Pipeline run

dd96951b-e3e2-445d-a89e-f645216013c6

Pipeline LLM cost (USD)

API 1: $0.0021 API 2: $0.0002 API 3: $0.0000 Total: $0.0023

Client output enrichment

v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA description

Nature of work · Applied AI / ML Engineering

Build production AI systems for document intelligence, retrieval, and agentic workflows, focused on accurate extraction, analysis, and workflow automation for financial institutions.

"work across the core systems that power our product: document intelligence, retrieval, agentic workflows, and the infrastructure required to deploy them reliably in production"

Tech stack maturity

Mainstream Modern

AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)

3.20 / 5

✓ Title match

✓ Has AI skill

✓ AI skill (primary)

· AI skill (secondary)

· On AI team

· Builds AI products

vocab breakdown (legacy)

Assistants (×1): Claude, Cursor

Frameworks (×2): —

Models / concepts (×3): RAG, LLMs, agentic, multimodal, AI, Machine Learning

Evidence — skills matched in JD (5)

Machine Learning Document Intelligence Retrieval Agentic Workflows Workflow Automation

Skill cluster (2 dimension groups, role-scoped)

AI Governance and Model Security

Machine Learning

Cross-cutting / unaligned

Document Intelligence Retrieval Agentic Workflows Workflow Automation

Show KRA description ↓

As an Applied AI Engineer at Bynd, you will work across the core systems that power our product: document intelligence, retrieval, agentic workflows, and the infrastructure required to deploy them reliably in production. You will build systems that financial institutions depend on for high-accuracy extraction, analysis, and workflow automation.

Status: completed Created: 2026-05-13T06:11:07.429446Z Updated: 2026-05-13T06:11:13.923852Z API 3 duration: 3811 ms

Flow Current 3-step pipeline

1 POST /skills/extract-from-jd

2 POST /skills/extract-details

3 POST /skills/final-role-output

Role Chosen role & resolution

AI Engineer

slug: ai-engineer · id: 12 · source: db

The primary skills focus on machine learning and automation, which align with the role of an AI Engineer.

Resolution: in_db — role exists in library; skill↔dim and role↔dim links saved when applicable.

New skills

Skill↔dim saved

Role↔dim saved

Skipped

Job description

About the job
Why Bynd

Bynd is building the intelligence layer for financial services.

We work with leading investment banks, private equity firms, asset managers, lenders, and advisory teams to transform how they extract, analyze, and act on information buried across financial documents, filings, reports, and internal workflows.

We operate with the standards of a research team and the urgency of a product company. We care deeply about technical quality, product taste, and building things that get used.

The Role

You will build systems that financial institutions depend on for high-accuracy extraction, analysis, and workflow automation.

What You Will Need

Must-haves

Strong programming ability in Python and TypeScript
Experience integrating LLMs into production systems, including prompting, context management, structured outputs, and cost-performance tradeoffs
Experience building or working with document processing systems such as VLMs for OCR and layout parsing models
Comfort with cloud deployment and production systems, including containers, CI/CD, and Azure or GCP
Experience thinking carefully about system quality, including evaluation, observability, or failure analysis for complex AI workflows

Preferred

Experience with RAG systems, hybrid retrieval, reranking, and eval design
Experience with vision-language models or multimodal document understanding
Familiarity with Azure- or GCP-based AI infrastructure
Familiarity with financial services workflows such as investment banking, private equity, equity research, credit, or diligence
Experience building multi-step agentic systems or using modern agent tooling

Who You Are

You thrive in fast-moving environments and care deeply about the quality of what you build.
You are ambitious and energized by difficult problems. You like working on things that are technically hard, operationally messy, and valuable when solved well.
You are AI-native in how you work. Tools like Claude Code, Cursor, Codex, and modern model APIs are part of your everyday workflow. You know these tools are powerful, but you also understand where they fail and how to build with judgment around them.
You are an owner. You are autonomous, self-directed, and comfortable with ambiguity. You take responsibility for outcomes, not just tasks.
You are curious about the domain. You want to understand how financial professionals actually work, what makes a workflow painful, what accuracy really means in context, and why a product decision matters.

Skills from this JD

Each row merges API 1 extraction, API 2 library match / v3 orchestration (dimensions + locked dims), and API 3 persistence tags.

Machine Learning Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)

Canonical: Machine Learning id=2672 · machine-learning

Aliases — catalog

Kendo UI for Angular (CANONICAL) primary

Context tags (catalog)

Angular Kendo themes UI components charts component library customization data binding directives form controls grid performance optimization responsive design services state management validation

Stored enrichment (catalog DB)

Category: Framework
Sub-category: Ui Component Framework
Vendor: Progress Software Corporation
License: proprietary
Year introduced: 2017
Confidence: 0.92
Version strategy: NOT_APPLICABLE

Maturity reasoning: Appears in some Angular enterprise JDs, but far less often than Angular Material/PrimeNG; market signal is a specialized commercial UI suite with limited hiring volume.

Skill profile (library / DB)

Skill nature: CONCEPT
Volatility: STABLE
Typical lifespan: EVERGREEN
Category id: 2
Sub-category id: 2146
Extractable: True
Also category: False

Dimensions (API 2 worklist)

Project Delivery and Coordination Catalog dimension db id 366

Library dimension (catalog)
Version Control Systems Catalog dimension db id 365

Library dimension (catalog)

API 3 link attempts (this skill)

Dimension	Skill↔dim	Role↔dim	Outcome
Project Delivery and Coordination d_init_02	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Version Control Systems d_init_01	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

Document Intelligence Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)

Canonical: Document Intelligence id=2673 · document-intelligence

Aliases — catalog

DevExtreme Angular (CANONICAL) primary

Context tags (catalog)

API integration Angular DevExtreme UI components charting component lifecycle custom directives data visualization event handling form controls grid layout performance optimization responsive design state management theme customization

Stored enrichment (catalog DB)

Category: Framework
Sub-category: Ui Component Framework
Vendor: DevExpress
License: other_open
Year introduced: 2015
Confidence: 0.90
Version strategy: NOT_APPLICABLE

Maturity reasoning: DevExtreme Angular appears in a limited set of enterprise UI job postings and vendor docs, but far less often than Angular/React; it’s a specialized component suite rather than a mainstream framework.

Skill profile (library / DB)

Skill nature: PLATFORM
Volatility: EMERGING
Typical lifespan: EVERGREEN
Category id: 13
Sub-category id: 2182
Extractable: True
Also category: False

Dimensions (API 2 worklist)

Version Control Systems Catalog dimension db id 365

Library dimension (catalog)

API 3 link attempts (this skill)

Dimension	Skill↔dim	Role↔dim	Outcome
Version Control Systems d_init_01	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

Retrieval Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)

Canonical: Retrieval id=2674 · retrieval

Aliases — from this run (catalog unavailable)

Retrieval (CANONICAL)

Skill profile (library / DB)

Skill nature: CONCEPT
Volatility: STABLE
Typical lifespan: EVERGREEN
Category id: 2
Sub-category id: 2183
Extractable: True
Also category: False

Dimensions (API 2 worklist)

Context Management and Retrieval Catalog dimension db id 264

Library dimension (catalog)

Roles linked in library: AI Engineer

API 3 link attempts (this skill)

Dimension	Skill↔dim	Role↔dim	Outcome
Context Management and Retrieval context-management-and-retrieval	✓	✓	Existing dimension (library) · Role↔dimension saved

Agentic Workflows Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)

Canonical: Agentic Workflows id=2675 · agentic-workflows

Aliases — catalog

WebSocket (CANONICAL) primary

Context tags (catalog)

API JSON Pub/Sub Socket.IO WebRTC asynchronous bidirectional client-server event-driven long polling low latency low-latency message broker networking protocol pub/sub real-time streaming

Stored enrichment (catalog DB)

Category: Protocol
Sub-category: Real Time Communication Protocol
Year introduced: 2011
Confidence: 0.99
Version strategy: NOT_APPLICABLE

Maturity reasoning: WebSocket is broadly used for real-time apps and appears regularly in job descriptions for chat, trading, and live dashboards; it remains a standard browser/server protocol rather than a niche or sunset tech.

Skill profile (library / DB)

Skill nature: PATTERN
Volatility: EMERGING
Typical lifespan: EVERGREEN
Category id: 1
Sub-category id: 2184
Extractable: True
Also category: False

Dimensions (API 2 worklist)

Context Management and Retrieval Catalog dimension db id 264

Library dimension (catalog)

Roles linked in library: AI Engineer
Workflow Automation and Approvals Catalog dimension db id 211

Library dimension (catalog)

Roles linked in library: ServiceNOW Developer

API 3 link attempts (this skill)

Dimension	Skill↔dim	Role↔dim	Outcome
Context Management and Retrieval context-management-and-retrieval	✓	✓	Existing dimension (library) · Role↔dimension saved
Workflow Automation and Approvals workflow-automation-and-approvals	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

Workflow Automation Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)

Canonical: Workflow Automation id=2676 · workflow-automation

Aliases — from this run (catalog unavailable)

Workflow Automation (CANONICAL)

Skill profile (library / DB)

Skill nature: METHODOLOGY
Volatility: STABLE
Typical lifespan: EVERGREEN
Category id: 7
Sub-category id: 2185
Extractable: True
Also category: False

Dimensions (API 2 worklist)

Workflow Automation and Approvals Catalog dimension db id 211

Library dimension (catalog)

Roles linked in library: ServiceNOW Developer

API 3 link attempts (this skill)

Dimension	Skill↔dim	Role↔dim	Outcome
Workflow Automation and Approvals workflow-automation-and-approvals	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

All API 3 persistence rows

Same grid as the skill-extractor “Persistence items” table: one row per (skill × dimension) work item.

Skill	Tag	Dimension	Skill↔dim	Role↔dim	Outcome
Machine Learning	in_db	Project Delivery and Coordination d_init_02	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Machine Learning	in_db	Version Control Systems d_init_01	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Document Intelligence	in_db	Version Control Systems d_init_01	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Retrieval	in_db	Context Management and Retrieval context-management-and-retrieval	✓	✓	Existing dimension (library) · Role↔dimension saved
Agentic Workflows	in_db	Context Management and Retrieval context-management-and-retrieval	✓	✓	Existing dimension (library) · Role↔dimension saved
Agentic Workflows	in_db	Workflow Automation and Approvals workflow-automation-and-approvals	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Workflow Automation	in_db	Workflow Automation and Approvals workflow-automation-and-approvals	✓	—	Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

Library artifacts (this run)

No artifact rows for this run.

nano JD Parser — gpt-4.1-nano click to toggle

RoleApplied AI Engineer

CompanyBynd

DomainFinancial Services

JD type pass

Show raw JSON

{
  "JD_type": "pass",
  "about_company": {
    "source_marker": {
      "first_5_words": "Bynd is building the intelligence",
      "last_5_words": "things that get used."
    },
    "text": "Bynd is building the intelligence layer for financial services.\n\nWe work with leading investment banks, private equity firms, asset managers, lenders, and advisory teams to transform how they extract, analyze, and act on information buried across financial documents, filings, reports, and internal workflows.\n\nWe operate with the standards of a research team and the urgency of a product company. We care deeply about technical quality, product taste, and building things that get used.",
    "word_count": 86
  },
  "certifications": [],
  "company_name": "Bynd",
  "ctc": null,
  "domain": {
    "primary": {
      "aliases": [
        "FinTech",
        "Investment Banking",
        "Private Equity",
        "Asset Management",
        "Lending",
        "Advisory"
      ],
      "domain": "Financial Services"
    },
    "secondary": null
  },
  "education": [],
  "experience": {
    "max": null,
    "min": null,
    "raw": null
  },
  "job_locations": [],
  "role": "Applied AI Engineer",
  "role_archetype": "Engineering",
  "roles_and_responsibilities": [
    {
      "bullet_count": 0,
      "heading": "Role Overview",
      "heading_was_present": false,
      "source_marker": {
        "first_5_words": "As an Applied AI Engineer",
        "last_5_words": "deploy them reliably in production."
      },
      "text": "As an Applied AI Engineer at Bynd, you will work across the core systems that power our product: document intelligence, retrieval, agentic workflows, and the infrastructure required to deploy them reliably in production.",
      "word_count": 31
    },
    {
      "bullet_count": 0,
      "heading": "Responsibilities",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "You will build systems that",
        "last_5_words": "workflow automation."
      },
      "text": "You will build systems that financial institutions depend on for high-accuracy extraction, analysis, and workflow automation.",
      "word_count": 20
    }
  ],
  "urls": []
}

API 1 — extract-from-jd click to toggle

{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Machine Learning"
    },
    {
      "is_primary": true,
      "skill_name": "Document Intelligence"
    },
    {
      "is_primary": true,
      "skill_name": "Retrieval"
    },
    {
      "is_primary": true,
      "skill_name": "Agentic Workflows"
    },
    {
      "is_primary": true,
      "skill_name": "Workflow Automation"
    }
  ],
  "jd_role": {
    "display_name": "Applied AI Engineer",
    "rationale": null,
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": {
      "source_marker": {
        "first_5_words": "Bynd is building the intelligence",
        "last_5_words": "things that get used."
      },
      "text": "Bynd is building the intelligence layer for financial services.\n\nWe work with leading investment banks, private equity firms, asset managers, lenders, and advisory teams to transform how they extract, analyze, and act on information buried across financial documents, filings, reports, and internal workflows.\n\nWe operate with the standards of a research team and the urgency of a product company. We care deeply about technical quality, product taste, and building things that get used.",
      "word_count": 86
    },
    "certifications": [],
    "company_name": "Bynd",
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [
          "FinTech",
          "Investment Banking",
          "Private Equity",
          "Asset Management",
          "Lending",
          "Advisory"
        ],
        "domain": "Financial Services"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": null,
      "min": null,
      "raw": null
    },
    "job_locations": [],
    "role": "Applied AI Engineer",
    "role_archetype": "Engineering",
    "roles_and_responsibilities": [
      {
        "bullet_count": 0,
        "heading": "Role Overview",
        "heading_was_present": false,
        "source_marker": {
          "first_5_words": "As an Applied AI Engineer",
          "last_5_words": "deploy them reliably in production."
        },
        "text": "As an Applied AI Engineer at Bynd, you will work across the core systems that power our product: document intelligence, retrieval, agentic workflows, and the infrastructure required to deploy them reliably in production.",
        "word_count": 31
      },
      {
        "bullet_count": 0,
        "heading": "Responsibilities",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "You will build systems that",
          "last_5_words": "workflow automation."
        },
        "text": "You will build systems that financial institutions depend on for high-accuracy extraction, analysis, and workflow automation.",
        "word_count": 20
      }
    ],
    "urls": []
  },
  "run_id": null
}

API 2 — extract-details

{
  "alias_matches": [
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3647,
      "existing_alias_text": "Machine Learning",
      "input_term": "Machine Learning",
      "matched_canonical": {
        "category_id": 2,
        "display_name": "Machine Learning",
        "id": 2672,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "machine-learning",
        "sub_category_id": 2146,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3648,
      "existing_alias_text": "Document Intelligence",
      "input_term": "Document Intelligence",
      "matched_canonical": {
        "category_id": 13,
        "display_name": "Document Intelligence",
        "id": 2673,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "document-intelligence",
        "sub_category_id": 2182,
        "typical_lifespan": "EVERGREEN",
        "volatility": "EMERGING"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3649,
      "existing_alias_text": "Retrieval",
      "input_term": "Retrieval",
      "matched_canonical": {
        "category_id": 2,
        "display_name": "Retrieval",
        "id": 2674,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "retrieval",
        "sub_category_id": 2183,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3650,
      "existing_alias_text": "Agentic Workflows",
      "input_term": "Agentic Workflows",
      "matched_canonical": {
        "category_id": 1,
        "display_name": "Agentic Workflows",
        "id": 2675,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PATTERN",
        "slug": "agentic-workflows",
        "sub_category_id": 2184,
        "typical_lifespan": "EVERGREEN",
        "volatility": "EMERGING"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 3651,
      "existing_alias_text": "Workflow Automation",
      "input_term": "Workflow Automation",
      "matched_canonical": {
        "category_id": 7,
        "display_name": "Workflow Automation",
        "id": 2676,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "workflow-automation",
        "sub_category_id": 2185,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    }
  ],
  "candidate_roles": [
    {
      "display_name": "AI Engineer",
      "id": 12,
      "rationale": null,
      "role_archetype": null,
      "slug": "ai-engineer",
      "source": "db"
    },
    {
      "display_name": "ServiceNOW Developer",
      "id": 24,
      "rationale": null,
      "role_archetype": null,
      "slug": "servicenow-developer",
      "source": "db"
    }
  ],
  "chosen_role": {
    "display_name": "AI Engineer",
    "id": 12,
    "rationale": "The primary skills focus on machine learning and automation, which align with the role of an AI Engineer.",
    "role_archetype": null,
    "slug": "ai-engineer",
    "source": "db"
  },
  "dimensions": [
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Project Delivery and Coordination",
        "id": 366,
        "rationale": "Coordination practices for organizing work, tracking progress, and aligning stakeholders across a delivery effort. Agile fits here when used as a team execution framework for managing scope, cadence, and collaboration.",
        "slug": "d_init_02",
        "source": "db"
      },
      "input_skill": "Machine Learning",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Version Control Systems",
        "id": 365,
        "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "Machine Learning",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Version Control Systems",
        "id": 365,
        "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
        "slug": "d_init_01",
        "source": "db"
      },
      "input_skill": "Document Intelligence",
      "llm_role": null,
      "roles_from_db": []
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Context Management and Retrieval",
        "id": 264,
        "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
        "slug": "context-management-and-retrieval",
        "source": "db"
      },
      "input_skill": "Retrieval",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "AI Engineer",
          "id": 12,
          "rationale": null,
          "role_archetype": null,
          "slug": "ai-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Context Management and Retrieval",
        "id": 264,
        "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
        "slug": "context-management-and-retrieval",
        "source": "db"
      },
      "input_skill": "Agentic Workflows",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "AI Engineer",
          "id": 12,
          "rationale": null,
          "role_archetype": null,
          "slug": "ai-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Workflow Automation and Approvals",
        "id": 211,
        "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
        "slug": "workflow-automation-and-approvals",
        "source": "db"
      },
      "input_skill": "Agentic Workflows",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "ServiceNOW Developer",
          "id": 24,
          "rationale": null,
          "role_archetype": null,
          "slug": "servicenow-developer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Workflow Automation and Approvals",
        "id": 211,
        "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
        "slug": "workflow-automation-and-approvals",
        "source": "db"
      },
      "input_skill": "Workflow Automation",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "ServiceNOW Developer",
          "id": 24,
          "rationale": null,
          "role_archetype": null,
          "slug": "servicenow-developer",
          "source": "db"
        }
      ]
    }
  ],
  "input_final_skills": [
    "Machine Learning",
    "Document Intelligence",
    "Retrieval",
    "Agentic Workflows",
    "Workflow Automation"
  ],
  "input_llm_skills": [
    "Machine Learning",
    "Document Intelligence",
    "Retrieval",
    "Agentic Workflows",
    "Workflow Automation"
  ],
  "new_aliases_persisted": 0,
  "run_id": "dd96951b-e3e2-445d-a89e-f645216013c6",
  "skills_detail": [
    {
      "aliases_in_db": [
        {
          "alias_text": "Machine Learning",
          "alias_type": "CANONICAL",
          "id": 3647,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 2,
        "display_name": "Machine Learning",
        "id": 2672,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "machine-learning",
        "sub_category_id": 2146,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Project Delivery and Coordination",
            "id": 366,
            "rationale": "Coordination practices for organizing work, tracking progress, and aligning stakeholders across a delivery effort. Agile fits here when used as a team execution framework for managing scope, cadence, and collaboration.",
            "slug": "d_init_02",
            "source": "db"
          },
          "input_skill": "Machine Learning",
          "llm_role": null,
          "roles_from_db": []
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Version Control Systems",
            "id": 365,
            "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "Machine Learning",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "Machine Learning",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Document Intelligence",
          "alias_type": "CANONICAL",
          "id": 3648,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 13,
        "display_name": "Document Intelligence",
        "id": 2673,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "document-intelligence",
        "sub_category_id": 2182,
        "typical_lifespan": "EVERGREEN",
        "volatility": "EMERGING"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Version Control Systems",
            "id": 365,
            "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
            "slug": "d_init_01",
            "source": "db"
          },
          "input_skill": "Document Intelligence",
          "llm_role": null,
          "roles_from_db": []
        }
      ],
      "input_skill": "Document Intelligence",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Retrieval",
          "alias_type": "CANONICAL",
          "id": 3649,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 2,
        "display_name": "Retrieval",
        "id": 2674,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "CONCEPT",
        "slug": "retrieval",
        "sub_category_id": 2183,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Context Management and Retrieval",
            "id": 264,
            "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
            "slug": "context-management-and-retrieval",
            "source": "db"
          },
          "input_skill": "Retrieval",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "AI Engineer",
              "id": 12,
              "rationale": null,
              "role_archetype": null,
              "slug": "ai-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Retrieval",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Agentic Workflows",
          "alias_type": "CANONICAL",
          "id": 3650,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 1,
        "display_name": "Agentic Workflows",
        "id": 2675,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PATTERN",
        "slug": "agentic-workflows",
        "sub_category_id": 2184,
        "typical_lifespan": "EVERGREEN",
        "volatility": "EMERGING"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Context Management and Retrieval",
            "id": 264,
            "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
            "slug": "context-management-and-retrieval",
            "source": "db"
          },
          "input_skill": "Agentic Workflows",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "AI Engineer",
              "id": 12,
              "rationale": null,
              "role_archetype": null,
              "slug": "ai-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Workflow Automation and Approvals",
            "id": 211,
            "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
            "slug": "workflow-automation-and-approvals",
            "source": "db"
          },
          "input_skill": "Agentic Workflows",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "ServiceNOW Developer",
              "id": 24,
              "rationale": null,
              "role_archetype": null,
              "slug": "servicenow-developer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Agentic Workflows",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "Workflow Automation",
          "alias_type": "CANONICAL",
          "id": 3651,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 7,
        "display_name": "Workflow Automation",
        "id": 2676,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "workflow-automation",
        "sub_category_id": 2185,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Workflow Automation and Approvals",
            "id": 211,
            "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
            "slug": "workflow-automation-and-approvals",
            "source": "db"
          },
          "input_skill": "Workflow Automation",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "ServiceNOW Developer",
              "id": 24,
              "rationale": null,
              "role_archetype": null,
              "slug": "servicenow-developer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Workflow Automation",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": []
}

API 3 — final-role-output

{
  "chosen_role": {
    "display_name": "AI Engineer",
    "id": 12,
    "rationale": "The primary skills focus on machine learning and automation, which align with the role of an AI Engineer.",
    "role_archetype": null,
    "slug": "ai-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "Machine Learning",
      "tag": "in_db"
    },
    {
      "skill": "Document Intelligence",
      "tag": "in_db"
    },
    {
      "skill": "Retrieval",
      "tag": "in_db"
    },
    {
      "skill": "Agentic Workflows",
      "tag": "in_db"
    },
    {
      "skill": "Workflow Automation",
      "tag": "in_db"
    }
  ],
  "persistence": {
    "items": [
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Project Delivery and Coordination",
          "id": 366,
          "rationale": "Coordination practices for organizing work, tracking progress, and aligning stakeholders across a delivery effort. Agile fits here when used as a team execution framework for managing scope, cadence, and collaboration.",
          "slug": "d_init_02",
          "source": "db"
        },
        "dimension_id": 366,
        "input_skill": "Machine Learning",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2672,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Version Control Systems",
          "id": 365,
          "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 365,
        "input_skill": "Machine Learning",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2672,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Version Control Systems",
          "id": 365,
          "rationale": "Tools and workflows for tracking source changes, branching, merging, and collaborating on code history. Git belongs here because it is the canonical distributed version control system used to manage revisions and coordinate team development.",
          "slug": "d_init_01",
          "source": "db"
        },
        "dimension_id": 365,
        "input_skill": "Document Intelligence",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [],
        "skill_dimension_saved": true,
        "skill_id": 2673,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Context Management and Retrieval",
          "id": 264,
          "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
          "slug": "context-management-and-retrieval",
          "source": "db"
        },
        "dimension_id": 264,
        "input_skill": "Retrieval",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "AI Engineer",
            "id": 12,
            "rationale": null,
            "role_archetype": null,
            "slug": "ai-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2674,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Context Management and Retrieval",
          "id": 264,
          "rationale": "Preparing, selecting, and packaging context for model calls so responses stay relevant and grounded. This is a distinct cluster because AI features often depend on what information is included, summarized, or retrieved at call time.",
          "slug": "context-management-and-retrieval",
          "source": "db"
        },
        "dimension_id": 264,
        "input_skill": "Agentic Workflows",
        "llm_role": null,
        "matched_chosen_role": true,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension saved",
        "role_dimension_saved": true,
        "roles_from_db": [
          {
            "display_name": "AI Engineer",
            "id": 12,
            "rationale": null,
            "role_archetype": null,
            "slug": "ai-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2675,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Workflow Automation and Approvals",
          "id": 211,
          "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
          "slug": "workflow-automation-and-approvals",
          "source": "db"
        },
        "dimension_id": 211,
        "input_skill": "Agentic Workflows",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "ServiceNOW Developer",
            "id": 24,
            "rationale": null,
            "role_archetype": null,
            "slug": "servicenow-developer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2675,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 12,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Workflow Automation and Approvals",
          "id": 211,
          "rationale": "Designing and configuring workflow-driven process automation, including approvals, task routing, and lifecycle transitions. This cluster is coherent because ServiceNow developers often implement process logic rather than standalone application code.",
          "slug": "workflow-automation-and-approvals",
          "source": "db"
        },
        "dimension_id": 211,
        "input_skill": "Workflow Automation",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "ServiceNOW Developer",
            "id": 24,
            "rationale": null,
            "role_archetype": null,
            "slug": "servicenow-developer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 2676,
        "skill_tag": "in_db",
        "skipped_reason": null
      }
    ],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "dd96951b-e3e2-445d-a89e-f645216013c6"
}

LLM Calls

Every model call made for this run, in pipeline order. Click a card to see the model's response.

Loading…