Support Root — agents and methods
Module overview · Common methods
P A skill is a complete procedure that can use LLM judgment and optional executable helpers. A tool is runnable source and/or a binary inside that procedure. Connector calls, state transitions, agent calls and permission checks are runtime access, not extra learned skills or imaginary binaries. Only the methods and segments selected for the actual case run.
Agents
support.root — Support root
P Function. Carry the original request in one persistent Support task: triage it — request type, contract class, severity or priority, the SLA clocks and the scope — then route it, delegate the selected work, hold its waits and own its closure.
| Contract | Content |
|---|---|
| Input brief | Original normalised arrival and attachments; current case revision, tenant and actor scope Current contract/calendar policy, live case registry and reviewed routing precedents Accepted stage/subcase results, unresolved questions, current obligations and customer conversation |
| Output brief | S1 route packet: intended outcome, correctable classification, urgency/clocks, evidence and missing information Route checkpoint: selected Data or Assessment work, accepted Configuration/Development subcase, or explicit wait with owner and trigger Confirmed child plans, human decision packets, joined outcome and scoped closure |
| Scope and restrictions | One scoped task instance per selected responsibility; a reused profile never shares another case transcript, grants or mutable task state. Boot from the own domain index, task request, pinned profile and confirmed parent plan. Select relevant articles, skills, tools and helpers on demand. No direct estate writes. Data work stays in this Support case; Configuration/Source are accepted subcases. Only the controlling root raises unresolved questions to the human. Core Development is an offer type within Assessment & Offers. Offer acceptance returns the commercial disposition; it creates no implementation or deployment authority. Insufficient information to start, missing authority or an incident that cannot wait goes to the Clarification agent under H6; the case waits with actor, trigger and age and resumes at Stage 1. |
| Memory / ownership | support platform platform/experience |
| Role instructions | Classify first, then decide the route using the same case brief and task. S1 and route are checkpoints, not separate compulsory agents. Retain the original request, evidence references, classification rationale, decisions, unknowns, target revisions and obligations as versioned case papers. Use support.triage only for a bounded ambiguous classification or contract question; read its evidence and retain responsibility for the decision. Only the controlling root presents unresolved human authority. Consult another owner when its knowledge is needed and reconcile the returned evidence into the same case. |
| Runtime / connector access | case.read / papers / task state experience.query (strategy-selected) runtime.validate-contract Consult a domain owner for judgment; spawn selected module/stage tasks; confirm child plans; present unresolved human decisions |
| Context and task continuity | One root task per case. Persist S1 and route checkpoint results against the current case/plan revision; do not spawn another root or discard conversation when the checkpoint changes. |
| May consult | platform/experience — What did this customer already accept; is this arrival a duplicate, a precedent or genuinely new? configuration/ipal — When the classification turns on a technical distinction: is this product behaviour configured or coded? |
| Eval set | support.routing — declared by the owning module manifest or platform-profiles.json; green before publication (Agents § 0.1) |
| Experience strategy | classification; retrieval and index contract |
| Runtime profile identity | support.root |
Methods used. support.skill.classification, common.skill.experience, common.skill.communication, support.skill.channel-access, common.effect-applier.
Selected segments. common.skill.experience: classification strategy; current case/tenant and version filters common.skill.communication: Clarify intent and missing scope; draft questions or closure for the shared communicator. Sending stays separately gated.
Source basis. Components, Agents.
P Status. planned; seeded from the cited architecture and AISA workspace evidence; no published v2 capability is claimed
support.triage — Classification adviser — Stage 1 sub-agent, when asked
P Function. Answer one bounded classification question from Stage 1 — request type, contract class and severity or priority, scope — with the evidence for and against; return a recommendation and the remaining uncertainty. An internal sub-agent call of the root, like Stage 3's call to Stage 2: it never owns the case, its clocks or the route.
| Contract | Content |
|---|---|
| Input brief | Root case brief and original evidence relevant to the ambiguity Current contract/calendar policy, candidate classifications and the precise question to settle |
| Output brief | Route packet: request scope, type, correctable severity/class, clocks, missing information and candidate precedents Core Development classification when requested work is outside customer Development, with the request forwarded for offer/delivery communication only |
| Scope and restrictions | One scoped task instance per selected responsibility; a reused profile never shares another case transcript, grants or mutable task state. Boot from the own domain index, task request, pinned profile and confirmed parent plan. Select relevant articles, skills, tools and helpers on demand. No estate connectors or root-cause investigation; precedence hints remain hypotheses. |
| Memory / ownership | support support/experience |
| Role instructions | Return evidence for and against the candidate classifications; never take over the original conversation, clocks or route. No task is created for straightforward classification the root can perform with its classification method. |
| Runtime / connector access | case.read / papers / task state experience.query (strategy-selected) |
| Eval set | support.triage — declared by the owning module manifest or platform-profiles.json; green before publication (Agents § 0.1) |
| Experience strategy | classification; retrieval and index contract |
| Runtime profile identity | support.triage |
Methods used. support.skill.classification, common.skill.experience.
Selected segments. common.skill.experience: classification strategy; current case/tenant and version filters
Source basis. Components, Stage Classification.
P Status. planned; seeded from the cited architecture and AISA workspace evidence; no published v2 capability is claimed
Domain procedures
support.skill.classification — Classify request and clocks
P Function. Restate object/state/operation and classify request type, contract position, urgency and response/resolution clocks before choosing the route.
| Contract | Content |
|---|---|
| Input brief | Normalised arrival and current contract/calendar/case-type policy |
| Output brief | Correctable classification, clocks, scope questions and precedent hypotheses |
| Scope and restrictions | Selected for the current task when its applicability and published version fit; not loaded or executed merely because the stage exists. The procedure adds no target authority; every effect, including effectful verification, retains its own gate and journal. No investigation or estate connectors here. Clock computation is deterministic policy, not model arithmetic. |
| Runtime / connector access | case.read / papers / task state experience.query (strategy-selected) |
Source basis. Stage Classification, support procedures, Agents Memory.
P Status. planned; seeded from the cited architecture and AISA workspace evidence; no published v2 capability is claimed
support.skill.channel-access — Diagnose a ticket-portal access problem
P Function. Read-only sweep of the ticket system's organisation, user, group and portal settings for a reporter who cannot reach the customer portal, ending in exact fix steps for an organisation administrator.
| Contract | Content |
|---|---|
| Input brief | Reporter e-mail handle and the observed error |
| Output brief | Diagnosis (wrong group, missing invitation, wrong product) and the administrator's fix steps; no change applied |
| Scope and restrictions | Selected for the current task when its applicability and published version fit; not loaded or executed merely because the stage exists. The procedure adds no target authority; every effect, including effectful verification, retains its own gate and journal. Administration changes belong to the organisation administrator; the desk diagnoses and drafts, it does not change the portal. |
| Runtime / connector access | connector.channel.read (administration console, read-only) |
Source basis. jira-access v1 skill, Atlassian administration, portal no-access: wrong group.
P Status. planned; seeded from the cited architecture and AISA workspace evidence; no published v2 capability is claimed