🔐
Agentgruppe 1 · Test 1
Login-protected Hermes Agent Info dashboard concept

Dette er et statisk design-sprint artefakt for en intern version af Hermes Agent Info. Det viser adgangsmodel, informationsarkitektur og beslutnings-dashboard — ikke live drift.

Prototype-login er kun en front-end demo. Rigtig adgang bør senere ligge i server-side auth, SSO eller gateway-beskyttelse.

Hermes Agent Info
Login-protected conceptNo live controls
Home / Command Center

Lisa’s daily start page

Forsiden prioriterer beslutninger, vigtigste interne links og seneste researchstatus — uden at blive et operations-panel.

1
Most important link
LLM routing board
4
Open decisions
Need Lisa review
7
Recently tested
Models/tools/workflows
3
Recently rejected
With reasons

Today’s answers

Best current LLM optionselected

Use primary reasoning model for planning/review; route coding prototype builds to allowed test builders.

Cheapest acceptable optionmonitor

Use free/low-cost candidates only after tool-use and reliability checks pass.

Needs attentionrisk

Do not move live sessions, logs, config/env, OAuth or controls into Agent Info.

Most visited internal links

LLM Dashboard

Model ranking, price, provider notes

Links Dashboard

Research memory and rejected sources

Workflow map

Hermes vs n8n vs LangGraph

Recently tested / rejected

testedDeepSeek builder route

Useful for compact static prototype code.

rejectedPublic/no-login dashboard

Rejected because dashboard is internal.

monitoringOpenRouter app data

Track Top 20/ranking changes over time.

Open decisions

  • Choose real auth: SSO, basic auth, magic link or reverse proxy.
  • Decide first live data source for LLM prices.
  • Define write permissions for link additions.
  • Pick evaluation cadence for testcenter.
LLM Dashboard

Model intelligence and routing decisions

Best default

Use for complex planning, review and synthesis.

Cheapest acceptable

Use only after passing tool/reliability tests.

OpenRouter tracking

Track Hermes Agent app ranking, Top 20 movement, provider availability.

ModelProviderStatusBest useCost signalReason
deepseek/deepseek-v4-flashOpenRouterbuilder-testedStatic prototype codingLowAllowed coding model for this test.
minimax/minimax-m2.7OpenRouterdesign-testedProduct/IA synthesisMediumGood broad planning output.
Free candidate poolMultiplemonitorCheap auxiliary tasksFree/lowMust pass quality/reliability tests first.
Rejected/unstable modelsMultiplerejectedDo not routeVariableFailed tool-use, latency or quality gates.
Links Dashboard

Research memory, not bookmarks

Alle eksterne kilder skal kunne markeres som useful, adopted, rejected, monitoring, later eller outdated — inkl. hvorfor de blev brugt eller fravalgt.

adoptedOpenRouter Hermes Agent app

Use for app ranking, Top 20 context and external model ecosystem signals.

monitoringLLM benchmark sources

Track but do not trust blindly; compare with local tests.

rejectedUnverified agent blogs

Checked but not used when claims lack repeatable examples.

laterHarness engineering references

Relevant for Phase 3 multi-agent evaluation work.

usefuln8n workflow examples

Useful when workflow is visual, repeatable and human-in-the-loop.

usefulLangGraph patterns

Useful when stateful orchestration matters more than simple automation.

Agent & Orchestration

Personas, skills, tools, memory, task planning, iterative loops, prompt/context engineering and specialist roles.

Phase 2

When to use

  • Specialist agent when domain is narrow and repeatable.
  • Router/reviewer when outputs need validation.
  • Simple Hermes task when orchestration is overkill.

Needed data views

Agent type, skills, tools, memory mode, risks, success examples, failure modes.

Tool Dashboard

Tool list, status, tests, guides, dependencies, alternatives, reliability and when-not-to-use guidance.

Phase 2

Status taxonomy

testedmonitorrejectedrevisit

Decision use

Helps Lisa choose native Hermes tool vs external service vs script.

Workflow Dashboard

Research, docs, coding, testing, review, monitoring, publishing, n8n, LangGraph, Hermes-native and multi-agent workflows.

Routing rule

  • Hermes: adaptive agent work.
  • n8n: repeatable visual workflow.
  • LangGraph: stateful orchestration.
  • Script: simple deterministic task.

Workflow record

Inputs, outputs, agents/tools, failure modes, reuse potential and examples.

Testcenter

Roadmap for model, agent, tool, workflow, integration and regression tests.

Result labels

best resultcheapest passneeds retestdo not use

Benchmark links

External evals must include trust/rejection notes.

Multi-agent / Harness

Planner, worker, reviewer, critic, router-driven development, Kanban coordination and evaluation harnesses.

Worth it when

Parallel research, independent review, complex build/eval loops or specialist isolation are needed.

Overkill when

Single deterministic task, simple script, or no meaningful review boundary.

Info / Knowledge Hub

Guides, tips, cheapest/best/fastest/safest solution, FAQ, glossary, decision trees and reusable checklists.

Guide examples

  • Use Hermes when…
  • Use n8n when…
  • Use LangGraph when…
  • Do not overbuild when…

Boundary

Explains decisions; does not expose live controls or raw operational data.

Must never be exposed

Secrets, credentials, raw logs, raw sessions, raw configs, env values, OAuth states, private paths, live controls or runtime operations.

Allowed after login

Curated research, sanitized summaries, decision frameworks, link intelligence, model/provider notes, test summaries and workflow maps.

Agent group

Product/IA, Access/Safety, UX Prototype, Builder, Spec Review, Quality Review.

Builder model

deepseek/deepseek-v4-flash via OpenRouter for build artifact; MiniMax used for design roles.

Artifacts saved

Prompts, outputs, model/session info, build files, checksums, review notes and evaluation rubric saved in run directory.