|
71 | 71 |
|
72 | 72 | .beta-note { margin-top: 2rem; font-family: var(--mono); font-size: 0.78rem; color: var(--text-faint); letter-spacing: 0.02em; max-width: none; } |
73 | 73 |
|
| 74 | +.rd-intro { padding-top: clamp(2.5rem, 5vw, 4rem); padding-bottom: 1rem; } |
| 75 | +.rd-intro h2 { font-size: clamp(1.5rem, 2.6vw, 1.95rem); font-weight: 500; letter-spacing: -0.02em; margin-bottom: 0; } |
| 76 | + |
| 77 | +.rd-block { padding-top: 0; padding-bottom: clamp(2.5rem, 5vw, 4rem); } |
| 78 | +.rd-block p { font-size: 0.95rem; color: var(--text-soft); line-height: 1.55; margin-bottom: 0.75rem; max-width: none; } |
| 79 | +.rd-block .rd-sub { font-weight: 500; color: var(--text); margin-top: 1.25rem; margin-bottom: 0.5rem; } |
| 80 | +.rd-block ul { font-size: 0.95rem; color: var(--text-soft); line-height: 1.55; margin: 0 0 1rem 1.5rem; max-width: none; } |
| 81 | +.rd-block ul li { margin-bottom: 0.3rem; padding-left: 0.25rem; } |
| 82 | + |
74 | 83 | section + section { border-top: 0; } |
75 | 84 |
|
76 | 85 | @media (max-width: 880px) { |
@@ -286,6 +295,34 @@ <h2>Server.</h2> |
286 | 295 | </div> |
287 | 296 | </section> |
288 | 297 |
|
| 298 | +<section class="rd-intro"> |
| 299 | + <div class="wrap"> |
| 300 | + <h2>Research and Development</h2> |
| 301 | + </div> |
| 302 | +</section> |
| 303 | + |
| 304 | +<section class="rd-block"> |
| 305 | + <div class="wrap"> |
| 306 | + <p>Workbench's principles came out of building multiple agentic ecosystems before it — agent-managed services working in team formats. Components of those fully custom-built ecosystems include Context Brokerage, Inference Brokerage, Conversation Brokerage, Agent Hosts, Meta-Programming Engineering Teams, Digital Content Generators, Policy-Based File Servers, Vector and Graph Knowledge Management, Agentic Monitoring and Observability, and Agentic CI/CD. Several case studies and concept papers document the journey: the possibilities of meta-coding through agentic teams, the efficacy of cross-model quorums, and the principles of ecosystems built from teams of full agents.</p> |
| 307 | + |
| 308 | + <p class="rd-sub">Concepts applied directly in Workbench:</p> |
| 309 | + <ul> |
| 310 | + <li>When to use provider-native agents vs. custom ReAct agents</li> |
| 311 | + <li>Cognitive diversity through varied models</li> |
| 312 | + <li>Rule-following models alongside reasoning models</li> |
| 313 | + <li>Agentic runbook-based UI testing</li> |
| 314 | + </ul> |
| 315 | + |
| 316 | + <p class="rd-sub">Concepts that emerged from the same work but are not yet applied in Workbench — generally applicable to large agentic systems:</p> |
| 317 | + <ul> |
| 318 | + <li>Context engineering</li> |
| 319 | + <li>Agentic memory</li> |
| 320 | + <li>Metacognition</li> |
| 321 | + <li>Conversation as both a protocol and a collective memory</li> |
| 322 | + </ul> |
| 323 | + </div> |
| 324 | +</section> |
| 325 | + |
289 | 326 | <footer> |
290 | 327 | <div class="wrap inner"> |
291 | 328 | <div>BlueprintAgentic · © 2026 · All rights reserved</div> |
|
0 commit comments