Research — Autonomous Agents Agentic Workflow

schema_version: 1
id: agent_pm_research
title: "Research"
description: "Investigate a research ticket and post structured findings"
overview: |
  A PM agent investigates the subject of a research ticket — competitive intelligence, customer or market research, due diligence, vendor evaluation, anything where the deliverable is structured findings rather than code. The ticket description defines investigation areas, success criteria, and the expected deliverable format.

  The agent pursues interesting leads beyond the original scope when warranted. Absence of public data is itself reported as a finding. Findings post as a single structured comment back to the ticket.

category:
  level: pipeline
  domain: research

metadata:
  agent: true
  role: pm

params:
  agentic_app:
    type: string
    default: "cc"
    description: "Agent-app slug selecting the per-run env file ~/.agent-env.d/<slug> (AAP-C); 'cc'/subscription clears provider vars"
  ticket_url:
    type: string
    description: "Jira ticket URL"
  hint:
    type: string
    default: ""
    description: "Optional extra instructions for the agent"
  entry_path:
    type: string
    default: "~/workspace"
    description: "Working directory for the agent"

steps:
  - type: terminal.open
    title: "Agent: PM Research"
    cwd: "{{entry_path}}"
  - type: terminal.run
    cmd: |
      source ~/.agent-env
      # AAP-C (SCRUM-1506) + AAP-17 (SCRUM-1653): clear EVERY provider var an agent-app can deliver so
      # none hijacks/poisons a subscription run. A stray global ANTHROPIC_MODEL / ANTHROPIC_SMALL_FAST_MODEL
      # needs no CLAUDE_CODE_USE_* flag, so the old ${!CLAUDE_CODE_USE_@} glob never caught it — it survived
      # into the run and 404-ed aux/small-fast calls against api.anthropic.com. This explicit list mirrors
      # AGENT_APP_ENV_KEYS 1:1 (the-assistant website/src/lib/cloud/agent-app-env.ts — the single source of
      # truth; a parity test in each repo guards the two from drifting). Explicit over a glob: the union has
      # non-ANTHROPIC_ members (AWS_REGION, AWS_PROFILE, CLOUD_ML_REGION, CLAUDE_CODE_MAX_OUTPUT_TOKENS) and
      # a ${!AWS_@} glob would over-clear unrelated creds. Then source the per-run app env by slug when it
      # exists; no file => subscription/default. base/19-secrets stages ~/.agent-env.d/<slug>.
      unset \
        ANTHROPIC_API_KEY ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN \
        CLAUDE_CODE_USE_BEDROCK AWS_REGION AWS_PROFILE ANTHROPIC_MODEL \
        ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION ANTHROPIC_SMALL_FAST_MODEL CLAUDE_CODE_MAX_OUTPUT_TOKENS \
        CLAUDE_CODE_USE_VERTEX CLOUD_ML_REGION ANTHROPIC_VERTEX_PROJECT_ID ANTHROPIC_VERTEX_BASE_URL \
        CLAUDE_CODE_USE_FOUNDRY ANTHROPIC_FOUNDRY_RESOURCE ANTHROPIC_FOUNDRY_BASE_URL \
        ANTHROPIC_DEFAULT_OPUS_MODEL ANTHROPIC_DEFAULT_SONNET_MODEL ANTHROPIC_DEFAULT_HAIKU_MODEL
      if [ -f "$HOME/.agent-env.d/{{agentic_app}}" ]; then
        source "$HOME/.agent-env.d/{{agentic_app}}"
      fi
      claude --dangerously-skip-permissions "$(cat <<'SB_PROMPT'
      read ticket with attachments and all comments - {{ticket_url}}. also read the parent epic if any. if it fails, stop and report the error.
      load skill packs for relevant domains. investigate. for each finding capture source URL, verbatim quote where available, and confidence (High/Medium/Low). absence of public data is itself a finding.
      {{hint}}
      if you produced a chart, dataset, or report file, you may publish it via the publish_artifact tool and cite the returned download link alongside the source URLs; otherwise save it under ~/workspace/artifacts/ for post-run collection.
      write one comment to the ticket with: findings organized per the deliverable spec, every claim cited, confidence ratings, surprises and counter-evidence flagged.
      SB_PROMPT
      )"