How the builder demo works
GhostFactory AOS Control Plane is where you would run a fleet of AI agents split into factories: who exists, what each run did and cost, which policy stopped it, and where a human has to sign. This is a clickable demo of it. The operations data is invented. The agent catalog is real: it comes from K-B, the GhostFactory knowledge base.
The catalog holds agents in teams, grouped into factories. of them have a running instance in the demo fleet.
What this is
The demo shows what operating an agent fleet could look like, from the catalog down to a single signed decision. It also holds itself to one rule: a number on a screen is derived from data underneath it, not typed into the page. Where two screens show the same fact, they read it from the same place.
- Everything runs in your browser. There is no backend, no agent process and no call to any model.
- A "run" is a simulation. It walks a fixed list of steps, prices every model call with the rates in the model registry, and records the result as if it had happened.
- Some screens are live projections of what you do here. Others are designed screens with invented data that you can browse but not change.
How to read this page
Every screen section carries one or more tags. Notes call out controls and texts that promise more than the demo does.
- live
- Computed or written in your browser, and read by other screens: simulations, the ledger, Shield, HITL Queue, Lab.
- K-B
- Real catalog data from K-B: agents, teams, factories, contracts, model recommendations.
- design
- A screen or panel with invented data. You can browse, filter and open details; nothing changes underneath.
- plan
- A control or a claim the demo does not implement. Clicking it does nothing, or only shows a toast.
The demo keeps its state in your browser, and there is no reset button. See What your browser keeps.
Catalog and fleet
Two different things, and the screens label which one they show.
- Catalog
- Who exists. orchestrators and members from K-B, each with a role, a team, a factory, contracts and a recommended model.
- Fleet
- What runs. Instances with status, load, uptime and task counts. The fleet is invented; sealing an agent in the Agent Builder adds an instance until the next reload.
An agent in the catalog with no instance is a state, not a gap. The agent card says so: "The agent is in the catalog, but the fleet has not deployed it." Agents lists it under Catalog, Factories counts catalog and deployed separately, and Topology marks a team with nothing deployed.
Factories, teams and agents
A team is an orchestrator and its members, as K-B defines them. A factory pairs K-B teams into one unit with its own graph in the Editor. Every agent carries its K-B contracts: the skill it performs, what it requires, what is optional, what it returns, and its token budget. K-B also recommends a model for each agent and lists models to avoid; the agent card compares that with the model the instance runs.
The Topology map draws teams as boxes. Not every team has a box on the map yet; the full catalog is on Agents.
Runs, spans and the ledger
You start a run in the Editor under Simulate. Each step of the run is a span, and each span is appended as an event to the ledger. When the run ends, its events are sealed into a block. A block stores the SHA-256 hash of its contents, the hash of the previous block and a merkle root, so the chain is append-only: changing an old entry breaks every hash after it.
Overview, Runs & Traces, Cost & Tokens, HITL Queue, Ledger / Audit and Lab read the ledger. A run you simulate shows up in all of them, next to the invented history they start with.
Verify Integrity on Ledger / Audit recomputes every block hash. Tamper edits a sealed entry so that Verify has something to catch.
Tamper is saved with the ledger. The chain stays broken in this browser, across reloads, until you clear the site data.
Shield and human sign-off
Shield rules are predicates the simulation checks. Task rules that refuse outright are checked before a run starts; the rest at the policy checkpoint, once the run's real cost is known. Step rules are checked before each step that reads or writes something. A rule does one of two things.
- escalate
- The run parks and waits for a signature. The request appears in HITL Queue and the sidebar shows a count.
- block
- The step is refused. Some rules re-route it (a write to a production path goes to staging instead); otherwise the run ends.
Examples you can try: the preset "Write prod migration" parks on R.01, a destructive operation. Switch R.01 off on Shield Rules and the same run parks on R.03 instead, because it costs more than its factory's per-task ceiling. A task that contains an email address is refused by R.08 before anything is dispatched.
Approve resumes the run, which then finishes and seals its block. Deny ends the run; the remaining steps are skipped and the block is sealed with the denial. Both decisions are ledger events signed by you.
What a run costs
An agent loop re-sends the whole conversation on every model call. A run therefore pays mostly for input, not for the text the model generates. A tool result, such as a file the agent read or a test transcript, joins the conversation and is paid for again on every later call.
The prompt cache softens this: the part of the conversation an earlier call already sent is read from cache at a fraction of the input rate, and writing to the cache costs a little more than plain input. The simulation prices planning and generation on the orchestrator model and research and review on the cheap tier. Rates come only from the model registry. The run drawer on Cost & Tokens splits a run into fresh input, cache read and output.
Models and routing
The model registry lists models. It is built from the public catalog at models.dev during maintenance, not fetched while you click, so prices are as of the last update. Models are grouped by their role in an agent system: Orchestrator, Worker, Cheap, Specialist, Local, Embedding and Deterministic.
Each routing role has a routing chain: a primary model, a failover at a different vendor, and an escalation. You see it in three places:
- the agent card, with the chain, the cost per task, what K-B recommends and whether the deployed model matches;
- the Agent Builder, whose model picker shows the chain for the chosen role and warns when a model is off-policy;
- the Models tab of the Editor library.
What your browser keeps
The demo stores its state in this browser's local storage for this site:
gf_ledger- the ledger: events and sealed blocks
gf_shield_rules- which Shield rules are switched on
gf_lab- Lab jobs, configs and the open tab
gf_data_mode- Seeded or First-run
gf_theme- Light or Dark; this page follows it
gf_screen- the last screen, reopened when you come back
gf_ov_range- the range picked on Overview
gf:cmdk:recent:v2- recent command palette entries
Agents sealed in the Agent Builder and factories sealed in the Factory Builder live only in memory and are gone after a reload.
There is no reset button. To start over, clear this site's data in your browser settings. That also repairs a chain broken by Tamper.
Overview livedesign
What did the fleet do since you left? Runs completed and failed, money spent, sign-offs waiting, trends and incidents. The figures are computed from the ledger and from an invented run history; the header counts agents and factories from the fleet.
- Session, 24h, 7d and 30d switch the range and are remembered.
- Links lead to HITL queue and Factory Editor; Review on an incident opens Quarantine.
- The screen repaints when the ledger changes.
View buttons and the incident rows.
Factories K-Bdesign
Which factories exist and what is in them? Factories and their teams come from the catalog, with catalog and deployed counts per factory. Throughput figures are invented.
- Inspect opens the factory's graph in the Editor.
- Open Factory Builder starts a new factory design.
- Quick spawn fills an empty slot on the page only; nothing is saved.
Scale and Quiesce.
Topology K-Bdesign
How do teams connect? A company map where each box is a K-B team, colored by what the fleet has deployed. Channels, call counts and SLAs are invented. Not every team has a box on the map yet.
- Departments, Data flow, Policy and Cost change what the map highlights.
- Click a team, a shared service, an edge or a table row for details; the details link to other screens.
Agents K-Bdesign
Who exists and who runs? Two lists: Deployed (fleet instances, with invented load and uptime) and Catalog (every agent from K-B). See Catalog and fleet.
- A row opens the agent card: role, team, factory, contracts, runtime, and the model with its routing chain and the K-B recommendation.
- Graph jumps to the agent's node in the Editor. Edit opens the Agent Builder with the agent filled in.
- Deploy on a catalog row also opens the Agent Builder; it does not deploy anything by itself.
Editor livedesign
What does a factory look like inside, and what happens when it runs? A node graph of the factory with a library of Agents, Skills, Models, RAG, Rules, Packages and Flow. The graphs are designed examples; the Models tab reads the model registry.
- Build, Route, Validate
- Build is the plain editing view; Route animates the routing paths; Validate marks findings on the graph.
- Deploy
- Opens a dry-run diff of the graph.
- Simulate
- Opens the run drawer. A preset only fills in the task; Run starts it. Steps stream into the trace, every step lands in the ledger, Shield checks run as described in Shield and human sign-off, and the finished run is sealed into a block.
Library cards, the + on a card and the Graph, Flow and Schema views change the canvas.
Deploy to Staging in the dry-run dialog only shows a toast saying that nothing was deployed. The options in the dialog change nothing.
Agent Builder K-Bdesign
How would you define a new agent? Pick a template, then walk the steps from identity to deploy. The templates are a few generic workers plus every agent in the catalog; a catalog template brings its K-B role, contracts and a system prompt composed from them. The model picker follows the routing chain of the chosen role.
Seal & Deploy adds the agent to the fleet and opens the Editor with its node. It writes nothing to the ledger or the ADR Vault. The instance lives in memory and is gone after a reload.
Factory Builder design
How would you design a new factory? Pick a topology (ROMA Planner, Pipeline, Map-Reduce or Review loop), then go through Identity, Topology, Squad, Guards and Review.
- Seal & Open in Editor generates the factory's graph and opens it in the Editor. It lives in memory until the next reload.
- Open in Agent Builder fills the Agent Builder with the worker you designed.
Runs & Traces livedesign
What did a run do, step by step? A list of runs (invented history, with your simulated runs on top) and a Trace Inspector that shows the spans of the selected run as a waterfall.
- Select a run, then a span, to see its details.
- Replay on a ledger block opens its run here.
The OK, Warn, Err and HITL pills only change their look; the list is not filtered. Also All, the factory and time pickers, Export CSV, Replay, View in Editor, Open ledger block, Flag and As eval set.
Cost & Tokens livedesign
Where does the money go? Spend per agent, grouped into factories by the catalog, priced with the rates of the model registry. Simulated runs join the list of the most expensive runs. Budgets and month-to-date billing are invented.
- Factory rows and expensive-run rows open a drawer; a run drawer splits the tokens into fresh input, cache read and output (see What a run costs).
Resolve and Edit.
Inbox design
What needs attention right now? One feed of HITL requests, Shield blocks, quarantine flags, cost alerts and connector errors. The feed is invented.
- A row opens a drawer with a link to the screen it came from.
Severity, source, team and time filters; Unread, All, Mentions and Subscribed; Mark all read; Filters; Approve refund, Edit amount & approve, Reject & send to support; Edit.
Schedules design
What starts runs without a human? Cron, webhook and event triggers. All invented.
The on/off switches change their look only. Nothing is saved or started.
Deployments design
Which version runs where, and is the canary safe? Versions, traffic split, eval gates, a deploy log and rollbacks. All invented.
- A version row opens a drawer.
Hold canary, Rollback and Promote → 50% do nothing. Promote when soak passes, Open incident, View diff, Forward to ADR Vault and Acknowledge only show a toast. An adapter promoted from the Lab does not appear here.
Evals & Replay design
Does a new version break anything? Golden sets, adversarial cases and red-team suites, a pass/fail matrix, a regression diff and production replay. All invented.
- → open in Deployments switches to Deployments.
Open ADR, Add to red-team suite, Re-prompt, Skip case, the replay pickers, Run replay, Save as suite and Cancel.
RAG Stores design
What can agents look things up in? Five stores: a golden-set YAML file used as a fast path, and vector stores. All invented.
- A row opens the store's drawer. Its query box (Run, or a suggested query) returns sample matches and shows whether the fast path or the vector search answered.
Reindex, Export · JSONL and Pin to Retrieval.
Skill Libraries K-Bdesign
What can agents do, and with which tools? Two layers, and they are different things:
- Skill Libraries
- The skill contracts from K-B, per team: triggers, input and output shape, constraints.
- Tools / MCP
- The tools of this demo that the Editor places on the canvas, such as reading a file or querying a store. They are not K-B skills.
Switch layers at the top and filter by team.
Knowledge Graph K-Bdesign
What depends on what? Entities and their relations: factories, agents, skill libraries, tools, stores, ADRs, eval suites and incidents. The graph shows a hand-picked selection of factories and agents, not the whole catalog. Their nodes read role, team, contracts and model from K-B; runtime figures on them are invented and labeled as such.
- Entity, Blast radius, Governance and Traffic change the view; the type filters hide node kinds.
- A node opens its details. On an agent, Open agent card opens the same card as on Agents, and Focus blast radius shows what it affects downstream.
ADR Vault design
Why is the system built the way it is? Architecture decision records with their status. The records are invented.
- Filter by status and select a record to read it.
Seal & Accept, Request changes and Add reviewer.
Shield Rules live
What is an agent not allowed to do? Eight rules, R.01 to R.08, each with its scope (task or step) and action (escalate or block), and how often it fired this session. The simulation checks exactly these rules; see Shield and human sign-off.
- A switch turns a rule on or off. The choice is saved and changes what the next simulation is allowed to do.
HITL Queue live
What is waiting for a human? Pending sign-offs from the ledger, with Approve and Deny. When the queue is empty, a link takes you to the Editor to create one. What Approve and Deny do to the run is described in Shield and human sign-off.
Recent Decisions lists your decisions, marked LIVE, above an invented history. The totals in the header add your decisions to fixed numbers.
Connectors design
Which outside services can agents reach? Eight integrations with their status. All invented.
- A card opens its drawer.
Configure, Rotate Key and Disable.
Quarantine design
Which agents are isolated, and why? Tripped circuit breakers, isolated agents and resolved cases. All invented.
- A row opens a drawer with the incident.
Inspect Stack, Release and Terminate.
Ledger / Audit livedesign
Can the record be trusted? The chain of sealed blocks: an invented seed history plus every block sealed in this browser. See Runs, spans and the ledger.
- Verify Integrity recomputes every hash and reports the first broken block.
- Tamper edits a sealed entry. The damage is saved; see the warning in Runs, spans and the ledger.
- Replay, on a block that holds a run, opens the run in Runs & Traces.
- Clicking a block opens it in a drawer: its hashes, every entry as it was sealed and, for a block sealed by a run, the run. Verify & Replay steps through the entries and recomputes the chain, so after Tamper it shows the break. A block number that is not in the chain opens as not found.
Export Chain · CSV, Download Compliance Bundle and Export Block · JSON in the block drawer.
Reliability design
Is the platform meeting its targets? SLOs, error budgets, active incidents and post-mortems. All invented.
- An incident opens its details; Open runs switches to Runs & Traces.
- A post-mortem opens its details; Linked ADRs → switches to ADR Vault.
Acknowledge, Page secondary, Escalate, Service health → and Edit post-mortem.
Lab livedesign
Can the fleet learn from its own record? Datasets are definitions over the ledger: sealed blocks, run spans and HITL decisions as preferences. Their counts grow as you simulate and sign.
- Datasets
- What each dataset selects; Tune → opens Tuning with that dataset picked.
- Tuning
- Create job and Start training. Training paces through its epochs and draws a loss curve.
- Configs
- Edit a queued job's settings; Save config records a new revision.
- Eval Gate
- Compares the result against the eval suites; Promote to Deployments is enabled when the gate passes.
Creating a job, training, saving a config and promoting are all ledger events; they are not sealed into blocks. The open tab and your jobs are remembered.
- No model is trained and no adapter is produced. The loss curve and the eval pass rates are simulated; they are deterministic, so the same job gives the same numbers.
- Promote to Deployments opens Deployments, which does not show the promoted adapter.
Command palette design
⌘K or Ctrl+K opens a searchable list: Recent, Navigate, Actions, Simulate, Factories, Agents, Runs and ADRs. The list is fixed; it is not built from the sidebar or the catalog.
- Navigate entries open their screen. They cover most screens, not all of them.
- Spawn new agent opens the Agent Builder; Open Inbox · Triage opens Inbox.
- Factory, agent, run and ADR entries are static examples that do not follow the catalog. They open the matching screen.
- Verify chain integrity runs the same check as Verify Integrity on Ledger / Audit and reports the result, including a chain broken by Tamper.
- Export compliance bundle and Pause all factories only show a toast. Toggle theme reports that it is not available; use Light and Dark in the top bar.
- Simulate entries raise a scripted incident in a strip across the top of the screen. It does not reach HITL Queue or the ledger. Approve all and Deny all pending HITL act on those scripted incidents only, not on sign-offs in HITL Queue.
Atelier guide design
The button marked A at the bottom right opens a chat panel. It answers from a script: your question is matched against keywords and the guide replies with prepared text and figures, plus a link to the screen that shows the topic. A question it does not recognize gets "I don't have a tool wired for that yet." The header and the welcome text say that the answers are scripted.
No model answers and nothing you type leaves your browser. The tool calls and the model name the panel shows are part of the script, and the figures in the answers do not follow the screens.
Top bar and rail
- Seeded / First-run
- First-run shows the empty state of seven screens: HITL Queue, Quarantine, Ledger / Audit, ADR Vault, RAG Stores, Skill Libraries and Connectors. The others stay as they are. Remembered.
- Light / Dark
- The theme. Remembered, and this page follows it.
- Emergency Stop plan
- Does nothing.
- + Spawn Factory
- Opens Factories.
- Play Incident
- A scripted walkthrough of about 18 seconds: a destructive command is caught by Shield, escalated, denied in HITL Queue, isolated in Quarantine and sealed in the Ledger. It moves between those screens with captions; arrow keys step, Space pauses, Esc quits. It writes nothing to the ledger.
- How this demo works
- The link under the logo opens this page.
The footer of the sidebar is static text.
Glossary
- Factory
- A unit that pairs K-B teams and has its own graph. More
- Team
- An orchestrator and its members, as K-B defines them.
- Orchestrator
- The agent that leads a team and hands work to members.
- Member
- An agent in a team that does one kind of work and reports back to the orchestrator.
- Catalog
- Every agent K-B defines. More
- Deployed / on the shelf
- An agent with a running instance in the fleet, or a catalog agent without one.
- Contract
- A K-B skill an agent performs: what it requires, what is optional, what it returns, its budget.
- Affinity
- The model K-B recommends for an agent, and the models it advises against.
- Primary / failover / escalation
- The links of a routing chain: the default model, a fallback at another vendor, and a stronger model to escalate to. More
- Model registry
- The list of models with their roles and rates, updated from models.dev.
- Run
- One execution of a task by a factory; in the demo, a simulation.
- Span
- One step of a run, with its duration, tokens and cost.
- Trace
- All spans of a run, shown as a waterfall.
- Ledger
- The append-only record of everything that happened. More
- Block / sealed
- A group of ledger events closed with a hash that chains it to the previous block.
- Genesis
- The start of the chain, shown on Ledger / Audit.
- Verify Integrity
- Recomputes every block hash and finds the first broken block.
- Tamper
- Deliberately edits a sealed entry so Verify can catch it.
- HITL
- Human in the loop: a run waits for a person to approve or deny.
- Shield
- The policy rules every run is checked against. A rule escalates or blocks. More
- Ceiling
- The per-task spend limit of a factory; rule R.03 escalates a run past it.
- ROMA Planner
- A factory topology where a planner fans tasks out to a squad of workers.
- Arbiter / Worker
- A deterministic router without a model, and an agent that does the work.
- ADR
- Architecture decision record.
- RAG store
- A store agents retrieve context from.
- Golden set
- Known questions with known answers, used as a fast path and as an eval suite.
- Skill Libraries vs Tools / MCP
- K-B skill contracts versus the demo's own tools. More
- Canary / Soak
- A new version on a small share of traffic, and the waiting period before it is promoted.
- Eval gate
- A check that must pass before a version or adapter is promoted.
- Circuit breaker
- Stops an agent that misbehaves, such as one stuck in a loop or over its token limit.
- Quarantine
- Where an agent goes when its breaker trips: no traffic in, no traffic out.
- SLO / Error budget
- A reliability target, and how much failure is left before it is missed.
- Connector
- An integration with an outside service.
- Seeded / First-run
- Sample data or the empty states a new installation would show.
- Cache read
- Input tokens served from the prompt cache at a fraction of the input rate. More
Limits of the demo
- No backend and no agents. No model is called, including by the Atelier guide.
- Operations figures are invented. The catalog comes from K-B and the model registry from models.dev, as of the last update.
- State lives in this browser only, and there is no reset in the UI. Agents and factories you seal last until the next reload.
- Controls tagged plan do nothing or only show a toast.
- Topology does not draw every team yet.
- The command palette holds static examples that do not follow the catalog.
- Built for desktop screens. Search engines are asked not to index it.