AI Agent Workflow Collection

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

Build a structured account plan for any key customer or target account. Use when asked to create an account plan, key account strategy, strategic account review, or territory plan. Produces a complete account plan with relationship map, growth opportunities, risks, and 90-day action plan.

Get back into a locked or hacked account the right way — the official recovery routes, what proof you'll need, and how to re-secure it so it doesn't happen again. Use when asked I'm locked out of my account, my account got hacked, help me recover my [email/social/bank] account, or I lost access to 2FA. Produces the official recovery path for the account type, the identity proof to prepare, a re-securing checklist for after you're back in, and warnings about fake 'recovery' services and support scams.

Simulate the acquirer's diligence team hunting for reasons to cut your price — their internal red-flags memo with a price-chip estimate per finding. Use when asked to red-team my company before a sale, how will an acquirer attack our valuation, pre-diligence audit, or what will DD find. Produces the acquirer's internal memo (revenue quality, key-person, tech debt, concentration, legal) and a debrief on which flags are fixable before a process.

Turn a skill's recommendations into real, executed actions — open the tickets, file the issues, post the updates — safely: dry-run preview, risk-classified, approval-gated, then recorded back to the brain. Use when asked to act on a plan, file tickets from a checklist, create issues from a PRD, execute the recommended next steps, or wire a skill's output into GitHub/Linear/Slack. Produces a dry-run actions plan with per-action risk, executes only after approval via the connected action MCP, and logs what was done. Nothing acts silently.

Enforce the simplest meeting rule that works — no agenda, no meeting — with the three-line agenda format (purpose, decisions sought, pre-reads), the 24-hour rule, and the graceful cancel scripts. Use when asked write an agenda for this meeting, should this meeting happen, our meetings have no agendas, or cancel this meeting politely. Produces the three-line agenda, the happen-or-cancel verdict, the cancel/convert scripts, and the team norm rollout.

Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.

Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pricing, to price an agent/API tier, or to defend revenue as customers automate their own usage. Produces a pricing migration plan: the new value metric, fences, agent-tier design, cannibalisation math, and a phased migration for existing customers. For general pricing and packaging strategy use pricing-strategy.

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective actions after an LLM failure. Produces a structured postmortem with trace reconstruction, a root-cause layer analysis, and corrective actions including a permanent regression case. For non-AI production incidents use incident-postmortem.

Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what to log for an LLM app, design agent tracing or spans, define quality and cost monitors, or answer 'how do we know if the agent is misbehaving?'. Produces an observability spec with a trace schema, metric definitions with owners and alert thresholds, sampling and retention policy, and a privacy note for logged content.

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready, to audit a site or API for AI usability, to prepare for agentic traffic, or when agents keep failing against your product. Produces a scored readiness report with per-surface findings and a prioritised fix list. For optimising a single article for AI citation use aeo-optimizer; for designing the MCP server itself use mcp-server-spec.

Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the handover for its successor (human or agent). Use when decommissioning an agent or bot, switching agent vendors, ending an AI pilot, or when someone asks 'what did this thing have access to?'. Produces a severance checklist, an access-revocation table, a memory disposition record, and a successor handover.

Assess whether and how someone can safely stay in their own home as they age — the home hazards, the support gaps, and the modifications and services that make it work. Use when asked can my parent stay in their home safely, aging in place assessment, is it safe for them to live alone, or what do we need for them to stay home. Produces a room-by-room safety read (fall hazards, accessibility), an honest look at the daily-living and support gaps, the modifications and services that could close them, warning signs that home may no longer be safe, and how to raise it respectfully — helping a family make a clear-eyed, dignity-preserving decision. Not medical advice.

Prepare the conversations with aging parents that everyone postpones — the driving talk, the money talk, the care-options talk, the moving talk — each with an opener that doesn't ambush, a dignity-first script, rehearsal against realistic resistance, and the fallback when it goes badly. Use when someone says 'I need to talk to my dad about driving', 'my mum won't discuss her finances', 'we need to talk about care', or is dreading a visit for exactly this reason. Produces the conversation plan, a rehearsal, and the small-steps fallback. A preparation tool, not family therapy — and it says so when the situation needs more.

Run a club, PTA, or association AGM that finishes on time and holds up later — the notice and agenda done right, a quorum plan, minutes that capture decisions not conversations, elections without awkwardness, and the follow-up that makes decisions real. Use when a volunteer says 'I have to run the AGM', 'what goes in the agenda', 'nobody comes to our meetings', or 'our elections are a mess'. Produces the notice, agenda, chair's script, minutes template, and quorum rescue plan.

Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, and how to run the review conversation. Use when reviewing someone whose work is heavily AI-assisted, when output volume stopped meaning anything, when calibrating a team with uneven AI adoption, or when writing review criteria for the AI era. Produces review guidance: a what-measures-whom analysis, rewritten criteria, calibration rules for mixed-adoption teams, and conversation scripts. For the general review document use performance-review; for redesigning the role itself use role-redesign-for-ai.

Audit a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content library, audit AI-written content quality, explain why content engagement or rankings dropped after scaling with AI, or set a quality bar for AI-assisted publishing. Produces an audited inventory with per-piece verdicts, the detection signals used, a triage plan, and a publishing quality gate that prevents recurrence. For a single article's AI-citability use aeo-optimizer; for the strategy itself use content-calendar or seo-content-brief.

Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are mediocre, or how do I get it right the first time. Produces the specific context this task needs (who/what/constraints/examples/format), a reusable primer you can paste ahead of the request, the difference between a starved prompt and a well-briefed one, and what to leave out — turning vague back-and-forth into a strong first result.

Decide when and how your product and communications must (or should) label AI-generated content, and write the disclosure policy — surface-by-surface rules, exact label wording, and the review trigger for regulations like the EU AI Act's transparency obligations. Use when asked 'do we have to label AI content', 'write our AI disclosure policy', 'are we covered for the AI Act', or when marketing/support/product start shipping AI-generated output. Produces a disclosure policy with a per-surface matrix and ready-to-use label copy. Not legal advice.

Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.

Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human evals, a pass bar, and a regression gate.

Check AI output before you trust or use it — where it's likely wrong, what to verify, and how to catch confident-sounding errors. Use when asked can I trust this AI answer, how do I verify what AI told me, fact-check this AI output, or is this AI response reliable. Produces a risk read on the specific output (the claims most likely to be wrong or made up), the parts that need independent verification vs the parts that are low-risk, how to actually verify each, the tells of AI hallucination and overconfidence, and a habit for building verification into your AI use — because AI is confidently wrong often enough that unchecked trust is a real risk.

Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.