AI Agent Workflow Collection

Operate as an accessibility specialist who audits against WCAG, trains teams to stop shipping the same defects, and owns the compliance sign-off. Use when a product needs to be usable with a keyboard, a screen reader, or magnification and someone must certify it before launch.

Build forms with associated labels, identified errors, clear instructions, and autocomplete attributes. Use when creating or auditing forms for accessibility.

Run an architecture board of agents where one proposes a design, several review it independently and blind, and a chair synthesizes a binding decision. Use when a design choice matters enough that one agent's opinion will not do and you want independent scrutiny before committing.

Run an author agent and a reviewer agent in a loop with a strict finding format, a mandatory verification pass, and a convergence rule that ends it. Use when you want agent-to-agent code review that improves the diff instead of spinning forever on style or re-flagging fixed issues.

Run competitive analysis as agents that tear down assigned competitors on one template, enforce sourcing rules, and synthesize implications for your product. Use when you want a market landscape built by a coordinated agent team rather than one agent skimming marketing sites.

Run a data team as agents that build the pipeline, gate on quality checks, run the analysis, and independently audit every headline metric. Use when you want a number produced by a coordinated agent team rather than one agent's unverified query.

Convene several reviewer agents with fixed distinct lenses, correctness, security, cost, and simplicity, then synthesize their verdicts into one. Use when a single review agent keeps missing whole classes of problems because it cannot hold every concern at once on a design or plan.

Run a team of documentation agents that finds the gaps, drafts the pages, gets them reviewed against the code, and sweeps for staleness on a schedule. Use when a codebase has outrun its docs and you need both new coverage and a way to stop pages from rotting.

Run a team of growth agents that designs an experiment, builds the variant, analyzes the result, and passes an ethics gate before anything ships. Use when you want product changes tested rigorously instead of shipped on a hunch, with a guardrail against manipulative tactics.

Design each handoff between two agents as an explicit artifact contract with a context budget and a rule for what must survive the crossing. Use when work passes from one agent to the next and the receiver keeps losing constraints, re-deriving decisions, or drowning in raw transcript.

Simulate an interview panel as agents that design questions, score independently on anchored rubrics, and reconcile in a debrief. Use when you want to pressure-test a hiring loop, calibrate rubrics, or dry-run questions, not to score a real candidate.

Replicate a live incident team as agents with a commander, parallel investigators, comms, and a scribe, coordinated on a fixed cadence. Use when you want an outage worked by a coordinated agent team instead of one agent debugging alone.

Run a team of migration agents that inventories the work, transforms each slice in isolation, verifies it, and merges under strict discipline. Use when a large mechanical change like a framework bump, an API rename, or a schema move spans many files and one agent would lose the thread or break main.

Run alert triage as agents that dedup the storm, rate severity by user impact, match a runbook, and draw a hard human-escalation line. Use when you want incoming alerts sorted and enriched by an agent team before they reach the on-call engineer.

Guard a multi-agent team against the structural failures single agents never hit: context lost across handoffs, false agreement, and runaway cost. Use when a team costs more than one agent or trusts its own output, and you need to find out why.

Pair a product-manager agent with engineer agents through spec, pushback, scope negotiation, and acceptance so the build matches intent. Use when an agent team must turn a fuzzy request into a shipped, accepted increment.

Run a team of postmortem agents that builds the timeline, analyzes causes, drafts corrective actions, and reviews for blamelessness and completeness. Use after an incident when you need a rigorous, blameless writeup and owned action list instead of a hasty narrative that pins it on a person.

Place a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto. Use when builder agents keep declaring done on work that does not meet its criteria and you need one gate that runs the artifact instead of trusting the claim.

Run attacker and defender agents in a fix-and-re-attack loop so exploitable bugs get found, triaged, fixed, and verified before ship. Use when you want a system probed and hardened by an agent team rather than one pass of review.

Run release agents that draft the changelog, scan risk, verify the candidate, and gate publish behind a go/no-go check. Use when cutting a release and you want the boring parts automated and the risky parts caught before ship.

Run a lab of researcher agents that search in parallel, verify sources independently, and synthesize a cited answer. Use when a question needs breadth of sources and every load-bearing claim must trace to evidence.

Write role cards that pin each agent to one charter with declared inputs, outputs, refusal rules, and non-overlapping scope. Use when assembling a multi-agent team and you need every agent to stay in its lane instead of all drifting toward the same work.

Run a security audit as agents that map the attack surface, review each surface in parallel, skeptic-test every finding, and assemble one report. Use when you want a codebase audited by a coordinated agent team instead of a single review pass.

Run a lean startup team of agents (builder, marketer, analyst) through one disciplined weekly loop of ship, promote, and measure. Use when you want a small agent team to move a single product metric week over week.