USER GUIDE · BUSINESS FIRST

Configure an Agent control plane from a business requirement.

This guide is for business owners, product managers, system administrators, and delivery teams. It explains why the control plane exists, what each console object represents, how to choose a first scenario, and what to hand to developers for implementation.

WHY

A complete operating path, not another chat box

Connecting an Agent to an existing system involves more than calling a model. You need entry points, identity, context, business tools, permissions, approvals, audit records, delivery, and troubleshooting. BailingHub extracts those concerns into an independent A2B control plane.

Keep business boundaries

Your system triggers jobs through HTTP, exposes only selected tools, and receives results. BailingHub does not import your business code or depend on your database schema.

Govern reach, keep authority

BailingHub controls routes, tool allowlists, risk policies, rate limits, approval intent, and audit. Your backend still decides whether the acting subject may perform the operation.

Run multiple scenarios

Support, operations analysis, knowledge assistance, inbound channels, web chat, and scheduled tasks can be configured as separate routes in the same complete open-source hub.

Trace failures

Every run has a job, trace events, tool calls, knowledge references, approval intent, and explicit errors, so teams can separate model, configuration, permission, and business API problems.

REQUIREMENT MAP

Break the requirement into eight decisions

1
Entry. Does the request arrive from your backend, the web widget, or an inbound platform such as Slack, Microsoft Teams, Discord, or another channel adapter?
2
Route. Which business scenario is this, which target handles it, and which memory, knowledge, tools, budget, and delivery policies apply?
3
Target. Use the built-in llm target, a local model, a remote executor, a custom agent, or another Agent tool.
4
Model credential. Register the endpoint, key, model, and intended capability for chat, vision, audio, files, or embeddings.
5
Tool provider. Select the business actions an Agent may reach and declare scope, risk, acting subject, and approval intent through ACC.
6
Knowledge. Decide which policies, manuals, FAQs, and product documents should be retrieved for this route.
7
Input policy. Decide how text, images, audio, PDF, Word, spreadsheet, and other attachments are extracted, forwarded, or rejected.
8
Audit and delivery. Decide how results return to the caller and how operators investigate runs, trace events, diagnostics, and smoke checks.
CONSOLE MAP

What each console area solves

AreaPurposeOutputDeveloper handoff
RunsInspect input, route, status, tools, knowledge, approval, trace, and errors.job_id, trace, debug report.Job id, exact error, and debug report.
RoutesDefine one business scenario and its runtime policies.route_key, input policy, tool allowlist.Route key, trigger code, and required metadata.
ClientsControl which business system may trigger which routes.app_id, token, route allowlist.Server-side token and allowed routes.
TargetsRegister the model or executor that handles jobs.Target name, kind, timeout.Target name, executor token, and startup command when needed.
Model credentialsRegister model endpoints, keys, models, and intended capabilities.Credential name and verification result.Usually the credential name, never the secret itself.
Tool providersTurn selected business APIs into governed Agent tools.Signing secret, tool list, scopes, authz probe result.ACC/OpenAPI declaration, HMAC verification, and business authorization rules.
KnowledgeMake policies, manuals, and FAQs retrievable.Knowledge base id and retrieval test.Data source endpoint or sync rules when content comes from another system.
Web chatEmbed a route into an existing website.entry_key, script snippet, ticket rules.Embed code, visitor ticket signing, and page-context requirements.
Inbound channelsReceive messages from external communication platforms.Callback URL, platform settings, route binding.Callback setup, reply windows, and delivery limits.
Media storageStore image, audio, and file attachments locally or in object storage.Storage name, attachment URLs, input policy.Only needed when the business owns the CDN or storage domain.
DiagnosticsValidate routes, tools, executors, routing rules, dead letters, and smoke checks.Errors, warnings, smoke results.The exact object and original diagnostic message.
SCENARIO PATHS

Choose a small first scenario

Read-only business assistant

Start with model credentials, read-only tools, one route, and one client. Good examples include orders, customers, tickets, inventory, and device status.

Web support assistant

Combine support knowledge, order or ticket tools, a route, and a web entry. Signed visitor tickets carry authenticated user identity.

Create a refund request

Expose a reversible “create request” action before a direct refund operation. Declare high-impact operations with high risk or explicit confirmation.

Internal knowledge assistant

Configure an embedding model, knowledge base, ingestion, and a route. Add source synchronization only when documents come from another system.

Backend-triggered job

Call POST /run when a business event occurs. Use a business-unique request_id and receive the result through callback or polling.

Local model or Ollama

Register an OpenAI-compatible base URL such as http://host.docker.internal:11434/v1. Business callers still target the same route contract.

Local coding or operations Agent

Register an executor target and issue an executor token so a local or private-network Agent can claim outbound jobs without exposing the machine to inbound access.

Images, audio, and files

Choose local or object storage, then configure each route to forward, recognize, transcribe, extract, or reject supported media types explicitly.

DEVELOPER HANDOFF

Turn the configured scenario into an implementable contract

Do not hand developers a vague request to “add an Agent.” Provide the route, client, metadata, tool provider, acting subject, signature, and business authorization requirements.

handoff.txt
Scenario: order inquiry assistant
Route: order-query
Client: commerce-backend
Trigger: backend POST /run
Required metadata: operator_uid and order_id
Tool provider: order-tools
Allowed scopes: order.read / shipment.read
Signature: verify BailingHub sha256 HMAC on every tool call
Authority: reuse the business permission table for operator_uid
Troubleshooting: start with job_id, trace, and debug report in Runs

Continue with the API contract, business tools, SDK, and operations guide. This guide defines the business intent; developer docs define the integration details.