processminer-v2

Run an interactive session with a banking architect to develop the business-architecture layer of a process's target state — the capabilities the target process needs, the target applications that host them, and the Architecture Decision Records (ADRs) that justify the shape — into the process JSON as draft elements. Use this whenever the user wants to map capabilities, decide the target application landscape (build / buy / configure / keep), or record architecture decisions for a process — even if they don't say "domain architect".

Technical behavior test harness for Processminer's DTP Enhancer — the procedure-document (DTP) compare / regenerate / summary flow. Takes a process that already has a worked As-Is and an original ingested DTP, and drives it through dtp-regenerate, dtp-compare and dtp-summary via the running app's UI, exercising the finding-disposition paths (Open / Fix in DTP / Reconcile wiki), asserting that responses reflect correctly in the DTP Enhancer UI and the runtime store (`dtpReports`), and benchmarking speed per turn. Run ONLY when the user explicitly invokes /dogfood-dtp in the CLI. Never auto-route to it from the app's chat.

Technical behavior test harness for Processminer's Target / Transformation track. Takes a process that already has an As-Is and drives it through the to-be skills via the running app's UI — transformation-agent, council-review, area-summary — exercising every interaction path (Y / E / R, Accept / Reject / Reopen), asserting that responses reflect correctly in the UI and the process JSON, and benchmarking speed per turn. The DTP Enhancer skills (dtp-regenerate, dtp-compare, dtp-summary) are covered by the separate /dogfood-dtp harness. Run ONLY when the user explicitly invokes /dogfood-target in the CLI. Never auto-route to it from the app's chat.

Technical behavior test harness for Processminer skills. Creates a fresh process and drives it through the skill roster via the running app's UI, exercising every interaction path (Y / N / Deep Dive / Move On), asserting that skill responses reflect correctly in the UI and runtime state, and benchmarking execution speed per turn. Run ONLY when the user explicitly invokes /dogfood-run in the CLI. Never auto-route to it from the app's chat.

Add a single new element to a process wiki section, AI-drafted. Read the section's context, ask the SME in the chat what they want to add, research it in the wiki and — where useful — on the web, draft an initial proposal, refine it with the SME, and write it on approval. Use this whenever the user wants to add an entry or element to a section — a market trend, innovation idea, competitor, CX benchmark or any other element type.

Review an uploaded document and extract its content into the process wiki. Read the document, summarise it, ask the user to confirm, then record it as a source and extract its content into wiki elements — creating new ones, updating existing ones, verifying every draft against the source document, and flagging conflicts. Use this whenever a document has been uploaded to raw-sources/ for ingestion, or the user asks to ingest, extract or process an uploaded document into the wiki.

Walk a freshly-ingested process end to end as a meticulous process analyst — read the whole wiki, then challenge every current-state element in foundational order to tease out rework, and surface the pain points and missing controls a source document never states, approving each with the SME. Resumable: a stopped run picks up where it left off. Use this after a document has been ingested into a process, or whenever the user asks to start, resume or run the foundational run / foundational review of a process.

Run a lint pass over a process wiki — the consistency checkpoint. Check every element against its schema template, then sweep the whole process from all five perspectives for cross-section discrepancies and clarifying questions. Write the findings to the runtime store for the app's Review panel and re-open any approved element a finding implicates. Use this whenever the user asks to lint, run a lint pass, check the wiki for consistency, or review a process for issues.

Autonomously source the external client-experience layer of a process from the web — scan how competitor banks and fintechs run the same client journey, and gather industry CX benchmarks and client-expectation research, then fill the Competitor CX and CX Benchmarks sections with draft elements. Non-interactive: no SME questions, no approval loop. Invoked by a button or another skill. Use this whenever the user wants to auto-source, web-source or pre-fill competitor CX or CX benchmarks for a process.

Autonomously source the innovation perspective of a process from the web — search for market studies, analyst reports and trends, and scan what competitor banks and fintechs are doing, then fill the Market Trends, Competitor and Innovation Ideas sections with draft elements. Non-interactive: no SME questions, no approval loop. Invoked by a button or another skill. Use this whenever the user wants to auto-source, web-source or pre-fill market trends, competitor moves or innovation ideas for a process.

Autonomously source the regulatory perspective of a process from the web — search for the financial-services regulation, supervisory rules and guidance that govern the process, then fill the Regulation section with draft elements. Non-interactive: no SME questions, no approval loop. Invoked by a button or another skill. Use this whenever the user wants to auto-source, web-source or pre-fill the regulations that apply to a process.

Autonomously consolidate everything documented about a process — the As-Is, the risk & compliance picture, the client experience, the innovation work and the systems landscape — into a first-stub Target Process: draft target-state, transformation-decision and gap elements. Non-interactive: no SME questions, no approval loop. Invoked by a button or another skill. Use this whenever the user wants to auto-draft, pre-fill or stub the target state, the to-be design or the transformation of a process from the work already done.

Run an interactive elicitation session with a banking subject-matter expert to extract and document the client-experience perspective of a process — channels, touchpoints, moments of truth and client-facing friction points — into the file-backed process wiki as draft elements. Use this whenever the user wants to document the customer journey, map client touchpoints, capture the client experience or client friction of a process — even if they don't say "client journey specialist".

Run an interactive elicitation session with a banking subject-matter expert to extract and document the risk & regulatory perspective of a process — controls, regulations, compliance gaps and audit findings — into the file-backed process wiki as draft elements. Use this whenever the user wants to document the controls of a process, capture regulatory obligations, map compliance gaps or audit findings, or run a control / risk / compliance extraction session — even if they don't say "control compliance specialist".

Run an interactive session with a banking subject-matter expert to develop the forward-looking perspective of a process — market trends, what competitor banks and fintechs are doing, innovation ideas and the risks of pursuing them — into the file-backed process wiki as draft elements. Use this whenever the user wants to ideate improvements, refine market trends or competitor moves, or weigh innovation risks for a process — even if they don't say "innovation analyst".

Run an interactive elicitation session with a banking subject-matter expert to extract and document the As-Is process perspective — process steps, exceptions, pain points, process gaps, roles and metrics — as draft elements using Native AI authoring tools. Use this whenever the user wants to document a banking process, capture or map process steps from an SME, run a process-extraction or knowledge-elicitation session, or build out As-Is process documentation — even if they don't explicitly say "process specialist".

Run an interactive session with a banking architect to develop the technical layer of a process's target architecture — the integrations between target applications, the components inside them, the non-functional requirements (NFRs), and the migration phases that sequence the cutover — into the process JSON as draft elements. Use this whenever the user wants to design integrations, decompose applications into components, set NFRs, or plan the migration of a process — even if they don't say "solution architect".

Run an interactive session with a banking subject-matter expert to develop the Target Process of a process — the target state / to-be design, the transformation decisions to reach it and the gaps to close — into the file-backed process wiki as draft elements. Use this whenever the user wants to design, refine or lock in the target/to-be state, plan the transformation, weigh transformation decisions or work the gap resolution of a process — even if they don't say "transformation agent".

Conduct a complete QER process-documentation session for a banking process — select or create the process, capture its overview, then run each perspective specialist's elicitation in turn, review across perspectives, validate, and close out. Use this whenever the user wants to document a banking process end to end, run a full QER or knowledge-extraction session, start a process documentation session, or work a process across multiple perspectives — even if they don't explicitly say "qer-session".

Scaffold a new banking process in the wiki. Ask the user for the process name, draft a one-line description, a slug and an ID abbreviation for them to confirm, then create the process as a single strongly-typed JSON document with an empty overview. Use this whenever the user wants to create or set up a new process, start a process from scratch, or add a process to the wiki — even if they don't explicitly say "new-process".

Compare a chosen DTP (procedure document) against the corrected As-Is wiki and critically review it — surface every material discrepancy between the document and the analysis, and store the findings via the writeDtpComparison tool. This is review-only: no DTP is regenerated and no new artifact is written. Non- interactive: no SME questions, no approval loop. Invoked by the DTP Enhancer's "Select a source DTP" action. Use this whenever the user wants to compare, review or check an existing DTP against the wiki without rebuilding it.

Regenerate a process's DTP (procedure document) from the corrected As-Is wiki and critically review the original ingested DTP against it. Read the original document and the worked As-Is, rewrite the procedure from the wiki's current truth, surface every material discrepancy between the old document and the analysis, and store both via the writeDtpReport tool — a new versioned .md artifact plus the critical-review findings. Non-interactive: no SME questions, no approval loop. Invoked by a button. Use this whenever the user wants to regenerate, rebuild or re-issue the DTP from the As-Is, or critically review the original DTP against the wiki.

Write an executive-summary memo for one DTP comparison run — an Amazon-style narrative for leadership that says, in plain prose, how far the procedure document has drifted from the corrected As-Is and what matters most. Read the findings handed to you, frame them, and store the memo via the writeDtpSummary tool. Non-interactive: no SME questions, no approval loop. Invoked by the DTP Enhancer's "Generate executive summary" button. Use this whenever the user wants a leadership summary, memo or narrative of a DTP comparison.

Work through the open discussion comments on a wiki element with the SME — evaluate each comment's impact, incorporate the changes you agree on into the element, then post a closing summary into the discussion as the section's analyst. Use this whenever the user wants to review, act on or resolve the comments or notes left on an element.

Generate an executive summary of one area of a process wiki — As-Is Process, Risk & Compliance, Client Experience, Innovation, Target Process or IT Architecture — written as an Amazon-style narrative memo. Read every section in the area and write the memo into the process's `summaries` field for the app to render. Non-interactive: no SME questions, no approval loop. Invoked by a button. Use this whenever the user wants an executive summary of an area.

Run the target-state council review of a banking process — the five other perspective specialists (process, control & compliance, client journey, innovation, IT architecture) challenge the proposed target state from their own lens and write their feedback to the process's `targetReview` field for the SME to triage. Use this whenever the user wants to review, challenge or sense-check the target state / transformation of a process, run the council on the target, or get a cross-perspective review of the To-Be — collectively or one specialist at a time. Non-interactive: no SME questions, no approval loop; invoked by a button or by free chat.

Resolve the conflicts a document ingest flagged — where a re-ingested document contradicts content the wiki already holds. Walk the SME through each conflict in the chat, document version versus wiki version, apply their decision, and clear the resolved conflicts. Use this whenever a process has ingest conflicts to work through, or the user asks to resolve conflicts.