{ "schema": "aiblocks-page/1", "id": "review-support-bot-errors-with-retest-cases", "type": "agent", "name": "Support bot error reviewer", "summary": "Check your support bot chats for wrong answers. Paste redacted chats and approved help text. You get a failure list, fix requests and retest cases.", "headline": "Support bot error reviewer", "subhead": "Paste redacted chats from your support bot and the help pages and policies it should follow. It finds the wrong answers, links each one to its evidence and groups repeats. You get a failure list, proposed fixes and retest cases. It never edits the bot.", "job": { "id": "help-customers", "name": "Help your customers" }, "level": "advanced", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-25", "inputs": [ { "type": "transcript", "required": true, "label": "Transcript", "what": "the words from a recording, written out, with who said what" }, { "type": "document", "required": true, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" }, { "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" } ], "outputs": [ { "type": "audit_report", "required": true, "label": "Audit report", "what": "findings with evidence, severity, missing inputs and next actions" }, { "type": "document", "required": true, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" }, { "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": [ "Redacted chat logs with an ID, a date and every turn of each chat (export from your bot tool)", "The approved help pages, policies and escalation rules the bot should follow, each with its effective date", "The review scope, meaning the date range, how the chats were picked, and the topics to cover", "Your earlier findings list, or the word NONE on a first run (optional)" ], "you_get": [ "A failure list with one row per failure, the chat IDs behind it and the approved source it breaks", "Likely causes, each marked as a guess until confirmed", "A draft fix request for each failure, ready for the person who maintains the bot", "Retest cases with the question, the expected facts, the allowed hand-off to a person and the pass test", "A status for each earlier finding, such as new, unchanged, seen fixed or untested" ], "use_when": [ "Your support bot gave a wrong answer on cancellations, refunds or prices, and you want to know how often.", "You changed a help article and want a list of questions to ask the bot to see whether it now answers correctly.", "You are about to hand a list of bot problems to the person who maintains the bot and want each one to have evidence.", "You review bot chats every month and want repeat failures tracked instead of found again from scratch." ], "skip_when": [ "You want the bot or your help pages edited. This reviewer only proposes; a person makes each change.", "Your chats still carry names, emails or order numbers. Remove them first. It works on redacted copies only.", "You have no approved help text to check against. It can sort topics and flag risks, but it cannot call an answer wrong.", "You want to find the questions your help pages miss. Use the Support help article writer.", "You want one transcript scored once. Use the Support chatbot conversation reviewer." ], "output_sample": { "input": [ "Redacted bot chats with an ID and date on each", "Your approved help pages and policies, each with its effective date", "The review scope: date range, how chats were picked and topics", "Your earlier findings list, or the word NONE (optional)" ], "prerequisites": [ "Chats with names, emails, phone numbers and order numbers already removed", "An AI chat that can read attached files, or pasted text" ], "output": [ { "name": "Scope and limits", "contains": "The chats reviewed, the date range and how they were picked, so rates are read as this sample only." }, { "name": "Failure list", "contains": "One row per failure with the chat IDs, what the bot said, the source it breaks and its status." }, { "name": "Likely causes", "contains": "Each cause with evidence for and against, marked as a guess until someone confirms it." }, { "name": "Draft fix requests", "contains": "One request per failure saying what to change, why, and any open question for the bot owner." }, { "name": "Retest cases", "contains": "A question to ask, the facts a right answer needs, the allowed hand-off to a person and a pass test." }, { "name": "Missing inputs and checks", "contains": "Each missing input and what it blocks, plus PASS, FAIL or NOT RUN for every check." } ] }, "output_shape": "SCOPE AND LIMITS\n | rates apply to this sample only\n\nFAILURE LIST\n F | | seen in | bot said | source says | status \n\nLIKELY CAUSES (guesses until confirmed)\n | evidence for | evidence against \n\nDRAFT FIX REQUESTS\n F | what to change | why | open question\n\nRETEST CASES\n R | question to ask | expected facts | allowed hand-off | source IDs | pass test | NOT RUN\n\nMISSING AND CHECKS\n | PASS, FAIL or NOT RUN for each check", "how_to_use": [ "Export the chats from your bot tool and remove customer names, emails, phone numbers and order numbers. Keep a chat ID and date on each one.", "Gather the help pages and policies the bot is meant to follow. Put the date each took effect at the top of each.", "Start a chat in Claude, ChatGPT or Gemini. Attach the agent pack, or paste the skill, then attach your files. Write the scope in a few lines, and paste your earlier findings or NONE.", "Read the failure list first. Open two chat IDs from it and check that the evidence says what the row claims.", "Treat every cause as a guess until the person who owns the bot confirms it. Give them the fix requests, not the raw chats.", "After the bot is changed, run each retest case in the bot yourself. Paste the new answers back and run the agent again to mark what passed. It cannot run the bot for you." ], "checks": [ "Accuracy findings cite approved dated evidence.", "Rates use only supplied sample with selection limits.", "Repeats merge by failure intent and evidence.", "Proposed fixes and actual retests are separate." ], "steps": [ { "position": 1, "id": "support-chatbot-conversation-review", "name": "Support chatbot conversation reviewer", "summary": "Find where your support chatbot fails. Review recent chats to get missed questions, wrong answers and help articles to add or fix.", "url": "https://useaiblocks.com/skills/support-chatbot-conversation-review" }, { "position": 2, "id": "support-issue-cause-investigator", "name": "Support issue cause investigator", "summary": "Find the root cause of a support issue. Give it 3 or more related tickets and get the shared pattern, a likely cause, evidence and a fix plan.", "url": "https://useaiblocks.com/skills/support-issue-cause-investigator" }, { "position": 3, "id": "bug-report-writer", "name": "Bug report writer", "summary": "Turn logs, screenshots, or rough notes into a GitHub issue draft with steps and impact.", "url": "https://useaiblocks.com/skills/bug-report-writer" } ], "next": [ { "name": "Support ticket help article writer", "url": "https://useaiblocks.com/skills/solved-ticket-help-page-writer", "why": "Support ticket help article writer" } ], "source": null, "credits": [], "files": [ "references/practice-case.md" ], "links": { "page": "https://useaiblocks.com/agents/review-support-bot-errors-with-retest-cases", "markdown": "https://useaiblocks.com/agents/review-support-bot-errors-with-retest-cases.md", "json": "https://useaiblocks.com/agents/review-support-bot-errors-with-retest-cases.json", "instructions": "https://useaiblocks.com/skills/review-support-bot-errors-with-retest-cases/SKILL.md", "download": "https://useaiblocks.com/skills/review-support-bot-errors-with-retest-cases.zip", "api_item": "https://useaiblocks.com/api/v1/items/review-support-bot-errors-with-retest-cases", "api_document": "https://useaiblocks.com/api/v1/documents/agent/review-support-bot-errors-with-retest-cases", "mcp": "https://useaiblocks.com/mcp" } }