{ "schema": "aiblocks-page/1", "id": "agency-testing-workflow-optimizer", "type": "agent", "name": "Workflow improvement reviewer", "summary": "Improve one work process. Get a step map, ranked bottlenecks, what to automate and small tests to try, from your numbers.", "headline": "Workflow improvement reviewer", "subhead": "Describe one process step by step, with who does each step and how long it takes. It maps the flow, ranks the bottlenecks, picks steps worth automating and plans small tests of each fix. You get a workflow review you can act on this month.", "job": { "id": "organise-work", "name": "Run meetings, notes and plans" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "source_text", "required": false, "label": "Source text", "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link" }, { "type": "spreadsheet", "required": false, "label": "Spreadsheet", "what": "a spreadsheet with its data, formulas and charts" } ], "outputs": [ { "type": "audit_report", "required": true, "label": "Audit report", "what": "findings with evidence, severity, missing inputs and next actions" }, { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" } ], "you_give": [ "One process, in plain words, with the steps in order and who does each one", "Time per step, split into work time and waiting time (rough numbers are fine)", "How often the process runs, and what goes wrong, such as errors or redo", "The tools used at each step, such as email, a spreadsheet or a ticket system", "Your goal, such as faster turnaround, fewer errors or less manual work", "An export with real times, such as ticket dates (optional)" ], "you_get": [ "A step map of the process as it runs today, with times and who does what", "A ranked list of bottlenecks, each with evidence, effect and effort to fix", "A short list of steps that suit automation, and ones that should stay with a person", "A set of small tests to run, each with one change, an owner, a measure and a trial length", "Savings worked out from your numbers, with the sums shown", "Facts still missing and what to time first" ], "use_when": [ "Work moves slowly between steps or people, such as approvals, handoffs or review queues.", "Your team does the same manual task every week, and you want to know what is worth automating.", "You have a quality problem, such as rework or errors at one step, and want a short list of fixes to test.", "You must explain to a boss or client why a process is slow and what you plan to change." ], "skip_when": [ "You want the root cause of a slow process, with baseline numbers measured first. Use the Operations Manager agent.", "You only want each step marked as value or waste, fast. Use the Process waste finder.", "You want to see why deadlines slip, week after week. Use the Project delay test reviewer.", "You want the automation itself set up in Zapier or Make. Use the Automation flow sketcher after this review." ], "output_sample": { "input": [ "One process, step by step, with who does each step", "Time per step, work time and waiting time", "How often it runs and what goes wrong", "Your goal, and a ticket or task export (optional)" ], "output": [ { "name": "Workflow review", "contains": "The process, your goal, how often it runs and how many steps it has." }, { "name": "Current flow", "contains": "Each step with who does it, work time, wait time, errors and the tool used." }, { "name": "Bottlenecks", "contains": "Steps that hold up the flow, ranked by effect and effort, with your numbers as evidence." }, { "name": "Automation candidates", "contains": "Rule-based steps that suit a tool, and judgment steps that should stay with a person." }, { "name": "Tests to run", "contains": "Each fix as one change, owner, measure, trial length and the result that counts as success." }, { "name": "Savings from your numbers", "contains": "Time or cost saved, with the sum shown, or \"not enough data\" if numbers are missing." }, { "name": "Rollout notes and facts missing", "contains": "Who is affected and what they need, plus the numbers still to measure." } ] }, "output_shape": "WORKFLOW REVIEW\n Process | Goal | Runs | Steps \n\nCURRENT FLOW\n | | | | | \n\nBOTTLENECKS (ranked)\n | | | \n\nAUTOMATION CANDIDATES\n | | \n\nTESTS TO RUN\n | | | | \n\nSAVINGS FROM YOUR NUMBERS\n | \n\nROLLOUT NOTES AND FACTS MISSING\n | ", "how_to_use": [ "Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.", "Describe one process, step by step, as it runs now, not as it should run. Add who does each step and the time it takes, even if rough.", "Say your goal and how often the process runs. Attach a ticket or task export if you have one. No code is needed.", "Read the bottleneck list first. Check each one with the people who do the work, and fix the map if it is wrong.", "Pick one or two tests, not all. Run them for the trial length and measure the same number before and after.", "Ask the Automation flow sketcher to lay out any step you decide to automate." ], "checks": [ "The result addresses your actual task and cites the evidence used.", "Examples, role-play experience and targets are kept separate from verified results.", "Claims of tests, memory, tool access or completed actions match what actually happened." ], "next": [ { "name": "Task list manager", "url": "https://useaiblocks.com/skills/task-list-keeper", "why": "Task list manager" } ], "source": { "by": "Michael Sitarzewski and Agency Agents contributors", "repo": "msitarzewski/agency-agents", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/testing/testing-workflow-optimizer.md", "licence": "MIT", "original_name": "Workflow Optimizer", "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219" }, "credits": [ { "title": "Workflow Optimizer", "by": "Michael Sitarzewski and Agency Agents contributors", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/testing/testing-workflow-optimizer.md", "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions." } ], "files": [ "LICENSE", "references/source-agent.md", "SETUP.md", "source.json" ], "links": { "page": "https://useaiblocks.com/agents/agency-testing-workflow-optimizer", "markdown": "https://useaiblocks.com/agents/agency-testing-workflow-optimizer.md", "json": "https://useaiblocks.com/agents/agency-testing-workflow-optimizer.json", "instructions": "https://useaiblocks.com/skills/agency-testing-workflow-optimizer/SKILL.md", "download": "https://useaiblocks.com/skills/agency-testing-workflow-optimizer.zip", "api_item": "https://useaiblocks.com/api/v1/items/agency-testing-workflow-optimizer", "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-testing-workflow-optimizer", "mcp": "https://useaiblocks.com/mcp" } }