{"domain":"agents.diezx.ai","count":1,"changes":[{"captured_at":"2026-08-22T03:07:43","card_hash":"59709362279535390c27acbc2d992aad0c1838c83f35464c6643c204fe683ca8","previous_card_hash":null,"diff":{"skills_added":[{"id":"analyze_pipeline_bottlenecks","name":"Analyze Pipeline Bottlenecks","description":"Computes per-stage open/age/loss-rate metrics and flags bottlenecks (high aging, high loss rate, value concentration) with severity. Returns a narrative prioritizing the most painful one.","tags":["crm","bottlenecks","analysis","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"assign_implementation_champion","name":"Assign Implementation Champion","description":"Picks the best person to own deployment of a given automation. Filters candidates deterministically (AI champions first, department match, role match) then the LLM ranks the top shortlist and returns its pick with rationale. Useful when an external agent has the org chart but needs Diego to recommend *who* should ship this.","tags":["execution","assignment","champions","org-chart","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"assign_implementation_champion_v2","name":"Assign Implementation Champion (v2 — process + candidates resolved server-side)","description":"Same output as assign_implementation_champion, but resolves the process and the candidate pool (active company users with name/department/title/AI-champion flag) from MongoDB given a processId. companyId is derived from the JWT.","tags":["execution","assignment","champions","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"compare_departments","name":"Compare Departments","description":"Side-by-side comparison of departments by avg score, process count, automation rate, and portfolio balance.","tags":["analysis","comparison","departments","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"compare_departments_v2","name":"Compare Departments (v2 — company-scoped)","description":"Same output as compare_departments, but resolves the portfolio from company context (MongoDB) instead of requiring the caller to pass it. Use this variant when calling from external A2A agents that do not have diezX DB access. companyId derived from JWT; body override must match (else 403).","tags":["analysis","comparison","departments","v2","company-scoped","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"connect_interview_to_process","name":"Connect Interview to Process","description":"Maps pain points from discovery interviews to processes in the portfolio. Flags discrepancies (high frustration vs low score).","tags":["interviews","mapping","discrepancy-detection","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"connect_interview_to_process_v2","name":"Connect Interview to Process (v2 — company-scoped)","description":"Same output as connect_interview_to_process. Interviews still come in the input (they are caller-specific), but the portfolio is resolved from company context (MongoDB). Use this variant when calling from external A2A agents that do not have diezX DB access.","tags":["interviews","mapping","discrepancy-detection","v2","company-scoped","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"connect_process_to_financial_outcome","name":"Connect Process to Financial Outcome","description":"Takes a processId from the diezX portfolio plus ERP context and estimates the annualized dollar savings of automating it, expressed as both an absolute number and as a % of operating expenses.","tags":["erp","roi","process-impact","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"connect_process_to_revenue_outcome","name":"Connect Process to Revenue Outcome","description":"Takes a processId from the diezX portfolio and CRM context, then estimates the annualized revenue lift of automating it (via win-rate uplift × annualized deal attempts × avg deal size).","tags":["crm","roi","process-impact","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"design_automation","name":"Design Automation","description":"Given a process (name, department, frequency, systems involved, why-it-matters), produces an executable AutomationDesign: ordered proposedFlow, flowGraph (adjacency list), systemsUsed (constrained to companyTools when provided), approvalAssignments with suggested roles, and executionModel. The LLM does the design synthesis; a deterministic post-processor sanitizes the output (drops out-of-bounds edges, self-loops, duplicates, systems not in companyTools, truncates flows >30 steps, infers a linear graph if the model omits edges) and reports every fix in postValidationFixes so the caller can audit.","tags":["execution","design","workflow","creative","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"diagnose_execution_issue","name":"Diagnose Execution Issue","description":"Given a symptom (free-text, error message, or execution complaint) plus optionally the AutomationDesign + companyTools + recent logs, returns up to 4 ranked hypotheses with category, confidence, and a concrete suggestedFix per hypothesis. A deterministic categorizer pre-detects common failure modes via regex (auth_or_credential, rate_limit, permission_denied, timeout_or_slow, data_shape_mismatch, integration_missing) and tries to identify the failed step from \"step N\" / \"paso N\" references. The LLM ranks and produces hypotheses, aligned to the pre-detected categories when evidence is strong.","tags":["execution","diagnosis","troubleshooting","continuous-operation","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"diagnose_execution_issue_v2","name":"Diagnose Execution Issue (v2 — process resolved server-side)","description":"Same output as diagnose_execution_issue, but resolves the AutomationDesign and companyTools from MongoDB given a processId. The symptom is still required in the body — that is the caller-specific context.","tags":["execution","diagnosis","troubleshooting","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"explain_pareto_breakdown","name":"Explain Pareto Breakdown","description":"Identifies the top X% of processes by score that account for the bulk of estimated impact (Pareto 20/80).","tags":["execution","pareto","prioritization","analysis","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"explain_pareto_breakdown_v2","name":"Explain Pareto Breakdown (v2 — company-scoped)","description":"Same output as explain_pareto_breakdown, but resolves the portfolio from company context (MongoDB) instead of requiring the caller to pass it. Use this variant when calling from external A2A agents that do not have diezX DB access.","tags":["execution","pareto","prioritization","analysis","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"explain_pl_variance","name":"Explain P&L Variance","description":"Compares two ERP P&L periods and returns deterministic deltas (income, expenses, net income, top driver accounts) plus a narrative explaining what is driving the change.","tags":["erp","variance","comparison","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"explain_process_score","name":"Explain Process Score","description":"Explains why a specific process ranked at a given score, citing scoring weights and process attributes.","tags":["prioritization","scoring","explanation","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"flag_financial_anomalies","name":"Flag Financial Anomalies","description":"Compares two ERP P&L periods and surfaces anomalies (expense spikes, revenue drops, net loss, expense concentration, unexplained accounts) ranked by severity, plus a narrative recommending where to investigate first.","tags":["erp","anomalies","risk","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"flag_validation_gaps","name":"Flag Validation Gaps","description":"Returns departments where AI-suggested processes lack human validation, ranked by risk.","tags":["data-quality","validation","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"forecast_cash_runway","name":"Forecast Cash Runway","description":"Projects months of runway from the company's last N months of net income (avg + worst-month stress test) and current cash on hand. Returns avg/worst/best month, runway months, zero-cash date, and a narrative read on whether the company is in a safe / watch / critical zone.","tags":["erp","cash","forecast","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"forecast_pipeline_velocity","name":"Forecast Pipeline Velocity","description":"Builds a baseline of cycle time + annualized throughput from closed-won deals and projects the upside of a cycle-time reduction (default 20%). Includes confidence based on sample size.","tags":["crm","forecast","velocity","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"generate_custom_app_brief","name":"Generate Custom App Brief","description":"Produces a CustomAppBrief for processes that do NOT fit a linear workflow (dashboards, complex forms, internal mini-apps). Output matches the diezX CustomAppBrief shape: appName, objective, targetUsers, dataSources (constrained to companyTools when provided), coreFeatures (capped at 12), screens (capped at 8) with React/Tailwind component hints, estimatedEffort enum, and goalsAlignment (filtered to caller-supplied goals). The brief is mostly LLM-emitted; a deterministic post-processor caps lists and filters dataSources/goals against allowlists. All fixes recorded in postValidationFixes.","tags":["execution","custom-app","design","product-brief","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"generate_custom_app_brief_v2","name":"Generate Custom App Brief (v2 — process resolved server-side)","description":"Same output as generate_custom_app_brief, but resolves the process and companyTools from MongoDB given a processId. goalsAlignment and targetUserRoles can still be supplied in the body (they are caller-specific context).","tags":["execution","custom-app","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"generate_n8n_workflow","name":"Generate n8n Workflow Skeleton","description":"Given an AutomationDesign, produces an n8n workflow SKELETON: nodes mapped to native n8n node types using the diezX NATIVE_NODES registry (Hubspot, Salesforce, Slack, Gmail, etc.), with trigger variant for the first step where available, Wait node for approvals, Set node for pure data shaping, and HTTP fallback when no native node matches. Connections derived from the AutomationDesign flowGraph. Per-step nodeMapping is fully deterministic — the LLM only writes a short narrative explaining required credentials and HTTP fallback steps. The output is NOT a fully-valid n8n .json (positions and parameters need a developer pass) but it IS the right starting point.","tags":["execution","n8n","workflow-generation","integrations","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"generate_n8n_workflow_v2","name":"Generate n8n Workflow Skeleton (v2 — process resolved server-side)","description":"Same output as generate_n8n_workflow, but resolves the AutomationDesign + companyTools from MongoDB given a processId. Errors with 400 if the process has no automationDesign yet (suggests running design_automation first).","tags":["execution","n8n","workflow-generation","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"recommend_engagement_automations","name":"Recommend Engagement Automations","description":"Detects engagement gaps in the CRM (stalled deals, unattended contacts, missing owners, low-activity reps) and proposes one concrete automation per gap, ordered by severity.","tags":["crm","engagement","automation","recommendation","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"recommend_next_processes","name":"Recommend or Challenge Next Processes","description":"Recommends what to automate first from the process portfolio. If proposedOrder is omitted, returns top-N processes to automate next; if proposedOrder is provided, pressure-tests it against portfolio data and returns agreement/concerns/counter-proposal.","tags":["execution","prioritization","recommendation","challenge","roadmap","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"recommend_next_processes_v2","name":"Recommend or Challenge Next Processes (v2 — company-scoped)","description":"Same output as recommend_next_processes, but resolves the portfolio from company context (MongoDB) instead of requiring the caller to pass it. Use this variant when calling from external A2A agents that do not have diezX DB access. companyId is derived from the bearer JWT; passing it explicitly in the body is supported but must match (else 403).","tags":["execution","prioritization","recommendation","challenge","roadmap","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"score_lead_qualification_health","name":"Score Lead Qualification Health","description":"Scores how well the inbound lead qualification process is operating: contact owner coverage, follow-up coverage, response-time SLO adherence, and lead→won conversion. Returns a 0-10 composite score with a letter grade.","tags":["crm","lead-qualification","scoring","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"score_new_process","name":"Score New Process","description":"Estimates a score for a candidate process not yet in the portfolio, by invoking the diezX scoring engine and benchmarking against similar processes.","tags":["scoring","estimation","what-if","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"summarize_corporate_card_spend","name":"Summarize Corporate Card Spend (Mendel)","description":"Pulls Mendel corporate-card transactions for the period and returns deterministic metrics (total spend, average transaction, top categories, top cardholders, optional growth vs comparison period) plus a narrative summary.","tags":["mendel","corporate-cards","spend-analysis","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"summarize_financial_health","name":"Summarize Financial Health","description":"Pulls a P&L snapshot from the connected ERP for the requested period and returns deterministic metrics (income, expenses, margin, top accounts) plus a narrative summary.","tags":["erp","financial-health","narrative","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"summarize_pipeline_health","name":"Summarize Pipeline Health","description":"Pulls a snapshot of deals/owners from the connected CRM and returns deterministic pipeline metrics (volume, value, win rate, stage distribution, aging) plus a narrative summary.","tags":["crm","pipeline","narrative","company-scoped","agent:sofia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"summarize_unverified_expenses","name":"Summarize Unverified Mendel Expenses","description":"Pulls Mendel corporate-card transactions for the period, isolates the ones missing a receipt (`payment.ticketAttached: false`), and returns deterministic metrics (total pending amount, count, % of total spend, oldest pending in days, top employees pending) plus a narrative summary aimed at the close-of-month review.","tags":["mendel","corporate-cards","compliance","close-of-month","company-scoped","agent:daniel"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"surface_feedback_backlog","name":"Surface Feedback Backlog","description":"Lists processes pending review or with unresolved feedback comments.","tags":["collaboration","review","backlog","agent:lucia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"validate_automation_design","name":"Validate Automation Design","description":"Pre-deploy gate. Given an AutomationDesign, runs structural checks (orphan approvals, flowGraph integrity, cycles, missing assignees, systems not present in companyTools) and returns an issues list + a narrative recommendation. The issues list is deterministic; the narrative is LLM-generated.","tags":["execution","validation","pre-deploy","quality","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"validate_automation_design_v2","name":"Validate Automation Design (v2 — process resolved server-side)","description":"Same output as validate_automation_design, but resolves the AutomationDesign and companyTools from MongoDB given a processId. companyId is derived from the JWT (or passed explicitly in body, must match else 403). Use this variant when calling from external A2A agents that have a process reference but no DB access.","tags":["execution","validation","pre-deploy","v2","company-scoped","agent:diego"],"inputModes":["application/json"],"outputModes":["application/json"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"DiezXSuite"},{"field":"description","before":null,"after":"A Business Observability platform for mid-market companies: it shows how your company operates in real time and lets you act from there. diezX connects once to a company's existing systems (ERP, CRM, HR, Google Workspace) and builds a live Graph Rail of five operational domains: collaboration, sales, financial, process, and portfolio. On top of that graph, four A2A 0.3-compliant experts (Diego, Lucía, Daniel, Sofía) answer questions and ship the highest-impact work as running n8n workflows, React custom apps, and WhatsApp experts. Each expert queries its domain graph before answering. Hosted on Google Cloud (Cloud Run) with inference on Vertex AI. Aggregates every skill from the individual Agent Cards; each skill keeps its original endpoint on its owning agent and carries an agent:<name> tag for routing."},{"field":"version","before":null,"after":"2.0.0"},{"field":"protocolVersion","before":null,"after":"0.3.0"},{"field":"url","before":null,"after":"https://agents.diezx.ai/api/a2a/suite"},{"field":"documentationUrl","before":null,"after":"https://app.diezx.ai/docs/agents"},{"field":"preferredTransport","before":null,"after":"HTTP+JSON"}],"other_changed":true,"is_empty":false,"human_summary":"added 36 skills · name ∅ → DiezXSuite · description ∅ → A Business Observability platform for mi · version ∅ → 2.0.0 · protocolVersion ∅ → 0.3.0 · url ∅ → https://agents.diezx.ai/api/a2a/suite · documentationUrl ∅ → https://app.diezx.ai/docs/agents · preferredTransport ∅ → HTTP+JSON"}}]}