004

LIVE

Routines Repo Audit

Anthropic Routines powers a nightly Claude Code session that audits 8 repos for stale manifests, CI failures, open Dependabot PRs, uncommitted worktrees, and stale branches — then posts a structured summary to Slack.

Anthropic RoutinesClaude CodeGitHub APISlackAgent Ops

2026.04.18

EXP_003

BETA

Crowd Flow Twin

This experiment couples three simulations: 10,000 autonomous agents running Boids flocking, a density trail grid tracking where agents have travelled, and a Gray-Scott reaction-diffusion system transforming raw crowd density into emergent organic patterns. Each subsystem reads and writes shared state. The result is a crowd simulation that visualises density as living structures, not heatmaps.

Canvas 2DBoidsSpatial HashGray-Scott RD

2026.04.15

EXP_002

BETA

Gesture Fluid Wall

This experiment runs a full Navier-Stokes fluid solver — diffusion, advection, pressure projection — at 60fps on a 256×256 grid using only CPU and Canvas 2D. No WebGPU, no WebGL. Stam's unconditionally stable semi-Lagrangian advection translates directly from offline VFX to interactive use. The simulation never blows up regardless of pointer speed.

Canvas 2DStable FluidsFluid DynamicsNavier-Stokes

2026.04.13

EXP_001

LIVE

Voice Particle Instrument

This experiment demonstrates that 150,000 GPU-instanced particles respond to microphone input at 60fps in the browser without WASM or native code. Audio frequency data drives per-particle physics on the GPU; no client-to-GPU bridge latency limits the scale. The terrain mesh deforms in sync, anchoring the particle field.

WebGPUWeb AudioCompute ShaderThree.js

2026.04.11

37 experiments loaded