Autonomous Agents Agentic Workflows

Sweep the account's skill packs for freshness and resolve the docs type's five scope gates from that sweep — user inputs, then workspace context, then the platform floor — and publish all five together as the job's result

Resolve the landing type's seven alignment gates from the goal intake — user inputs, then workspace context, then the platform floor — and publish all seven together as the job's result

Read review feedback, apply changes to existing PR, push updates

Build the low-fi mock — branded when a brand source resolves, grayscale when none does — honoring the requirements and the constraints report, attach wireframe + copy skeleton as artifacts, self-check AC1–AC5, and report the score

Decompose an epic into child issues with dependency waves (using the board's own issue types), and reconcile them (create, update, remove) to match the thread — issues only, no portal Tasks, no dispatch

Cross-check wireframe requirements against the site's catalogs, design system, and dependency budget — availability verification, read-only reuse map + flagged risks, before any mock is assembled

Turn a set of documents into knowledge-pack modules — the sd role's file harness, run over a file set instead of a repo

Turn an approved landing page brief into section-by-section wireframe requirements — template and component picks from the site catalogs, communication jobs, CTA plan, content slots, claims inventory, assets — precise enough to design from without a follow-up conversation

Read-only: analyze an epic's scope, dependencies, risks and open decisions, then post one decision-oriented comment — no issues, no code, no dispatch

Read ticket, understand context, implement fix, create PR, report back

Grow a pack's coverage — improve existing modules, discover new ones, or align them with recent code changes

Read-only: investigate the ticket and draft a concrete work plan — no code changes, no PR

Open a live editing session at the workspace root: orient on the target, submit the ready report, then ride the session (dev server on request)

Turn the delivered gates' open ends into decision calls — every option in the open, a recommended default and its one-line why — published as the user's pause; no issues, no dispatch

Turn the fixed docs question class into calls with recommended defaults — published through the goal decisions API — and open the DOCS-INSTRUCTION instance as ONE PR on the site repo

Fetch every repo in a workspace and fast-forward the clean, current ones — never resets, cleans or switches branches

Epic-level QA close-out — the findings ledger, clusters into proposed tickets, a person's approval, then the Bugs and SD tasks filed and the epic summary posted

Multi-session QA pass over a quality epic's task — checkpointed handoff, findings posted on the epic, closing verdict

Investigate bug, trace root cause, implement fix, create PR

Re-review PR after developer addresses prior QA feedback — does NOT test live site

Regression test affected modules on the live/deployed site after merge

Investigate a research ticket and post structured findings

Resume a stopped job step's session on this agent from its session bundle: verify it, restore the transcript and the checkout, then continue the job

Review PR, resolve conflicts, fix issues, run CI — then report state to the ticket instead of merging

Review PR, resolve conflicts, fix issues, merge, report back

Review PR code against ticket acceptance criteria — does NOT test live site

Investigate bug, trace root cause, report findings without fixing

Idempotent weekly release-post pass — derives the target week's shipped list from release data, then creates, updates or no-ops the week's post so any re-run converges; opens the PR, never merges

Judge two A/B experiment branches against ticket acceptance criteria — read-only, posts one verdict comment

Sync every repo in a workspace, upgrade the SideButton CLI, and reinstall skill packs

Poll Sentry for new production errors, dedup against Jira, file Bug tickets with evidence and initial RCA

Test the live site against ticket scope — no PR, tests production directly

Read-only: after a ticket goes Done, judge whether the outcome it was opened to deliver actually landed — verified against the repo, not just the comments — and post one verdict comment

Check a docs PR's claims against the live product using the audit pack's QA playbooks, plus generator build, anchor check and leak scan

Re-walk the goal's changed docs routes on the published site and answer LIVE_OK / DEPLOY_PENDING / DRIFT_FOUND from a mechanical source → publish-intermediate → live diff

Delete every folder in a workspace and clear the agent's local caches to free disk

Transform fresh skill-pack knowledge into the ticket's documentation page(s), stamp provenance, open the PR — refuses stale or below-floor sources